cot
Skill8 starsChanged 3 months agoMITView on GitHub
Chain-of-thought analysis before action. Forces structured reasoning, risk assessment, and explicit plan before execution. Use for any complex, destructive, or important request. Invoke with "/cot [request]" or "use cot: [request]". Triggers on "cot", "chain of thought", "think through".
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- dependency-healthSkill
- hibernateSkill
- repo-docsSkill
- skill-builderSkill
- skill-validatorSkill
- task-cleanupSkill
- template-upgradeSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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 15
When you want explicit reasoning visible
- Distinctive: line 20
When this skill is invoked, analyze the request using this structure:
- Distinctive: line 41
Do NOT proceed to execution.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Chain-of-Thought (COT) Skill
Force structured reasoning before action. Prevents rushing into execution.
When to Use
- Any destructive operation (delete, remove, refactor)
- Complex multi-step tasks
- Decisions with significant consequences
- When you want explicit reasoning visible
- Any time "think carefully" would normally be said
The Pattern
When this skill is invoked, analyze the request using this structure:
1. What is being asked
Restate the request in clear terms. What is the actual goal?
2. What are the considerations
- What files/systems are involved?
- What are the dependencies?
- What context matters?
- Are there multiple valid approaches?
3. What could go wrong
- What are the risks?
- What's irreversible?
- What assumptions are being made?
- What information is missing?
4. Step-by-step plan
Numbered list of discrete actions to accomplish the request.
5. STOP for approval
Do NOT proceed to execution. Wait for explicit:
- "proceed"
- "approved"
- "go ahead"
- "yes"
Invocation
/cot remove all deprecated API endpoints
use cot: refactor the authentication module
/cot what's the best way to restructure this database schemaExample Output
**COT:**
- **Asked:** Remove deprecated API endpoints from the codebase
- **Considerations:**
- Need to identify which endpoints are deprecated
- Check for internal consumers
- May need migration path for external users
- Tests reference these endpoints
- **Risk:**
- Breaking changes for API consumers
- Dead code might still be imported elsewhere
- **Plan:**
1. Grep for @deprecated annotations
2. List all deprecated endpoints with their consumers
3. Check for external API documentation references
4. Create removal plan with each file
5. Stop for approval before any deletion
Awaiting approval to proceed.Why This Exists
"Think carefully" and "plan thoroughly" don't change Claude's behavior. Concrete output requirements do.
This skill creates a mandatory structured output before any action, making the reasoning visible and creating an approval gate.
Origin: 2025-12-29 session where files were deleted without analysis despite explicit request to "think hard, plan carefully"
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.

