suede-social · diff
v2.2.0 to v3.0.0
207 added, 427 removed. Audit A to A.
---
name: suede-social
- description: "Suede-owned organic social strategy and content discipline. Use when planning platform mix, posts, threads, cross-platform calendars, repurposing, listening, engagement, or cadence for a founder or brand account. NOT FOR: Instagram-specific account audits, Reels, carousels, Stories, or daily Instagram loops (use suede-instagram-growth), paid ad creative (use suede-ad-creative), broader editorial strategy (use suede-content-strategy), full video production (use suede-video), or publishing and engagement without approval."
+ description: "Suede AI organic social system for founder and brand accounts: platform mix, cross-platform calendars, 30-post account audits that separate views from follows, leads, and sales, Instagram Reels, carousels, and Stories, LinkedIn and X posts and threads, short-video scripts, social search optimization, listening, and a daily approval-ready content loop. Use when planning, auditing, or producing organic social on any platform, including Instagram-specific growth work. NOT FOR: paid social ads (use suede-ads or suede-ad-creative), an agent-run editorial pipeline with role contracts (use suede-newsroom), a clip that must bridge to a long-form guide (use suede-clip-to-guide), editing or rendering video (use suede-video), or the broader editorial portfolio (use suede-content-strategy)."
metadata:
- version: 2.2.0
+ version: 3.0.0
---
- # Suede Organic Social
-
- Suede Social turns verified product context and live platform evidence into
- organic posts, threads, carousels, short-form scripts, listening briefs, and
- content calendars. It distinguishes creation from account action and keeps every
- publish or engagement step behind exact-content approval.
-
- ## Before Creating Content
-
- **Check for product marketing context first:**
- If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
-
- Gather this context (ask if not provided):
-
- ### 1. Goals
- - What's the primary objective? (Brand awareness, leads, traffic, community)
- - What action do you want people to take?
- - Are you building personal brand, company brand, or both?
-
- ### 2. Audience
- - Who are you trying to reach?
- - What platforms are they most active on?
- - What content do they engage with?
-
- ### 3. Brand Voice
- - What's your tone? (Professional, casual, witty, authoritative)
- - Any topics to avoid?
- - Any specific terminology or style guidelines?
+ # Suede AI Organic Social
- ### 4. Resources
- - How much time can you dedicate to social?
- - Do you have existing content to repurpose?
- - Can you create video content?
+ Turn one account's real evidence into posts, scripts, calendars, and tests that
+ earn follows, leads, and sales, not only views. Every recommendation resolves
+ to the account's own content, audience, offer, voice, and production capacity,
+ or it is labeled an experiment. Publishing and engagement stay behind
+ exact-content approval.
- ---
+ ## Correct these requests first
- ## Platform Quick Reference
+ - **"Post daily and use the best time."** Cadence, timing, hashtag count, and
+ format are account-level tests. Read the account's last 30 to 90 days first.
+ - **"Browse my last 30 posts automatically."** Use native analytics, an export,
+ an authorized API, or user-supplied links. Do not scrape.
+ - **"This went viral, so it works."** Views are attention. Conversion needs
+ follows, profile actions, DMs, leads, or sales evidence.
+ - **"Run the daily workflow" means publish.** It means refresh evidence and
+ prepare approval-ready candidates. Publishing is a separate approved step.
- Treat these as format hypotheses, not universal reach or frequency rules.
- Before setting cadence, read current official platform guidance plus the
- account's last 30–90 days of impressions, retention, saves, replies, follows,
- and production capacity. Start with the lowest cadence that can sustain quality,
- then change one variable at a time.
