git:20261014.4e5e7e5 to git:20261015.07749c7

- description: Plan and run a whole edit in BashCut from raw footage to export — intake, recipe, survey, story, cut, sound, text, colour, effects, review, draft, export — through the user's gates, a checklist with evidence and independent audits, picking the one skill to read per stage. Use when the user asks to edit or cut a video, make a vlog, ad, review, short or montage from footage, revise an edit, or asks where to start; also tool demos from a screen recording plus a presenter. Triggers: "dựng video", "cắt video", "làm vlog", "làm video quảng cáo", "dựng giúp", "sửa lại video", "edit this", "bắt đầu từ đâu", "video giới thiệu tool", "talking head", "video nói chuyện".

- Reply in the user's language. Two files hold the rest; read **one section** when a step names it, never a whole

- file (`sed -n '/^## Starting/,/^## [A-Z]/p' <skill_dir>/REFERENCE.md`):

- A **recipe** (a plugin skill such as `bashcut.vlog:product-ad`) writes data into the plan (stages, checks, promise,

- ranges); this skill runs the process. Editorial numbers are **ranges with their source**: choose within them for

- this footage and say why in the plan (`"deliberate": true` with the reason to leave one).

- - **Tool rules are BashCut's** (MCP instructions, `bashcut help`): `--base-rev`, scope, error codes, library first,

- no ffmpeg pre-renders. This kit says what to do and why.

- - Edit without asking; stop only at gates. Download what the edit needs (music, SFX, pictures, video, fonts)

- without asking; no source or licence records (`--source URL` only when you have it anyway). Never clone a voice

- that is not the user's. Install a BashCut plugin the edit needs (`plugins search --capability`, `plugins install`;

- trusted automatically unless the user turned it off, then the user approves it in the app).

- - Read a plugin's skill before using its feature; plugin skills are read-only (corrections: `bc:self-learn`).

- - **Every call is a turn that resends the whole context** (cost ≈ calls × context): one call for many things, the

- cut as one list (`plan.cut`), never clip by clip; read big things in sub-agents, not yourself. After your own

- commands pass `--base-rev last` instead of reading the revision; `context get` again only when a stale error

- says someone else changed the project.

- - Say why: every `plan apply` and `timeline apply` carries `--why` (and `--evidence`).

- - Kit scripts run with `uv`. Name files in English, lowercase with hyphens (`draft-v1`).

- Same gates and audits; the cut is one list BashCut checks. Target: a 45 s ad in about 20 calls.

- 1. **Intake, one call**: `context get`, `knowledge get`, `workflow gates`, the recipe's working parts

- (`skills get <recipe> --section "Plan data,Ranges,Review notes"` plus any other section you need; recipes are

- plugin skills described "Recipe for", listed as `vlog-<kind>`) and the review limit table

- (`sed -n '/^## Before round 1/,/^## The loop/p' <skill_dir>/../review/SKILL.md`). No recipe plugin: tell the

- user `/bc:setup`, use kit defaults.

- 2. **Ask once** (at most 4 questions, REFERENCE "Intake questions"), each led by "AI chọn: …". User away: take your

- choices, write them `inferred` in the brief, never ask later.

- landscape|portrait|square --fps 30 --language <tag> --import` imports and starts transcription and analysis

- (result: `media` IDs, `jobs {transcribe, analyze}`). "Unsaved changes" about a project you did not make:

- `--save-current`. Then the survey sub-agent at once, with media and job IDs (it waits): `bc:surveyor`, else a

- sub-agent briefed with `<skill_dir>/../footage-survey/SURVEYOR.md`, else that brief yourself. **Never print a

- transcript or digest, never open source frames**; its quotes resolve as they are (a few lines around them:

- `media transcript --media M --ranges 640:652,1050:1058 --as text --format text`).

- 4. **Brief, plan, sound and review limits in one call**: download any music or SFX first (below), `media import`

- them, then `project format --outputs <preset> --base-rev last` (`youtube-1080`, `shorts`, `reels`, `tiktok`…),

- `project set-data brief brief.json --base-rev last` (fields `{value, status: stated|inferred|confirmed, source}`:

- `goal`, `audience`, `outputs`, `angle`, `lengthSeconds {min, max}`, `notes`) and `project set-data plan plan.json

- --merge --base-rev last` with `promise`, `sections` (`{id, label, lengthSeconds {min, max}, reason}`), `recipe`,

- `checks`, `decisions`, `ranges` and **`cut`**:

- Clips go in order, by quote (or `from`/`to`, which on a quote move its edges); `cover` lays pictures over a

- line; `zoom` (`pan`, `tilt`) is a punch-in. Titles take a preset (`hook-title`, `place-card`, `stacked-keyword`…)

- and anchor to a `clip` or `section` (+ `offset`), lasting to its end without `seconds`. `style` changes only what

