A-Evolve Agent Evolution
Orchestra-Research/AI-Research-SKILLs
Guidance for using A-Evolve to improve an AI agent automatically, evolving its prompts, skills and memory against a benchmark through solve, observe and evolve cycles.
Self-evolving skill system. An agent skill from vibeeval/vibecosystem.
MITAuto-check passed
Install Skill Evolution
$ npx skills add vibeeval/vibecosystem --skill skill-evolution -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install vibeeval/vibecosystem skill-evolution --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-evolution .claude/skills/skill-evolution && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skill-evolution" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/skill-evolution into .claude/skills/skill-evolution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-evolution", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/vibeeval/vibecosystem/tree/main/skills/skill-evolutionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add vibeeval/vibecosystem --skill skill-evolution -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install vibeeval/vibecosystem skill-evolution --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-evolution .agents/skills/skill-evolution && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-evolution" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/skill-evolution into .agents/skills/skill-evolution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-evolution", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vibeeval/vibecosystem --skill skill-evolution -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install vibeeval/vibecosystem skill-evolution --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-evolution .cursor/skills/skill-evolution && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skill-evolution" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/skill-evolution into .cursor/skills/skill-evolution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-evolution", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/vibeeval/vibecosystem.git --path skills/skill-evolution--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add vibeeval/vibecosystem --skill skill-evolution -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install vibeeval/vibecosystem skill-evolution --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-evolution .gemini/skills/skill-evolution && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skill-evolution" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/skill-evolution into .gemini/skills/skill-evolution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-evolution", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install vibeeval/vibecosystem skill-evolutionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add vibeeval/vibecosystem --skill skill-evolution -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-evolution .github/skills/skill-evolution && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skill-evolution" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/skill-evolution into .github/skills/skill-evolution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-evolution", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vibeeval/vibecosystem --skill skill-evolution -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install vibeeval/vibecosystem skill-evolution --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-evolution .opencode/skills/skill-evolution && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skill-evolution" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/skill-evolution into .opencode/skills/skill-evolution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-evolution", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
skill-evolution- GitHub stars
- 531
- Token cost
- ~1.8k tokens
- SKILL.md length
- 562 words
- Files
- 1
- Skills in repo
- 144
- Repo updated
- First seen
- Licence
- MIT
At a glance
Self-evolving skill system. An agent skill from vibeeval/vibecosystem.
- Works in 5 steps: Verify scores in… → Add locked: true to the skill's… → Apply git tag → …
- SKILL.md covers The 5 Scoring Dimensions, Skill Lifecycle, Score Storage Format and Crystallization Protocol, plus 4 more sections
- Calls python3, git and node
What it does
Skill Evolution is an agent skill from vibeeval/vibecosystem. Self-evolving skill system. Skills are scored after execution (0-100) on 5 dimensions. Score 90+ over 5 runs = crystallized (locked). Score below 30 = auto-repair attempted. Skills improve themselves through usage feedback.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: AI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution. The licence is MIT.
Example prompts
- “/skill-evolution”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Verify scores in ~/.claude/skill-scores.jsonl -- confirm no outliers inflating the average
- Add locked: true to the skill's frontmatter
- Apply git tag
- Log the crystallization in thoughts/SKILL-EVOLUTION.md
- Notify via canavar cross-training so all agents know this skill is stable
What it can do on your machine
Read from SKILL.md and the folder at commit 3b763b1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python3gitnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Skill Evolution loads about 1.8k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 562 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from vibeeval/vibecosystem at commit 3b763b1, republished under its MIT licence (© vibeeval). 562 words, ~1,814 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-evolution/SKILL.md (or your agent's skills folder).- name
- skill-evolution
- description
- Self-evolving skill system. Skills are scored after execution (0-100) on 5 dimensions. Score 90+ over 5 runs = crystallized (locked). Score below 30 = auto-repair attempted. Skills improve themselves through usage feedback.
Skill Evolution
Darwinian selection for skills. Skills that produce good outcomes are crystallized and protected. Skills that produce poor outcomes are repaired or archived. Every execution generates a score that drives the next generation of the skill.
The 5 Scoring Dimensions
Each skill execution is scored 0-100 on five dimensions:
| Dimension | Weight | What It Measures |
|---|---|---|
| Accuracy | 25% | Did the skill produce the correct result for the task? |
| Relevance | 20% | Was the skill content applicable to the actual use case? |
| Token Efficiency | 20% | Did the skill guide the agent without bloat or repetition? |
| User Satisfaction | 20% | Did the outcome meet or exceed user expectations? |
| Reusability | 15% | Could another agent use this skill in a similar situation? |
Composite score = weighted average of all five dimensions (0-100).