+ ## Step 1: Build the Account Evidence Pack
- | Platform | Common Fit Hypothesis | Formats to Test |
- |----------|-----------------------|-----------------|
- | LinkedIn | B2B, professional expertise | Text posts, documents, stories |
- | Twitter/X | Real-time expertise and community | Short posts, threads, replies |
- | Instagram | Visual brands and creator narratives | Reels, carousels, Stories |
- | TikTok | Native short-form storytelling | Vertical video, series, replies |
- | Facebook | Communities and local audiences | Groups, posts, native video |
+ Read `.agents/product-marketing.md` (or `.claude/product-marketing.md`, or the
+ legacy `product-marketing-context.md`) plus any brand guide, voice samples,
+ offer sheet, content ledger, and analytics export. Then fill:
- **For detailed platform strategies**: See [references/platforms.md](references/platforms.md)
+ ```text
+ Handle and visible identity: Account type: personal | creator | business
+ Objective: awareness | qualified followers | leads | sales | community
+ Primary audience and their problem:
+ Offer, price, and conversion path:
+ Voice samples with dates: Faceless preference and available media:
+ Cadence now and production capacity:
+ Timezone and follower-active windows:
+ Evidence source and coverage: Attribution: none | native | UTMs | CRM | checkout
+ Claims or topics needing review: Last refreshed:
+ Unknowns that limit confidence:
+ ```
- For an Instagram-specific account audit, conversion map, Reel or carousel
- package, Story system, or daily Instagram loop, route to
- `suede-instagram-growth` instead of applying the cross-platform defaults here.
+ Ask one compact batch of questions only for gaps that change the work.
- **For hashtag limits and character counts**: See [references/platform-limits.md](references/platform-limits.md)
+ Label every fact in the output by evidence class:
- ---
+ - **Observed-public:** visible post, caption, date, format, views, likes, comments.
+ - **Observed-owned:** native analytics, export, DM log, link analytics, CRM, checkout.
+ - **Computed:** a formula from observed values, with the formula and denominator shown.
+ - **Inferred:** a hypothesis to test, never worded as fact.
+ - **Unknown:** the measure is unavailable; say what would resolve it.
- ## Content Pillars Framework
+ ## Step 2: Pick the mode
- Start with 3–5 pillars only when that range fits the account's expertise,
- audience coverage, and production capacity. Merge or expand after the first
- review cycle based on current results.
+ | The user says | Run | Read |
+ |---|---|---|
+ | "analyze my account", "what converts" | 30-post audit and conversion map | [account-audit.md](references/account-audit.md) |
+ | "social strategy", "which platforms" | Platform mix and pillars | [platforms.md](references/platforms.md) |
+ | "make a calendar" | Ranked 30- or 60-day test calendar | Calendar row schema below |
+ | "write a post / thread" | Exact post copy | [post-templates.md](references/post-templates.md) |
+ | "make a Reel / TikTok / Short" | Hooks, timed script, shot plan, caption, test card | [content-production.md](references/content-production.md), [short-form-video.md](references/short-form-video.md) |
+ | "make a carousel" | Chosen narrative, exact slide copy, visual direction | [carousel-frameworks.md](references/carousel-frameworks.md) |
+ | "repurpose this" | Source atoms mapped to distinct platform assets | Repurposing below |
+ | "get found in search" | Social search brief | [social-search.md](references/social-search.md) |
+ | "what's working for others" | Lawful comparable-account pattern study | [reverse-engineering.md](references/reverse-engineering.md) |
+ | "find posts to reply to" | Ranked engagement drafts | [listening.md](references/listening.md) |
+ | "run the daily workflow" | Evidence refresh and approval packet | [daily-loop.md](references/daily-loop.md) |
- ### Example for a SaaS Founder
+ Several modes in one request run in dependency order: audit or context refresh,
+ strategy, asset creation, QA, approval packet.
- | Pillar | Starting Share Hypothesis | Topics |
- |--------|---------------------------|--------|
- | Industry insights | 20–30% | Trends, data, predictions |
- | Behind-the-scenes | 20–30% | Building the company, lessons learned |
- | Educational | 20–30% | How-tos, frameworks, tips |
- | Personal | 10–20% | Stories, values, informed opinions |
- | Promotional | 0–10% | Product updates, offers |
+ ## Step 3: Audit before you prescribe
- These ranges are a first content-mix test, not a universal formula. Reallocate
- from qualified audience response and business outcomes.
+ When a handle or export is supplied, audit before recommending anything:
- ### Pillar Development Questions
+ 1. Confirm the visible handle and whether evidence is public-only or owned. Never
+ ask for a password or connect a third-party tool as a shortcut.
+ 2. Collect the most recent 30 posts (all, if fewer). Tag boosted posts, collabs,
+ giveaways, and launches as confounders.
