instincts
Skill7 starsChanged 3 months agoMITView on GitHub
Show all learned instincts for this project with confidence scores, grouped by domain. Use to review what the project has learned and identify patterns ready for evolution.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- SKB3002/agenthubtheir own version, first seen Apr 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- SKB3002/agenthub★ 4same 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 repository25 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- enlightenSkill
- brainstormingSkill
- ce-brainstormSkill
- ce-compound-refreshSkill
- ce-compoundSkill
- ce-ideateSkill
- ce-planSkill
- ce-reviewSkill
- ce-workSkill
- claude-permissions-optimizerSkill
- deepen-planSkill
- document-reviewSkill
- evolveSkill
- feature-videoSkill
- karpathy-guidelinesSkill
- learnSkill
- lfgSkill
- observeSkill
- ralph-loopSkill
- resolve_todo_parallelSkill
- setupSkill
- slfgSkill
- test-browserSkill
- unslopSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read .atv/instincts/project.yaml.
- Distinctive: line 46
After the dashboard, suggest actions:
- Distinctive: line 48
If any instincts have confidence > 0.8: "★ N instincts are ready to evolve into skills.
- Distinctive: line 49
If no instincts exist: "Run /learn to extract patterns from your recent work"
- Distinctive: line 50
If instincts exist but are old (last_seen > 14 days): "Some instincts are stale.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
/instincts — View Learned Patterns
Display all instincts learned for this project, grouped by domain with confidence scores.
Execution Flow
Step 1: Read Instincts
Read .atv/instincts/project.yaml. If the file doesn't exist, report:
No instincts found. Run /learn to extract patterns from your work.Step 2: Display Dashboard
Group instincts by domain and show:
Project Instincts — [project name from git remote or directory]
Code Style (3 instincts)
● prefer-early-returns 0.8 "use early returns instead of deep nesting" 12 obs
● kebab-case-files 0.7 "name files with kebab-case" 8 obs
○ trailing-commas 0.4 "use trailing commas in multi-line literals" 3 obs
Error Handling (2 instincts)
★ always-wrap-errors 0.9 "wrap errors with fmt.Errorf using %w" 15 obs
● sentinel-errors 0.6 "use sentinel errors for expected conditions" 5 obs
Testing (2 instincts)
● table-driven-tests 0.7 "use table-driven test pattern" 9 obs
○ test-helpers-in-helpers 0.3 "put test helpers in _test.go helpers file" 2 obs
Legend: ★ ready to evolve (>0.8) ● active ○ tentative (<0.5)
Total: 7 instincts across 3 domains
Last learned: 2026-04-06Step 3: Recommendations
After the dashboard, suggest actions:
- If any instincts have confidence > 0.8: "★ N instincts are ready to evolve into skills. Run /evolve"
- If no instincts exist: "Run /learn to extract patterns from your recent work"
- If instincts exist but are old (last_seen > 14 days): "Some instincts are stale. Run /learn to refresh"
Confidence Indicators
| Symbol | Range | Meaning |
| ★ | > 0.8 | Ready to evolve into a full skill |
| ● | 0.5–0.8 | Active — seen multiple times |
| ○ | < 0.5 | Tentative — needs more evidence |
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.

