arbor-ideate SKILL.md skillA

arbor-ideate from invergent-ai/surogates is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add invergent-ai/surogates/arbor-ideate@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
invergent-ai/surogates
Path
skills/research/arbor-ideate/SKILL.md
Versions recorded
2
Latest version
v1.0.0, committed Oct 12, 2026
First version recorded
Jun 13, 2026
Size
3,576 bytes
Repository stars
28
License
AGPL-3.0

Hard-gated ideation for an Arbor research run. Load at the START of every IDEATE round, before drafting any hypothesis. Enforces the PI mindset (mechanism over knob), the four-question first-principles probe, the kill-filter, and the four-line hypothesis format. Ported from Arbor's idea_drafting + first_principles_probe.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Arbor Ideate — Hard-Gated Idea Drafting

<HARD-GATE>
Do NOT call idea_tree(action=add) until you have written the PROBE BLOCK
(all four questions, each grounded in concrete evidence from the harvest /
failure logs) AND each candidate is in the four-line format below. Skipping
the probe is the default LLM failure mode — it is forbidden here.
</HARD-GATE>

## 1. Mindset: PI, not engineer

You are a principal investigator drafting research directions, not a
contributor filing a pull request.

- **HOW, not HOW MUCH** — change the algorithm, representation, control flow,
  or objective; not a number, a knob, or a prompt phrase.
- **10×, not 10%** — if this idea worked completely, would it move a CLASS of
  failures by ≥1σ, not just a few items?
- **Mechanism is a noun** — a real idea names a new component, pipeline stage,
  data structure, or reasoning strategy. "Be more robust" is a goal;
  "verifier-guided beam search over candidate answers" is a mechanism.

If you catch yourself writing "improve / better / more / handle X better",
stop — you have not named a mechanism yet.

## 2. First-Principles Probe (MANDATORY, before any candidate)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add invergent-ai/surogates/arbor-ideate@sha256:3315bc1c9f80fcdf

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_js7ximt6y4s7xv65.svg)](https://markdownregistry.com/a/art_js7ximt6y4s7xv65)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jun 13, 2026 and Oct 12, 2026, about one every 121 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-12 f6e8148 3,576 BA view · diff
v1.0.02026-06-13 0059817 3,540 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3576 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

invergent-ai/surogates · 28 stars · license AGPL-3.0 · pushed 2026-11-05 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_js7ximt6y4s7xv65
GET https://markdownregistry.com/api/v1/resolve?ref=invergent-ai/surogates/arbor-ideate
GET https://markdownregistry.com/api/v1/blob/3315bc1c9f80fcdfc05650ba53670240ff8e59bc9ddd7eda7c6b59c0ca47b778

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from invergent-ai/surogates

subagent-task-orchestrator SKILL.md skill
invergent-ai/surogates · skills/kanban/subagent-task-orchestrator/SKILL.md · Decomposition playbook and anti-temptation rules for an orchestrator agent that routes work through the Surogates…
v1.0.0 · audit A · 28 stars
subagent-task-worker SKILL.md skill
invergent-ai/surogates · skills/kanban/subagent-task-worker/SKILL.md · Pitfalls, examples, and edge cases for workers executing a Surogates subagent task. Loaded automatically when the…
v1.0.0 · audit A · 28 stars
brainstorming SKILL.md skill
invergent-ai/surogates · skills/process/brainstorming/SKILL.md · Agree the design of a large, open-ended build with the user before building it.
v1.0.0 · audit A · 28 stars
dispatching-parallel-agents SKILL.md skill
invergent-ai/surogates · skills/process/dispatching-parallel-agents/SKILL.md · Split 2+ independent investigations or tasks across sub-agents (delegate_task) and merge the results.
v1.0.0 · audit A · 28 stars
executing-plans SKILL.md skill
invergent-ai/surogates · skills/process/executing-plans/SKILL.md · Carry out an existing written implementation plan step by step with checkpoints.
v1.0.0 · audit A · 28 stars
writing-plans SKILL.md skill
invergent-ai/surogates · skills/process/writing-plans/SKILL.md · Turn an agreed spec for a large multi-step build into a step-by-step implementation plan.
v2.0.0 · audit A · 28 stars
writing-skills SKILL.md skill
invergent-ai/surogates · skills/process/writing-skills/SKILL.md · Create or edit a skill (SKILL.md) when the user asks for one.
v1.0.0 · audit A · 28 stars
consolidate-memory SKILL.md skill
invergent-ai/surogates · skills/productivity/consolidate-memory/SKILL.md · Clean up memory (merge duplicates, fix or remove stale entries) when the user asks.
git:20261104.c3eaa01 · audit A · 28 stars
doc-coauthoring SKILL.md skill
invergent-ai/surogates · skills/productivity/doc-coauthoring/SKILL.md · Co-write a long structured document (proposal, spec, decision doc) with the user over several rounds, when they want to…
git:20261104.c3eaa01 · audit A · 28 stars
docx SKILL.md skill
invergent-ai/surogates · skills/productivity/docx/SKILL.md · Create, edit or convert Word documents (.docx/.dotx), including tracked changes, comments, images and formatting.
git:20261104.c3eaa01 · audit A · 28 stars
import-memory SKILL.md skill
invergent-ai/surogates · skills/productivity/import-memory/SKILL.md · Import a memory export from another assistant (ChatGPT, Gemini, Claude, ...) into memory.
git:20261104.c3eaa01 · audit B · 28 stars
maps SKILL.md skill
invergent-ai/surogates · skills/productivity/maps/SKILL.md · Geocoding, places, routes and timezones via OpenStreetMap/OSRM.
v1.2.0 · audit A · 28 stars

Every file in invergent-ai/surogates

Browse by kind, by grade A, or by owner.