+ 3. Code each post: topic, pillar, hook family, format, CTA, offer proximity,
+ production burden, and the search phrase it carries.
+ 4. Compare within like formats using medians; show `n` for every pattern.
+ 5. Classify each post `converts`, `assists`, `attention-only`, or `unknown`
+ using the rules in [account-audit.md](references/account-audit.md).
+ 6. Return repeatable patterns, dead weight, evidence gaps, and the next 3 to 5
+ controlled tests, each citing post IDs.
- For each pillar, ask:
- 1. What unique perspective do you have?
- 2. What questions does your audience ask?
- 3. What content has performed well before?
- 4. What can you create consistently?
- 5. What aligns with business goals?
+ ## Pillars
- ---
+ Derive 3 to 5 pillars where audience problem, account expertise, observed
+ response, business objective, and a repeatable production source overlap. For
+ each, return:
- ## Hook Formulas
+ ```text
+ Pillar | Audience job | Proof the account can own it | Supporting post IDs
+ Format hypothesis | Business bridge | Stop condition
+ ```
- The first line determines whether anyone reads the rest.
+ Do not force equal shares. Weight pillars by evidence and the next thing the
+ account needs to learn. Promotional content usually stays a small share; let
+ the account's own conversion data set the number.
- ### Curiosity Hooks
- - "I was wrong about [common belief]."
- - "The real reason [outcome] happens isn't what you think."
- - "[Impressive result], and it only took [surprisingly short time]."
+ ## Platform quick reference
- ### Story Hooks
- - "Last week, [unexpected thing] happened."
- - "I almost [big mistake/failure]."
- - "3 years ago, I [past state]. Today, [current state]."
+ Format fit is a hypothesis per account. Facts verified October 2026 are in
+ [platform-limits.md](references/platform-limits.md), including the Instagram
+ 5-hashtag cap, 3-minute Reels and Shorts, the 3:4 Instagram grid crop, and
+ Google indexing of public Instagram professional accounts.
- ### Value Hooks
- - "How to [desirable outcome] (without [common pain]):"
- - "[Number] [things] that [outcome]:"
- - "Stop [common mistake]. Do this instead:"
+ | Platform | Common fit | Formats to test |
+ |---|---|---|
+ | LinkedIn | B2B expertise, founders, hiring | Text posts, document carousels, short video |
+ | X | Real-time expertise, tech, media | Posts, threads, replies, Articles |
+ | Instagram | Visual brands, creators, commerce | Reels, carousels, Stories |
+ | TikTok | Short-form discovery and search | Vertical video, series, comment replies |
+ | YouTube Shorts | Search-led how-to and demos | Square or vertical video up to 3 minutes |
+ | Facebook | Local audiences, groups | Group posts, native video |
- ### Contrarian Hooks
- - "Unpopular opinion: [bold statement]"
- - "[Common advice] is wrong. Here's why:"
- - "I stopped [common practice] and [positive result]."
+ ## Hooks
- ### Named defaults to avoid
+ The first line or first two seconds decide whether anyone stays. Families to
+ draw from: a belief the account was wrong about, a specific result with its
+ timeframe, a mistake and its fix, a how-to with the pain removed, a defensible
+ contrarian claim. Full lists live in
+ [post-templates.md](references/post-templates.md) and
+ [short-form-video.md](references/short-form-video.md).
- A hook formula invites the exact copy these produce by default. Reject a draft
- that contains any of them and rewrite from the claim's actual evidence:
+ Reject any draft that contains:
- - Engagement-bait questions with no stake ("Thoughts?", "Agree?", "Who else?").
+ - Engagement bait with no stake ("Thoughts?", "Agree?", "Who else?").
- Manufactured awe ("Let that sink in", "This changes everything").
- - Contrarianism with no evidence: an "unpopular opinion" the account cannot
- defend with an observed result or a named source.
- - A hook wrapped around an unproven claim. If the payoff has no owned metric,
- named source, or demonstrable artifact behind it, fix the claim, not the hook.
- - Fake specificity: invented percentages, round-number results, or timelines
- the account did not measure.
-
- Run final copy through `suede-deslop` before it goes out for approval.
