instinct-import
Skill3 starsChanged 7 months agoMITView on GitHub
Import instincts from teammates or community collections
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
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 8
Import instincts from external sources (teammates, community, exported files).
- Distinctive: line 23
Verify required fields (id, trigger, confidence, domain)
- Distinctive: line 24
Check for conflicts with existing instincts (same id or overlapping trigger)
“Common” is measured: kept by at least 6 in 10 of the 3 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
/instinct-import
Import instincts from external sources (teammates, community, exported files).
Arguments
$ARGUMENTS— Path to instinct file, directory, or URL
Process
1. Source Detection
Identify the source format:
- Single
.mdfile: Import one instinct - Directory: Import all instincts from directory
- JSON/YAML file: Import structured instinct collection
2. Validation
For each instinct being imported:
- Verify required fields (id, trigger, confidence, domain)
- Check for conflicts with existing instincts (same id or overlapping trigger)
- Validate confidence score is in range [0.1, 0.9]
3. Conflict Resolution
## Import Conflicts
| Instinct | Existing | Incoming | Resolution |
|----------|----------|----------|------------|
| prefer-const | 0.7 (personal) | 0.5 (imported) | Keep higher (0.7) |
| use-errgroup | — | 0.6 (imported) | Import as new |
| validate-zod | 0.9 (personal) | 0.8 (imported) | Keep existing |Merge strategies:
- Higher confidence wins (default): Keep whichever has higher confidence
- Incoming wins: Override with imported values
- Flag for review: Mark conflicts for manual resolution
4. Storage
Imported instincts are stored in:
~/.claude/instincts/inherited/
teammate-prefer-const.md
community-use-errgroup.mdEach imported instinct is tagged with:
source: importedimported_from: [filename or teammate]imported_at: [timestamp]original_confidence: [score]
5. Report
## Import Complete
- Imported: 5 instincts
- Skipped (conflicts): 2
- New domains discovered: 1 (database)
- Run `/instinct-status` to reviewOther versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- mycelium-hq/ai-brain-starter★ 50same name
- PatriotAgenticLLC/better_claude_skillz★ 3same name
- TheKREATORS/my-claude-skills★ 1same name
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 repository72 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- api-designerSkill
- backend-patternsSkill
- code-reviewerSkill
- debugging-assistantSkill
- golang-testingSkill
- project-guidelines-exampleSkill
- python-testingSkill
- refactoring-guideSkill
- spec-driven-developmentSkill
- tdd-workflowSkill
- verification-loopSkill
- update-docsSkill
- api-docsSkill
- changelog-writerSkill
- readme-generatorSkill
- django-patternsSkill
- django-securitySkill
- django-tddSkill
- django-verificationSkill
- fastapi-patternsSkill
- nextjs-patternsSkill
- react-patternsSkill
- springboot-patternsSkill
- springboot-securitySkill
- springboot-tddSkill
- branch-strategySkill
- changelogSkill
- commit-helperSkill
- pr-creatorSkill
- prSkill
- evolveSkill
- instinct-exportSkill
- instinct-statusSkill
- cleanupSkill
- lint-fixSkill
- refactor-cleanSkill
- update-depsSkill
- continuous-learningSkill
- continuous-learning-v2Skill
- eval-harnessSkill
- iterative-retrievalSkill
- strategic-compactSkill
- golang-patternsSkill
- python-patternsSkill
- rust-patternsSkill
- typescript-patternsSkill
- accessibility-checkerSkill
- build-fixSkill
- code-reviewSkill
- e2eSkill
- performance-reviewerSkill
- security-auditorSkill
- security-reviewSkill
- test-coverageSkill
- checkpointSkill
- deploySkill
- evalSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