Scoring Rubric
90-100: Excellent -- candidate for crystallization
70-89: Good -- active skill, no action needed
50-69: Adequate -- flag for review after 3 more runs
30-49: Poor -- schedule auto-repair attempt
0-29: Critical -- immediate auto-repair or archiveSkill Lifecycle
DRAFT ACTIVE CRYSTALLIZED ARCHIVED
| | | |
New skill In regular use Proven stable Deprecated/replaced
| | | |
+-- first run ->+-- score >90 ++-- score <30 |
| for 5+ runs | (3 attempts) |
+-- score <30 -->+ auto-repair |
| auto-repair | fails 3x -->--+
+-- score >90 -->+Draft
New skills enter as Draft. They receive no special protection and are evaluated critically on first use. A Draft skill that scores below 30 on its very first run is discarded rather than repaired.
Active
Skills in regular use. Scores are tracked in ~/.claude/skill-scores.jsonl. No action unless scores trend below 30 or above 90 over a rolling window of 5 runs.
Crystallized
A skill that maintains an average composite score above 90 over 5 or more consecutive runs is crystallized:
- Git tag applied:
skill/<name>/crystallized-v<N> - Read-only flag added to frontmatter:
locked: true - Skill is excluded from auto-repair
- Changes require explicit human unlock + PR
Archived
A skill that fails auto-repair 3 times is archived:
- Moved to
skills/_archived/<name>/ - Git tag applied:
skill/<name>/archived - Replacement skill drafted by
catalystagent if the capability is still needed
Score Storage Format
Append one record per execution to ~/.claude/skill-scores.jsonl:
{"skill":"experiment-loop","ts":"2026-04-07T10:00:00Z","session":"abc123","scores":{"accuracy":88,"relevance":92,"token_efficiency":75,"user_satisfaction":90,"reusability":85},"composite":86.5,"feedback":"Loop ran 4 iterations successfully, target nearly met"}
{"skill":"experiment-loop","ts":"2026-04-07T14:30:00Z","session":"def456","scores":{"accuracy":95,"relevance":90,"token_efficiency":82,"user_satisfaction":95,"reusability":88},"composite":90.4,"feedback":"Bundle size reduced 28%, target exceeded"}Score CLI (quick check)
# Average scores for a skill (last 10 runs)
cat ~/.claude/skill-scores.jsonl | python3 -c "
import sys, json, statistics
skill = '$1'
runs = [json.loads(l) for l in sys.stdin if json.loads(l).get('skill') == skill][-10:]
if runs:
avg = statistics.mean(r['composite'] for r in runs)
print(f'{skill}: {avg:.1f} avg over {len(runs)} runs')
"Crystallization Protocol
When a skill reaches 90+ composite score over 5+ consecutive runs:
- Verify scores in
~/.claude/skill-scores.jsonl-- confirm no outliers inflating the average - Add
locked: trueto the skill's frontmatter - Apply git tag:
bash git tag skill/<name>/crystallized-v1 -m "Crystallized: avg score 92.3 over 7 runs" git push origin skill/<name>/crystallized-v1 - Log the crystallization in
thoughts/SKILL-EVOLUTION.md - Notify via canavar cross-training so all agents know this skill is stable
Show full SKILL.md (233 more words)Show less
Auto-Repair Protocol
When a skill's composite score drops below 30:
Diagnosis
- Identify the lowest-scoring dimension (the primary failure mode)
- Read the last 3 session feedback notes from
~/.claude/skill-scores.jsonl - Summarize what went wrong (specific, not vague)
Repair
The catalyst agent rewrites the failing section(s) of the skill:
- Only the sections relevant to the low-scoring dimension
- Preserve all high-scoring sections unchanged
- Add a concrete example for the repaired section
Validation
After repair, the skill is re-scored on a synthetic test case by the verifier agent:
- Synthetic score must be 50+ to proceed to Active state
- If synthetic score < 50, attempt 2 of 3 repairs begins
Escalation
After 3 failed auto-repairs:
- Archive the skill
- Alert via
thoughts/SKILL-EVOLUTION.md - Spawn
catalystto draft a replacement from scratch
Evolution Log Format
Append events to thoughts/SKILL-EVOLUTION.md:
## 2026-04-07
### skill: experiment-loop
- Status change: Active -> Crystallized
- Trigger: avg composite 91.2 over 6 consecutive runs
- Git tag: skill/experiment-loop/crystallized-v1
- Notable strength: Token Efficiency dimension consistently 85+
### skill: legacy-deploy-helper
- Status change: Active -> Auto-Repair (attempt 1/3)
- Trigger: composite 24 on last run
- Lowest dimension: Relevance (12) -- skill referenced outdated Heroku patterns
- Repair: catalyst rewrote "Deployment Targets" section with Vercel/Railway focus
- Post-repair synthetic score: 71 -- promoted back to ActiveIntegration with Canavar Cross-Training
Skill evolution data feeds into canavar's cross-training pipeline:
- A crystallized skill is injected into canavar's
skill-matrix.jsonwithtrust: locked - An archived skill is marked
trust: deprecated-- agents stop referencing it - Auto-repair failures are logged to
error-ledger.jsonlwithsource: skill-evolution - The canavar leaderboard tracks which agents most frequently produce high-scoring skill executions
# View crystallized skills
node ~/.claude/hooks/dist/canavar-cli.mjs leaderboard --filter crystallized
# View skills needing repair
cat ~/.claude/skill-scores.jsonl | python3 -c "
import sys, json, collections
runs = [json.loads(l) for l in sys.stdin]
low = {r['skill'] for r in runs if r['composite'] < 30}
print('Skills needing repair:', low)
"Activation
This skill activates automatically when:
- A skill completes an execution (PostToolUse hook)
- A skill is referenced in a session that ends with user dissatisfaction
- The
verifieragent reports a skill-guided task as failed
Agents involved: catalyst (repair), verifier (validation), self-learner (feedback extraction), canavar (cross-training propagation).