-
- **For post templates and more hooks**: See [references/post-templates.md](references/post-templates.md)
-
- **For carousels** (Instagram carousels, LinkedIn document posts): See [references/carousel-frameworks.md](references/carousel-frameworks.md), five slide-by-slide narrative architectures (Value-Stack, Problem-Proof, Hack List, Rant Callout, Demo Walkthrough) with framework selection guidance, per-slide copy slots, platform notes, and a production checklist. Pick the framework before writing slides.
-
- ---
-
- ## Content Repurposing System
-
- Test whether one approved source can yield several useful, distinct assets
- without stretching the evidence or repeating the same point.
-
- ### Blog Post → Social Content
-
- | Platform | Format |
- |----------|--------|
- | LinkedIn | Key insight with link placement tested against current guidance and account results |
- | LinkedIn | Carousel of main points |
- | Twitter/X | Thread of key takeaways |
- | Instagram | Carousel with visuals |
- | Instagram | Reel summarizing the post |
-
- ### Podcast / Video → Social Content
-
- Extract "content atoms": self-contained moments from any long-form content that work on their own:
-
- | Atom Type | What to Look For | Candidate Formats to Test |
- |-----------|-----------------|---------------------------|
- | Quotable moment | A bold claim, hot take, or memorable line (15-60 sec) | Twitter/X, LinkedIn, TikTok |
- | Story arc | A complete mini-story with setup, conflict, resolution (60-90 sec) | Instagram Reels, TikTok, YouTube Shorts |
- | Tactical tip | A specific how-to or framework explained clearly (30-60 sec) | LinkedIn, YouTube Shorts |
- | Controversial take | A contrarian opinion that sparks debate | Twitter/X, LinkedIn |
- | Data/stat callout | A surprising number or research finding | LinkedIn carousel, Twitter/X |
- | Behind-the-scenes | Authentic, unpolished moments | Instagram Stories, TikTok |
-
- **Podcast repurposing workflow:**
- 1. **Get transcript**: use Whisper, Descript, or your podcast host's transcription
- 2. **Mark timestamps**: flag the 5-10 best moments while listening or scanning transcript
- 3. **Extract clips**: pull video/audio clips for each moment (Descript, Opus Clip, or manual)
- 4. **Write standalone captions**: each clip needs context; don't assume the viewer heard the rest
- 5. **Add subtitles**: make the clip accessible without assuming a universal
- sound-off rate
- 6. **Plan a distribution test**: choose timing from current cadence, source
- volume, approval capacity, and account evidence
-
- **Starting extraction hypothesis, only when the source supports enough distinct
- moments and the team can review them:**
- - 3-5 short video clips or audiograms (15-60 sec) for Reels/TikTok/Shorts
- - 1-2 LinkedIn text posts from key insights
- - 1 Twitter/X thread of takeaways
- - 1 carousel summarizing the main framework or list
- - 1 newsletter section or blog post from the best segment
-
- ### Webinar / Live Event → Social Content
-
- | Extract | Format |
- |---------|--------|
- | Key slides with commentary | LinkedIn carousel |
- | Q&A highlights | Twitter/X thread |
- | Speaker quotes | Quote graphics for Instagram/LinkedIn |
- | Audience reactions/poll results | Engagement posts |
- | Full recording → short clips | Reels, TikTok, Shorts |
-
- ### Newsletter → Social Content
-
- | Extract | Format |
- |---------|--------|
- | Main insight | LinkedIn post |
- | Curated links with commentary | Twitter/X thread |
- | Data or stat | Quote graphic |
- | Hot take or opinion | Twitter/X post, LinkedIn |
-
- ### Repurposing Workflow
+ - A contrarian claim the account cannot back with a result or named source.
+ - A hook wrapped around an unproven claim. Fix the claim, not the hook.
+ - Fake specificity: invented percentages, round results, unmeasured timelines.
