think
Skill1 starsChanged 4 months agoMITView on GitHub
Structured thinking moves for when you're stuck, the answer feels too easy, or a problem needs depth — invert, second-order, base-rate, analogy, constraint-flip, decompose. Routes a situation to the right move and forces it to completion. Use for design deadlock, suspicious consensus, novel problems, or "we've always done it this way".
30 other projects use a version of this.
Adopted by
Most recently taken up by
- hurleywgly/skillstheir own version, first seen Nov 8, 2026
- seankoji-com/.agentstheir own version, first seen Nov 8, 2026
- TserenTserenov/FMT-exocortex-templatetheir own version, first seen Nov 2, 2026
- iwesys/IWEtheir own version, first seen Nov 1, 2026
- therealtinhtute/mono-harnesstheir own version, first seen Nov 1, 2026
- deonmenezes/thinktheir own version, first seen Nov 1, 2026
Used with
Projects with it also use hunt, read and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ninehillsSkillhunt
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code review or new features.
Also in 5 projects that use this
MicrosoftSkillread
Read pages from a document. Returns MinerU markdown (preferred) or PyPDF text, with optional page screenshots and sub-image fetching. When markdown is available, a figure_images_meta catalog is included — use the figures parameter to fetch specific sub-image pixels. Triggers include "read page 5", "what does page 12 say", "show me the chart on page 3", "extract pages 3-5".
Also in 6 projects that use this
DockerSkillwrite
Write or edit reader-facing technical prose for immediate comprehension. Use for documentation, PR titles and descriptions, release notes, design documents, user-facing explanations, and substantive comments. Also use when asked to make writing clearer, more natural, less AI-generated, or easier to read. For documentation fixes, handles edits, formatting, self-review, and commits after research identifies what to change. Do not use for code-only tasks with no prose deliverable.
Also in 7 projects that use this
genomewalkerSkillhealth
Soul system health check with remediation
Also in 5 projects that use this
kt057Skillcheck
lint, typecheck, test を一括実行して結果をサマリーする
Also in 6 projects that use this
OpenAISkilltranscribe
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
Also in 3 projects that use this
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 30
- AgriciDaniel/claude-obsidian★ 16ksame name
- tw93/claude-health★ 7.5ksame name
- tw93/Waza★ 7.5ksame name
- ninehills/skills★ 280same name
- garagon/nanostack★ 206same name
- jonathanmalkin/jules★ 65same name
- TserenTserenov/FMT-exocortex-template★ 63same name
- myclaude-sh/myclaude-creator-engine★ 25same name
- ironyjk/strategy-frameworks★ 14same name
- therealtinhtute/mono-harness★ 5same name
20 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
/think — Forced Thinking Moves
Depth isn't a mood, it's a set of operations. Each move below is mechanical enough for any model to execute, and each one reliably surfaces things straight line reasoning misses. Pick ONE move and run it to completion — six half-moves are worth nothing.
The moves
invert — Solve the opposite. "How would we guarantee this project fails / this page is slow / users churn?" List 5+ ways, concretely. Then check which ones you're currently doing. The anti-goal list is usually more actionable than the goal list.
second-order — "And then what?" three times. Every proposed change: who reacts, what adapts, what breaks one step later? First-order thinking says "cache it, it's faster." Second-order asks who now serves stale data, and third-order asks what they build to work around it.
base-rate — Before reasoning about THIS case, ask: what happens to MOST cases like it? Most rewrites fail. Most "quick migrations" take 3×. Most features get <10% adoption. Start from the base rate, then justify — with specifics, not optimism — why this instance beats it. No specifics = it doesn't.
analogy — Name 2–3 systems that solved a structurally identical problem (different domain welcome: logistics, biology, markets, other codebases). Steal the shape of the solution, then list where the analogy BREAKS — the break-points are where your real design work lives.
flip — Take the binding constraint and negate it. "We can't change the schema" → design as if you could; is the result 10× better? Then the real task is removing the constraint, not working around it. Also run the reverse: add a brutal constraint ("must work offline", "10ms budget", "one file") and see what the forced simplicity teaches.
decompose — The problem resists because it's actually 3 problems wearing a coat. Split until each piece has a known solution or a nameable unknown. The nameable unknowns are the real work; everything else is assembly.
Routing (when invoked with a problem, not a move)
| Smell | Move |
| Consensus came too easily | invert |
| Change looks free | second-order |
| "This time is different" energy | base-rate |
| Genuinely novel problem | analogy, then decompose |
| Grinding against a wall | flip |
| Too big to hold in your head | decompose |
Procedure
- State the problem in one sentence.
- Pick ONE move (use the routing table; say why).
- Execute it fully — the listed outputs, not a gesture at them.
- End with: what changed? A new risk found, a decision reversed, a constraint to attack, sub-problems named. If nothing changed, say so and either run ONE different move or stop — don't move-shop until something agrees with you.
Composes with
/premortemisinvertspecialized for shipping;/altitudeisdecomposespecialized for bugs. Use those when they fit; /think covers the open field./door— one-way doors deserve asecond-orderpass before committing.- Output verdicts worth keeping →
/verdict log THINK: …. /premortemand/altitudename /think back as the general form of their moves.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

