evolve
Skill7 starsChanged 3 months agoMITView on GitHub
Promote mature instincts (confidence > 0.8) into full Copilot skills that get auto-discovered. Clusters related instincts and generates SKILL.md files in .github/skills/.
41 other projects use a version of this.
Adopted by
Most recently taken up by
- SethGammon/Citadeltheir own version, first seen Nov 4, 2026
- vidit19sharma/neogentstheir own version, first seen Nov 1, 2026
- cabernect/caberostheir own version, first seen Nov 1, 2026
- Snowflake-Labs/coco-skillstheir own version, first seen Nov 1, 2026
- NobiResearch/Ovenbirdtheir own version, first seen Nov 1, 2026
- ES-92/esctheir own version, first seen Oct 20, 2026
Used with
Projects with it also use instinct-export, instinct-import 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.
TheKREATORSSkillinstinct-export
Export instincts from project/global scope to a file
Also in 4 projects that use this
TheKREATORSSkillinstinct-import
Import instincts from file or URL into project/global scope
Also in 4 projects that use this
AWSSkillmap
Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.
Also in 5 projects that use this
diego-tobalinaSkillbuild-fix
Fix build and compilation errors systematically. Run when build fails.
Also in 3 projects that use this
launch52-aiSkillskill-create
Create and validate Claude Code skills with proper structure, checklists, and validation scripts. Use when creating a new skill, auditing existing skills, or ensuring skills meet quality standards. Generates complete skill scaffolds with SKILL.md, check scripts, guides, and templates.
Also in 3 projects that use this
qtzx06Skilleval
Evaluate trained YOLO model accuracy with mAP metrics and per-class error analysis. Identifies failure cases for targeted improvement. Use after training.
Also in 5 projects that use this
- +1 more from TheKREATORS
Other versions41 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 41
- revfactory/harness★ 9.1ksame name
- Q00/ouroboros★ 6.3ksame name
- yologdev/yoyo-evolve★ 1.9ksame name
- iovisor/ubpf★ 996same name
- SethGammon/Citadel★ 927same name
- GAIR-NLP/ASI-Evolve★ 867same name
- Kanevry/session-orchestrator★ 53same name
- mycelium-hq/ai-brain-starter★ 50same name
- Snowflake-Labs/coco-skills★ 49same name
- unclejobs-ai/second-claude-code★ 41same name
31 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 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
- feature-videoSkill
- instinctsSkill
- 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
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 36 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
When /instincts shows patterns with ★ (confidence > 0.8)
- Distinctive: line 13
When you want to formalize a recurring pattern into a discoverable skill
- Very specific: line 20
Read .atv/instincts/project.yaml and filter for:
- Very specific: line 23
Not already evolved (check .atv/instincts/archive/)
- Distinctive: line 25
If no candidates found:
- Distinctive: line 100
Always review generated skills before committing — they're a draft
- Distinctive: line 102
If a generated skill doesn't feel right, delete it and the instincts will re-accumulate
“Common” is measured: kept by at least 6 in 10 of the 36 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
/evolve — Promote Instincts to Skills
Transform mature instincts into full Copilot skills. When an instinct reaches high confidence through repeated observation, it has proven valuable enough to become a permanent part of the project's skill set.
When to Use
- When
/instinctsshows patterns with ★ (confidence > 0.8) - When you want to formalize a recurring pattern into a discoverable skill
- Periodically to graduate well-established project conventions
Execution Flow
Step 1: Identify Candidates
Read .atv/instincts/project.yaml and filter for:
- Confidence > 0.8
- Observations > 5
- Not already evolved (check
.atv/instincts/archive/)
If no candidates found:
No instincts ready to evolve yet.
Run /learn to build confidence, or check /instincts for current status.
Instincts need confidence > 0.8 and 5+ observations to evolve.Step 2: Cluster Related Instincts
Group candidates by domain. Each cluster becomes one skill:
Evolution candidates:
Cluster 1: "Go Error Handling" (error-handling domain)
★ always-wrap-errors 0.9 15 obs
★ sentinel-errors 0.85 8 obs
→ Will generate: .github/skills/learned-go-error-handling/SKILL.md
Cluster 2: "Testing Conventions" (testing domain)
★ table-driven-tests 0.85 12 obs
→ Will generate: .github/skills/learned-testing-conventions/SKILL.md
Proceed with evolution? (Copilot will generate the skills)Step 3: Generate SKILL.md
For each cluster, generate a SKILL.md file:
---
name: learned-[domain-name]
description: "[Auto-generated] Project conventions for [domain] learned from [N] observations across [M] sessions."
---The skill content should:
- Describe when to apply these conventions
- List each instinct as a concrete guideline with examples
- Reference the evidence (commit hashes, observation counts)
- Mark as auto-generated so humans know to review
Naming convention: learned- prefix so generated skills are visually distinct from hand-written ones.
Output path: .github/skills/learned-<domain>/SKILL.md
Step 4: Archive Evolved Instincts
Move evolved instincts from project.yaml to .atv/instincts/archive/evolved-YYYY-MM-DD.yaml with metadata:
evolved_to: .github/skills/learned-go-error-handling/SKILL.md
evolved_at: 2026-04-06Step 5: Report
Evolution complete!
Generated skills:
✅ .github/skills/learned-go-error-handling/SKILL.md (from 2 instincts)
✅ .github/skills/learned-testing-conventions/SKILL.md (from 1 instinct)
Archived 3 instincts to .atv/instincts/archive/
These skills will be auto-discovered by Copilot in the next session.
Review the generated files and adjust as needed — they're a starting point.
Remaining instincts: X active (run /instincts to see)Important Notes
- Generated skills use
learned-prefix — easy to spot and edit - Always review generated skills before committing — they're a draft
- Evolved instincts are archived, not deleted, so history is preserved
- If a generated skill doesn't feel right, delete it and the instincts will re-accumulate
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.