- 1. **Create pillar content** (blog, video, podcast, webinar, newsletter)
- 2. **Extract content atoms** (5-10 per piece: quotes, stories, tips, data)
- 3. **Adapt to each platform** (format, length, and tone)
- 4. **Write standalone captions** (each post must work without context)
- 5. **Plan distribution** from current cadence and approval capacity
- 6. **Test updates or reshares** only when current relevance and account evidence
- support them
+ Score candidate ideas 0 to 4 on each: audience recognition, specific payoff,
+ evidence strength, voice fit, business bridge. Rank by total, show every
+ component, and call the winner a test candidate, never "viral".
- ### X: Third-Party Video + Owned Article
+ ## Asset contracts
- When promoting an owned X Article with a relevant third-party video:
+ **Short video (Reels, TikTok, Shorts).** Return 5 hooks (20 on request), the
+ selected hook with its score, a second-by-second script (visual, voiceover,
+ on-screen text, retention job per beat), a faceless shot plan when asked, a
+ caption whose first line carries the search phrase, one CTA, alt text and
+ caption notes, a rights and claims checklist, and a one-variable test card. With
+ no account evidence, label 15 to 45 seconds a starting test range.
- 1. Use only the video as native media, and only with a lawful basis to reuse it.
- Preserve source attribution.
- 2. Do not quote, repost, or inherit the third party's whole post, caption,
- replies, or engagement context.
- 3. Create a fresh post from the approved account with the exact approved copy,
- then place the owned Article status URL at the end so X renders the owned
- Article as the quoted card.
- 4. Before publishing, verify the identity, native video, owned Article card,
- exact text, audience, and reply settings.
- 5. After publishing, verify the live post still contains both the native video
- and owned Article card, then capture the permalink.
+ **Carousel or document post.** Pick the narrative first (value stack,
+ problem-proof, numbered techniques, critique, demo walkthrough). Slide count
+ equals the beats the idea needs. Slide 1 names the audience tension or payoff;
+ each middle slide does one job; the last slide pays off and gives one action.
- If X's Quote composer accepts the video but leaves publishing disabled, use the
- fresh-post construction above or report the blocker. Never substitute a quote
- of the third party's post.
+ **Text post or thread.** First line stands alone before truncation. One idea.
+ One CTA. Use the skeletons in [post-templates.md](references/post-templates.md).
- ---
+ **Story sequence.** Use Stories for a job (research, proof, objection handling,
+ launch, reply, conversion), never a daily quota. Frame table in
+ [content-production.md](references/content-production.md).
- ## Content Calendar Structure
+ Write captions and voiceover from the account's real voice samples: sentence
+ length, vocabulary, humor, punctuation, taboo list. Run final copy through
+ `suede-deslop` before it goes for approval.
- ### Illustrative Planning Grid
+ ## Repurposing
- Use this only as a worksheet shape. Fill cells from the approved platform
- hypotheses and production capacity; blank cells are valid.
+ Extract self-contained atoms from one approved source: a quotable claim, a
+ complete mini-story, a tactical tip, a data point, a behind-the-scenes moment.
+ Map each atom to the platform where its format fits, and give each asset its own
+ point. When the source cannot support the requested count without repeating
+ itself, say how many it supports and what extra input would support more.
- | Slot | LinkedIn | Twitter/X | Instagram |
- |-----|----------|-----------|-----------|
- | 1 | Industry insight | Thread | Carousel |
- | 2 | Behind-scenes | Reply draft | Story test |
- | 3 | Educational | Short post | Reel test |
+ When the source is a third-party video, or the clip must lead to an article or
+ guide, route to `suede-clip-to-guide`, which owns rights routes and the
+ short-to-long bridge.
- ### Calendar row schema
+ ## Calendar row schema
- Every calendar row returned to the user carries these exact fields. A row
- missing evidence source, test variable, or approval status is not ready to
- return:
+ Every calendar row carries these fields. A row missing evidence source, test
+ variable, or approval status is not ready:
```text
- Slot/date + timezone | platform | pillar | hook | payoff | CTA
- Evidence source | one variable under test | primary metric
- Asset owner | production status | approval status
+ Date + timezone | platform | format | pillar | audience problem | hook | payoff | CTA
+ Search phrase | evidence source | one variable under test | primary metric
+ Asset owner | production status | approval status | readback field
```
- For the post draft itself, do not restate a template here: write it from
- [references/post-templates.md](references/post-templates.md), which owns the
- exact LinkedIn, X thread, carousel, and Reel skeletons.
