think
Skill2 starsChanged 9 days agoMITView on GitHub
Think a plan, decision or idea through with focused questions until it is ready to build. Use when the user says think or thinking about a plan, decision or idea, such as think this through, think about it or keep thinking, asks to interrogate or stress-test it, or wants an interview to clarify their thinking.
30 other projects use a version of this.
Adopted by
Most recently taken up by
- ronniepinnell/caspertheir own version, first seen Nov 8, 2026
- hurleywgly/skillstheir 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.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-tuneupSkill
- babysitterSkill
- challengeSkill
- choose-designSkill
- design-loopSkill
- focus-groupSkill
- github-writingSkill
- implementSkill
- raise-issueSkill
- raise-prSkill
- review-loopSkill
- reviewSkill
- shipSkill
- test-writerSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 25 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Ask the currently answerable questions together through the host's question tool, or numbered text questions when no question tool is …
- Distinctive: line 20
After the answers, revisit only affected decisions.
- Distinctive: line 22
When you believe it is met, summarize the goal, scope, choices, constraints, assumptions, observable acceptance criteria, verification …
- Distinctive: line 26
If the user requests an exhaustive interview, continue to that endpoint instead.
- Distinctive: line 28
Before concluding the interview or handing off implementation, use review to obtain a cross-lineage second opinion on that stop condition.
- Distinctive: line 37
Verify material gaps, investigate available facts and ask only the affected questions that need the user.
- Distinctive: line 50
After readiness is established, honour an already-requested artifact or implementation endpoint.
- Distinctive: line 61
Use numbered text questions only when no question tool is available.
“Common” is measured: kept by at least 6 in 10 of the 25 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Think through the decisions that matter
Find the decisions whose answers could materially change the goal, design, risk or next implementation step. Reuse settled decisions and inspect available facts before asking the user. Look up small facts directly; delegate substantial, independent investigations only when the host supports them and scope permits. Apply T3 dispatch preflight before those T3 investigations.
Ask the currently answerable questions together through the host's question tool, or numbered text questions when no question tool is available, with one decision per question, your recommendation first and its tradeoff. Defer questions that depend on an unanswered decision. Do not turn routine, reversible choices into owner decisions.
After the answers, revisit only affected decisions. The stop condition is that the remaining uncertainty cannot materially change the next implementation step. When you believe it is met, summarize the goal, scope, choices, constraints, assumptions, observable acceptance criteria, verification methods and unresolved gates in a concise brief. Preserve material rejected alternatives and their reasons; do not exhaust every possible branch. If the user requests an exhaustive interview, continue to that endpoint instead.
Before concluding the interview or handing off implementation, use review to obtain a cross-lineage second opinion on that stop condition. Supply the original request, current brief, settled decisions, assumptions, relevant facts and intended next implementation step. Ask the reviewer to state whether the condition is met and identify any remaining uncertainty whose resolution could materially change that step, with its impact and the question or investigation needed. This is a readiness review, not a requirement to implement the feature or invent extra questions.
Verify material gaps, investigate available facts and ask only the affected questions that need the user. Revise the brief and obtain a fresh readiness review when material gaps change it. Allow at most three readiness reviews, including failed attempts, across the interview and its resumes. If the budget is exhausted or reviews stall, apply review's budget diagnosis within this three-review limit. If readiness remains unverified or cross-lineage review is unavailable, report readiness as incomplete and hold implementation. Still provide the brief in the requested format, or offer the artifact choices below, marked not ready with the review gate and next action. A reviewer verdict without supporting reasoning does not establish readiness.
After readiness is established, honour an already-requested artifact or implementation endpoint. Otherwise use the host's ask-user-question tool to ask what the user wants to create:
- An issue, with sub-issues when the work warrants them.
- A Markdown brief saved to a file.
- Complete the work now in the same session
For a chosen issue endpoint, apply raise-issue to prepare and file the accepted brief in the owning repository.
Use numbered text questions only when no question tool is available. Wait for the user's choice before creating either artifact. Carry the settled decisions, assumptions and unresolved gates into the chosen artifact. Confirm a missing issue destination only if it cannot be inferred from context. For the Markdown option, honour any supplied path. Otherwise use the host-approved artifact location, verifying an ignored directory inside the session worktree when required. Report the file's absolute path and preserve it for the user's handoff.
This skill alone does not authorize implementation. If implementation is already requested, continue within that authority once material decisions are settled and the readiness review establishes the stop condition. For UI implementation, apply choose-design after settling product decisions and before editing when its trigger applies. Preserve explicit constraints.
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.

