think
Skill25 starsChanged 7 months agoMITView on GitHub
Brainstorm, evaluate, or decide during product creation. Pause the pipeline to think through a problem, compare approaches, or explore ideas before committing. Use when: 'think about', 'brainstorm', 'evaluate', 'compare', 'should I', 'help me decide', 'what if', 'not sure about', or any hesitation during /fill.
31 other projects use a version of this.
Adopted by
Most recently taken up by
- romeohc/afkittheir own version, first seen Nov 15, 2026
- ronniepinnell/caspertheir own version, first seen Nov 8, 2026
- 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
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 versions31 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 31
- AgriciDaniel/claude-obsidian★ 16ksame name
- tw93/Waza★ 7.6ksame name
- tw93/claude-health★ 7.5ksame name
- ninehills/skills★ 280same name
- garagon/nanostack★ 206same name
- jonathanmalkin/jules★ 65same name
- TserenTserenov/FMT-exocortex-template★ 64same name
- ironyjk/strategy-frameworks★ 14same name
- therealtinhtute/mono-harness★ 5same name
- ByronFinn/dev-skills★ 4same name
21 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
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 11 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 26 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 31
Read creator.yaml → adapt to profile.type and technical_level
- Very specific: line 32
If a product is active (workspace/{slug}/ exists), read .meta.yaml → understand current context
- Distinctive: line 85
Search workspace/ for related patterns
- Distinctive: line 86
Check product-dna/ for type-specific guidance
- Very specific: line 87
Search marketplace via myclaude search --json 2>/dev/null if relevant (silent-skip on failure per references/cli-contract.md)
- Distinctive: line 88
Read references/ for best practices
- Very specific: line 96
Read current product state from .meta.yaml
- Distinctive: line 98
Ask ONE clarifying question to narrow the block
- Distinctive: line 105
If invoked DURING /fill (detected by conversation context):
- Distinctive: line 106
Don't break the section walker flow
- Distinctive: line 108
After thinking resolves, seamlessly resume: "Ready to continue with {next_section}?"
- Distinctive: line 110
If invoked BETWEEN commands:
- Distinctive: line 114
If invoked with a product slug:
- Distinctive: line 124
If the thinking question is about product strategy ("should I build X?", "is there demand for Y?"):
- Distinctive: line 158
When summarizing this conversation, always preserve:
“Common” is measured: kept by at least 6 in 10 of the 26 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 — Mid-Process Brainstorming & Decision Support
The pipeline builds. This skill thinks. Use it whenever you need to pause, explore, or decide.
When to use: Between any two pipeline steps. During /fill when you're unsure about a section. Before /create when choosing a product type. Before /publish when evaluating readiness.
When NOT to use: For mechanical tasks (/validate, /package). Those have deterministic flows — thinking slows them down.
Activation Protocol
- Shared preamble: Load
references/quality/activation-preamble.md— context assembly, persona adaptation, deterministic routing rules. - Read
creator.yaml→ adapt to profile.type and technical_level - If a product is active (workspace/{slug}/ exists), read
.meta.yaml→ understand current context - Parse
$ARGUMENTSor conversation context to identify the thinking need - Route to the appropriate thinking mode
- Load voice identity: Load
references/quality/engine-voice-core.md. Every user-facing line in this skill honors the ✦ signature, three tones, and six anti-patterns. 5b. Load UX vocabulary: Loadreferences/ux-vocabulary.md— translate all internal terms before creator-facing output. 5c. Load proactives: Loadreferences/engine-proactive.md— wire #17 (lost creator detection: if the creator has been in /think for 3+ questions without resolution, suggest concrete next step or /scout).
Thinking Modes
MODE 1: Brainstorm (divergent)
Trigger: "brainstorm", "ideas for", "what could", "possibilities"
Generate 5-7 distinct approaches to the creator's question. For each:
- Name it in 3 words
- One sentence description
- Strength (why this works)
- Risk (why it might not)
End with: "Which resonates? Or want me to combine elements from multiple?"