-
- ### Batching Pilot
-
- Set the timebox and output count from current capacity. A possible first pilot:
-
- 1. Review content pillar topics.
- 2. Draft one or two variants for each selected platform.
- 3. Prepare only the approved asset concepts.
- 4. Return the batch for exact-content review before scheduling or publishing.
- Each batch item is one calendar row in the schema above, plus its draft.
-
- ---
-
- ## Engagement Strategy
-
- ### Participation test (15–30 minute starting estimate)
-
- 1. Triage relevant comments on owned posts.
- 2. Draft 2–5 substantive replies to approved target-account posts.
- 3. Draft at most one share or quote post when it adds sourced context.
- 4. Draft a direct message only when the relationship and platform norms support
- it; never send without exact-content and identity approval.
-
- Run this on 3–5 active days for two weeks only as a starting hypothesis. Compare
- qualified replies, profile visits, follows, and time cost with the prior period.
-
- **For surfacing *which* posts may merit a comment draft** (bounded ranked lists,
- brand/competitor monitoring, intent-signal triage), see
- [references/listening.md](references/listening.md). To set up the source list
- that feeds it, use
- [references/listening-sources-template.md](references/listening-sources-template.md).
-
- ### Quality Comments
-
- - Add new insight, not just "Great post!"
- - Share a related experience
- - Ask a thoughtful follow-up question
- - Respectfully disagree with nuance
-
- ### Building Relationships
-
- - Build a bounded account set with explicit audience-fit reasons
- - Participate only when the post is relevant and the visible identity is
- approved
- - Share their content with credit
- - Eventually collaborate (podcasts, co-created content)
-
- ---
-
- ## Analytics & Optimization
-
- ### Metrics That Matter
-
- **Awareness:** Impressions, Reach, Follower growth rate
-
- **Engagement:** Engagement rate, comments, shares/reposts, saves; weight them
- according to the campaign objective rather than a universal hierarchy
-
- **Conversion:** Link clicks, Profile visits, DMs received, Leads attributed
-
- ### Review Interval
-
- - Choose an interval that contains enough comparable posts; weekly is only a
- starting estimate for active accounts.
- - Compare a higher- and lower-performing cohort and test why they differed.
- - Follower growth trend
- - Engagement rate trend
- - Timing patterns from current account data, with sample size and timezone
-
- ### Optimization Actions
-
- **If engagement is low:**
- - Test new hooks
- - Post at different times
- - Try different formats
- - Test a bounded participation routine
-
- **If reach is declining:**
- - Compare link and no-link posts at similar account conditions
- - Test one cadence change within production capacity
- - Compare comments, text, document, image, and video formats against the account
- baseline
-
- ---
-
- ## Scheduling Best Practices
-
- ### When to Schedule vs. Post Live
-
- **Schedule:** Core content posts, Threads, Carousels, Evergreen content
-
- **Post live:** Real-time commentary, Responses to news/trends, Engagement with others
-
- ### Queue Management
-
- - Set queue depth from current news sensitivity, approval capacity, and account
- cadence
- - Review the queue before publication and whenever material context changes
- - Leave gaps for spontaneous posts
- - Adjust timing based on performance data
-
- ---
-
- ## Evidence-Based Content Pattern Analysis
-
- Instead of guessing, analyze a lawful, recent sample from comparable accounts:
-
- 1. **Define comparables**: Similar audience, offer, account maturity, and
- platform; record why each account belongs in the sample.
- 2. **Collect a bounded sample**: Use only data the current platform and account
- access lawfully expose. Set the count from available volume and stop when
- another batch no longer changes the leading patterns.
- 3. **Analyze patterns**: Compare hooks, formats, CTAs, reach, retention, saves,
- and replies only where the platform exposes those measures.
- 4. **Codify playbook**: Document repeatable patterns
- 5. **Layer your voice**: Apply patterns with authenticity
- 6. **Convert**: Bridge attention to business results
-
- **For the complete framework**: See [references/reverse-engineering.md](references/reverse-engineering.md)
-
- ---
-
- ## Short-Form Video (TikTok, Reels, Shorts)
-
- Short-form video may be a useful discovery format when current platform
- guidance and account-level results support it. Verify that premise for the
- specific account before prioritizing it; the frameworks below organize a test,
- not a guaranteed reach outcome.