© vibeeval, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/skill-evolution of vibeeval/vibecosystem.
Open the folder on GitHubat commit 3b763b1
Compare with similar skills
Skill Evolution next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skill Evolution this skillvibeeval/vibecosystem | 531 | — | ~1.8k | Automated safety check: Pass | MIT | |
| A-Evolve Agent EvolutionOrchestra-Research/AI-Research-SKILLs | 13k | 1 repos | ~3.6k | Automated safety check: Pass | MIT | |
| Harness Evolveruvnet/ruflo | 74k | — | ~1.6k | Automated safety check: Notes | MIT | |
| Evolver Agent Self-EvolutionEvoMap/evolver | 9.1k | 1 repos | ~2.2k | Automated safety check: Pass | GPL-3.0 | |
| Evolutionsickn33/agentic-awesome-skills | 47k | 2 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Darwin Mode Harness Evolutionruvnet/RuView | 97k | — | ~693 | Automated safety check: Pass | MIT |
Similar skills
Harness Evolve
ruvnet/ruflo
Run @metaharness/darwin evolve <repo to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, and…
Evolver Agent Self-Evolution
EvoMap/evolver
Self-evolution engine for agents: studies runtime history for failures and inefficiencies, writes improvements, and syncs with the EvoMap Hub through a local proxy mailbox.
Evolution
sickn33/agentic-awesome-skills
This skill enables makepad-skills to self-improve continuously during development.
Darwin Mode Harness Evolution
ruvnet/RuView
Runs Darwin Mode on an agent harness: mutates one policy file per generation in a sandbox, scores each variant against your tests, and archives only variants that measurably improve.
Harness Score
ruvnet/ruflo
5-dimension harness readiness scorecard from metaharness score <path.
More from vibeeval/vibecosystem
All 144 skills in this repoAgent Benchmark
vibeeval/vibecosystem
Framework for measuring and tracking agent response quality over time.
Differential Review
vibeeval/vibecosystem
Security-focused differential code review with blast radius analysis, risk-adaptive depth (DEEP/FOCUSED/SURGICAL), git history correlation, and structured finding format.
Factcheck Guard
vibeeval/vibecosystem
A skill your agent uses when making any factual claim about the codebase — existence, absence, or behavior.
Fp Check
vibeeval/vibecosystem
Systematic false positive verification for security findings.
N8n Workflows
vibeeval/vibecosystem
n8n otomasyon workflow'lari. An agent skill from vibeeval/vibecosystem.
Notepad System
vibeeval/vibecosystem
A skill your agent uses when context compression is imminent, when resuming a session, or when preserving critical decisions across long tasks.
Questions about Skill Evolution
What does Skill Evolution do?
Self-evolving skill system. An agent skill from vibeeval/vibecosystem. Skill Evolution is an agent skill from vibeeval/vibecosystem. Self-evolving skill system.
How do I install Skill Evolution in Claude Code?
Run `npx skills add vibeeval/vibecosystem --skill skill-evolution -a claude-code`. Or copy the skill folder (skills/skill-evolution in vibeeval/vibecosystem) into .claude/skills/skill-evolution in your project. Claude Code loads it when a task matches its description.
How do I install Skill Evolution in Codex?
Run `npx skills add vibeeval/vibecosystem --skill skill-evolution -a codex`. Or copy the skill folder (skills/skill-evolution in vibeeval/vibecosystem) into .agents/skills/skill-evolution in your project. Codex loads it when a task matches its description.
Can I use Skill Evolution in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vibeeval/vibecosystem --skill skill-evolution -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-evolution, .gemini/skills/skill-evolution, .github/skills/skill-evolution and .opencode/skills/skill-evolution in your project.
What does Skill Evolution need to run?
Going by SKILL.md and its folder, Skill Evolution needs the command-line tools its instructions call (python3, git and node). Our summary lists: Python 3.
Does Skill Evolution access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Skill Evolution safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Skill Evolution use?
Skill Evolution is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Skill Evolution use?
About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Skill Evolution?
Skills that share tags, products or a category with Skill Evolution: A-Evolve Agent Evolution (Orchestra-Research/AI-Research-SKILLs, 13k stars), Harness Evolve (ruvnet/ruflo, 74k stars), Evolver Agent Self-Evolution (EvoMap/evolver, 9.1k stars) and Evolution (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skill Evolution?
vibeeval (a GitHub user) maintains it in vibeeval/vibecosystem, which has 531 GitHub stars. The repository holds 144 skills in this directory. The repository was last updated on August 8, 2026.
Source: vibeeval/vibecosystem on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.