- it names: `size` (share of the short side), `positionY` (baseline from the bottom, 0–1), `positionX`, `align`,

- `font`, `fill`, `stroke`, `strokeWidth` (points), `uppercase`, `background {color, opacity}`, `shadow`. White

- text over daylight measured 1.2–2:1: plate captions and titles now; two texts at once need different

- `positionY`. **Sound**: a `music` bed unless the brief says none; `sfx` only where a moment needs one (whoosh on

- a hard cut, pop as a title lands; `offset` -0.1 peaks on it). Library first (`library list --kind audio`), else one

- command finds, downloads and imports them, one short line per file with its `media` ID: `uv run

- <skill_dir>/../audio-mix/fetch_audio.py --dest <project>/media/audio --music "<mood words>" --sfx whoosh,pop

- --import`.

- **Review limits** (`review`) come from the recipe's `Ranges` and the review table; `plan check` lists any still

- unset in `review-profile-unset` (`facts.unsetLimits`, `facts.accepts`): set them all, else review stays

- incomplete; a limit no source covers: choose it and say so in `ranges`. Request **G1** with the brief.

- 5. **Check, no edit**: `plan check` resolves quotes on a scratch copy: clip edges, titles (`textShare`, chars per

- second), problems, the review as it would be. Fix by `plan check --patch '{"clips": {"c2": {"to": 953.0}}}'`

- (merges by entry ID; never rewrite plan files with scripts) until `ok`: `cut-in-word` gives `facts.before/after`

- to move the edge to; `same-framing` is a jump cut to come (give the second clip a `zoom` 1.15–1.3, `bc:beat-cut`

- §5, never over text, or a `cover`); `unknown-field` changes nothing. The **strategy audit** is yours (`--by

- self`): promise, sections, `inferred` brief fields, recipe checks.

- --why "…"` (with `--patch` holding the check's fixes: a check saves nothing). It returns the review's errors and

- warnings and the storyboard: look at that one sheet for G3. Every later change is `plan apply --patch …`.

- 7. **Voice and graphics go to sub-agents** (recipe steps too): with the lines and rows in the

- plan, `bc:voice`, then `bc:graphics` (else sub-agents briefed with `<skill_dir>/../voiceover/VOICE.md` and

- project, IDs, facts, look and limits; never read their skills, results or renders. Then only what the plan

- 8. **Review**: `review run --measure --summary`. Fix a kind of problem for every entry it touches **in the list**

- (`plan apply --patch`, never `timeline apply` on plan-built items) with `review run --measure --summary` and

- `review verify all` in the same call. **Draft audit**: `bc:critic` (else a sub-agent briefed with

- `<skill_dir>/../review/CRITIC.md`, else `--by self`) builds the packet and returns one `plan.cut` patch; give it

- the project, revision and your suspicions. Never open the packet: in **one call** `run append audit --point

- draft --by critic …`, `plan apply --patch … --base-rev last`, `review run --measure --summary`, `review verify

- all`. A sheet (`timeline sheet --entries …`) only for what no measurement covers; a second critic look only for

- an unproven blocker.

- then **G5** and the hand-off report (REFERENCE "The hand-off report").

- Brief and plan are project data (`project set-data brief|plan`, `--merge` for one part); `context get` summarises

- both, so after a reset resume from them and `run log`, not from memory. Shapes: REFERENCE "The brief and the plan

- as data". A recipe writes `recipe {skill, version}`, `promise {hook, payoff}`, `stages` (deviations only), `checks`

- (at most 8) and `askAtIntake`; you write `mode`, `stage`, `options`, `sections`, `shots`, `beats`, `visuals`,

- `decisions`, `ranges` and `cut`.

- `colour`, `effects`, `review`, `export`, `learn` (table and skills: FULL "Stages, checklist and gates"). BashCut

- writes `intake` (the brief set), `survey` (every media described), `story`, `rough-cut` and `captions` (plan

- apply), `review` (a review run that passes) and `export` (an export that lands). Optional stages you leave out

- need no entry; a stage you do by hand: `run append stage --stage colour --status done --evidence "a;b"` in the call

- that finishes it. A long stage shows in the user's run panel: `run append stage --stage cut --text "Cutting 12

- shots" --eta 120` (skip it for stages of seconds). Gates (`workflow gates`) are `ask`, `notify` or `skip`; request every one with

- something cheap to look at (`checkpoint request G2 --summary "…" --attach sheet.png`, then `checkpoint status --wait

- 100` while `awaiting_user`). Only the user answers a gate. A skipped G2 needs the strategy audit and a skipped G5

- the draft audit; BashCut refuses the rough cut without the recipe read and the strategy audit, and a final export

- without a passing draft audit: run what the error names. Details: FULL "Gates" and "Audits". `review run` status

- `incomplete` is never a pass.