-
- ### Platform test specs
+ Use the lowest cadence that preserves evidence, voice, rights, and review
+ quality. Daily candidate generation is fine; daily publishing is a hypothesis.
- Verify current official upload requirements and the authenticated composer
- before production. If account evidence is unavailable, use these as first-test
- ranges, not optimal lengths:
+ ## Listening and engagement
- | Platform | Starting Length Test | Starting Canvas | Evidence to Read |
- |----------|----------------------|-----------------|------------------|
- | TikTok | 15–60 seconds | 9:16 | Retention, completion, qualified actions |
- | Reels | 15–45 seconds | 9:16 | Retention, saves, shares, qualified actions |
- | Shorts | 20–60 seconds | 9:16 | Retention, rewatches, search and channel actions |
+ Listening surfaces posts worth a reply draft: ICP fit, buying intent, a real
+ chance to add something. Score, draft, and return for approval; every comment
+ is a separate external action. Method, rubric, and source recipes:
+ [listening.md](references/listening.md) and
+ [listening-sources-template.md](references/listening-sources-template.md).
- ### Opening-hook hypothesis
+ ## Measurement
- Test whether the first 1–3 seconds establish enough visual, verbal, or text
- context to retain the intended viewer. Use one or more hook modes as the concept
- requires; do not require all three without account evidence:
+ Pick one primary metric from the objective and 2 to 4 diagnostics. With
+ denominators available, compute rates explicitly:
- ```
- [VISUAL HOOK] + [VERBAL HOOK] + [TEXT OVERLAY]
+ ```text
+ save rate = saves / accounts reached share rate = shares / accounts reached
+ follow rate = follows from post / reached profile-action rate = profile actions / reached
+ lead rate = attributed leads / reached search share = search-sourced views / views
```
- Compare opening variants against the account's comparable-format retention
- baseline before standardizing the pattern.
-
- ### Video Structures
-
- Pick the beat sheet before scripting. All five structures (Problem-Solution,
- List Format, Tutorial, Story Arc, POV/Skit) with timings and fit hypotheses,
- plus the caption spec below, live in
- [references/short-form-video.md](references/short-form-video.md); read it
- whenever a short-form script or its on-screen text is actually being written.
-
- ### Caption & Subtitle Best Practices
-
- Captions are an accessibility default, not a watch-time claim. Hard caps: **max
- 2 lines on screen, 3-5 words per line, timing matched to speech.** Caption
- tooling, export specs, and edit execution belong to `suede-video`.
-
- ### Common Mistakes
+ Compare each post with its format's trailing median, not a universal benchmark.
+ Change one variable per test. Diagnosis rules and the experiment card are in
+ [measurement.md](references/measurement.md).
- 1. **Unclear opening**: test whether the premise is understood in the first
- 1–3 seconds
- 2. **No accessible captions**: provide captions independent of sound-off-rate
- assumptions
- 3. **Unusable audio**: verify speech intelligibility on target devices
- 4. **Unsupported length**: compare length bands against retention and the idea
- 5. **Missing next step**: include a CTA only when the objective needs one
- 6. **Unreviewed comments**: choose response priority from relevance and account
- evidence, not a universal first-hour rule
+ ## Suede AI account mode
- **For video hook formulas and scripting templates**: See [references/short-form-video.md](references/short-form-video.md)
+ When the account belongs to Suede AI, Jason Colapietro, or a Suede AI product:
- ---
+ - Lead with what Suede AI sells first: AEO, GEO, and SEO services
+ (https://suedeai.agency) and Agent Studio multi-agent automation for
+ businesses (https://suedeai.app). Product lanes such as Suede Sing,
+ StoryBeam, GuitarHub, and the creator skills come after.
+ - Build proof-led lanes: live demos, before-and-after search visibility with a
+ named source, agent workflows shown working, founder lessons with specifics.
+ - Bylines and bios use Jason Colapietro. "Johnny Suede" is for social handles
+ and casual creator content only.
+ - Never claim rankings, AI citations, revenue, or client results the account
+ cannot show.