MODE 2: Evaluate (convergent)
Trigger: "evaluate", "compare", "which is better", "pros and cons"
Structure the evaluation as a decision matrix:
EVALUATING: {what's being compared}
| Criterion | Option A | Option B | Option C |
|-----------|----------|----------|----------|
| {criterion_1} | {score/assessment} | ... | ... |
| {criterion_2} | ... | ... | ... |
RECOMMENDATION: {option} because {one-sentence reasoning}
RISK: {what could go wrong with the recommendation}MODE 3: Decide (commit)
Trigger: "should I", "help me decide", "which type", "what approach"
Walk through a 3-step decision:
- What are you optimizing for? (speed, quality, simplicity, market fit)
- What are the constraints? (time, skill level, dependencies)
- Given 1+2, the best path is: {recommendation with clear reasoning}
Then: "Ready to act on this? Here's the command: {next_command}"
MODE 4: Explore (research)
Trigger: "what if", "how does", "is there a way to", "explore"
Investigate the question using available context:
- Search workspace/ for related patterns
- Check product-dna/ for type-specific guidance
- Search marketplace via
myclaude search --json 2>/dev/nullif relevant (silent-skip on failure perreferences/cli-contract.md) - Read references/ for best practices
Synthesize findings, then suggest actionable next steps.
MODE 5: Unstuck (unblock)
Trigger: "I'm stuck", "not sure", "confused", "don't know how"
Diagnose the block:
- Read current product state from .meta.yaml
- Identify where in the pipeline the creator is stuck
- Ask ONE clarifying question to narrow the block
- Offer 2-3 concrete paths forward, each as a command or action
Context-Aware Behavior
If invoked DURING /fill (detected by conversation context):
- Don't break the section walker flow
- Frame thinking as "let's pause on this section"
- After thinking resolves, seamlessly resume: "Ready to continue with {next_section}?"
If invoked BETWEEN commands:
- Full thinking mode, no time pressure
- Can explore multiple angles
If invoked with a product slug:
- Load that product's full context before thinking
- Frame recommendations in terms of that specific product
Marketplace Intelligence
CLI contract: Load references/cli-contract.md for unified error handling. Both commands are silent-skip severity — thinking proceeds without marketplace data if CLI is unavailable.
If the thinking question is about product strategy ("should I build X?", "is there demand for Y?"):
myclaude search "{relevant_query}" --json 2>/dev/null
myclaude trending --json 2>/dev/nullSurface: how many similar products exist, their download counts, pricing, and gaps.
"There are {N} products in this space. The top one has {downloads} downloads. Your differentiation could be: {suggestion based on gap analysis}."
Anti-Patterns
- Analysis paralysis — If the creator has been thinking for 3+ rounds without deciding, gently push: "You have enough information to start. The best way to test an idea is to build v1. You can always iterate."
- Thinking when doing is needed — If the question has an obvious answer ("should I add a README?"), skip thinking mode and just do it.
- Scope expansion — Thinking can expand scope. Always anchor back: "This is interesting, but for YOUR current product ({slug}), the relevant part is: {focused takeaway}."
- Replacing /validate — Thinking is subjective exploration. Quality checks are objective. Don't let /think substitute for /validate.
- Endless brainstorm — Cap brainstorm rounds at 3. After 3: "We've explored enough. Pick one and let's build."
Quality Gate
- Thinking output is actionable (ends with a clear next step or command)
- Adapted to creator's language and technical level
- If product context exists, thinking is anchored to that product
- Analysis paralysis guard: no more than 3 rounds without a decision push
Compact Instructions
When summarizing this conversation, always preserve:
- The specific question or decision the creator was thinking about
- Key options evaluated and the reasoning for/against each
- The final recommendation or decision made
- Any marketplace data surfaced during exploration
- The command or action suggested as next step
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.