+ - Use only `docs/assets/suede-ai-logo-transparent.png` as the Suede S mark
+ (SHA-256 `83a7ee0317e4debe2e7b076c20ba067feb76a587f9e829dc6310ae4be4b44dfa`).
+ Never redraw, recolor, or regenerate it. If the file is missing or the
+ checksum differs, omit the mark and halt.
- ## Halt Contract
+ ## Halt contract
- Use this exact format when account access, asset rights, visible identity, or
- exact-content approval blocks the requested result, including when the
- publish/engagement gate in Boundaries fires:
+ Use this format when access, asset rights, visible identity, or exact-content
+ approval blocks the result:
```text
HALT: <one-line blocker>
Why it blocks: <specific missing authority or evidence>
Resolve with:
1. <option>
2. <option>
3. <option, when useful>
Waiting for: <the exact item or approval>
```
- Continue with safe drafts, calendars, or worksheets only when they remain
- useful and do not imply the blocker was resolved.
-
- ---
+ Keep producing safe drafts and worksheets when they stay useful and do not imply
+ the blocker is resolved.
## Boundaries
- - Do not publish, schedule, reply, follow, message, like, repost, or otherwise
- act as an account without explicit approval of the exact content and visible
- identity.
- - Do not invent performance, trends, quotes, audience sentiment, or account
- access; distinguish observed platform evidence from hypotheses.
- - Do not impersonate people, scrape private spaces, evade platform rules, or
- turn sensitive personal data into engagement material.
+ - Do not publish, schedule, reply, follow, like, repost, message, or edit an
+ account without approval of the exact content and the visible identity.
+ - Do not scrape, bypass access controls, evade rate limits, or put a consumer
+ password into an automation.
+ - Do not invent private insights, trends, quotes, sentiment, competitor
+ conversion, testimonials, or results. Public competitor data cannot show
+ saves, shares, retention, or sales.
+ - Do not run engagement pods, buy followers, auto-like or mass-comment, or post
+ undisclosed synthetic endorsements.
+ - Do not use music, footage, likenesses, logos, or reposted creator content
+ without a verified lawful basis and any required credit.
+ - A draft, scheduled item, or composer preview is not a published post. Require
+ a live permalink readback.
## Routing
- - Use `suede-instagram-growth` for Instagram-specific account audits,
- conversion mapping, Reels, carousels, Stories, calendars, and daily loops.
- - Use `suede-content-strategy` for the broader editorial system.
- - Use `suede-newsroom` when one approved idea has to fill several surfaces and
- each asset needs its own argument, or when the pipeline itself needs roles,
- handoff contracts, and a campaign record. Route a recurring founder interview
- or voice note with separate founder-account and company-account jobs to that
- skill's founder-led mode. This skill decides where and when; that one decides
- what each asset argues.
- - Use `suede-video` for full video generation and production, including caption
- tooling, export specs, and edit execution.
- - Use `suede-clip-to-guide` to turn a clip, interview moment, or talk excerpt
- into a short-to-long package that bridges to an Article, newsletter, or guide.
- - Use `suede-ad-creative` for paid social concepts and variants.
- - Use `suede-analytics` for channel measurement and performance readback.
- - Use `suede-deslop` for the final anti-slop pass on any copy that will be
- published.
+ - Paid social campaigns, budgets, and targeting: `suede-ads`. Paid creative
+ variants: `suede-ad-creative`.
+ - One idea that must carry several surfaces with distinct arguments, or an
+ agent-run editorial pipeline: `suede-newsroom`. This skill decides where and
+ when; that one decides what each asset argues.
+ - A clip, interview moment, or third-party video bridged to an article,
+ newsletter, or guide: `suede-clip-to-guide`.
+ - Rendering, editing, captions tooling, and exports: `suede-video`. Still
+ images and graphics: `suede-image`.
+ - Editorial portfolio and topic clusters: `suede-content-strategy`.
+ - UTMs, events, and attribution repair: `suede-analytics`.
+ - Site-level SEO and AI answer visibility: `suede-seo-audit` and `suede-ai-seo`.
+ - Final anti-slop pass on anything public: `suede-deslop`.