skill-evolution
/skill-evolution
Use when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one branch and one pull request, and lands nothing without the owner's merge. Also use when asked why a skill changed, what the loop would propose next, or how to reject a proposal so it is not raised again.
- Author
- coco-research ↗
- Repository
- coco ↗
- Licence
- MIT
- Last repository change
- 25.10.2026
Assessment and security
- Files in this package
- 8
- Scripts
- 1
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 1 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: scripts/ledger.py
What it does and when to use it
Use when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one branch and one pull request, and lands nothing without the owner's merge. Also use when asked why a skill changed, what the loop would propose next, or how to reject a proposal so it is not raised again.
Original author description
Use when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one branch and one pull request, and lands nothing without the owner's merge. Also use when asked why a skill changed, what the loop would propose next, or how to reject a proposal so it is not raised again.
How it works
- The one rule
- What a cycle does
- What the guard refuses
- Exit codes
- Cost
- Where things live
- Testing
- Changing this skill
SKILL.md preview
--- name: skill-evolution description: "Use when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one branch and one pull request, and lands nothing without the owner's merge. Also use when asked why a skill changed, what the loop would propose next, or how to reject a proposal so it is not raised again." domain: meta --- # Skill Evolution A cycle that improves this repository's own skills from observed use, and proposes every change for a human to merge. It never writes to `main` and never merges. **Status:** the scripts this file documents, `scripts/evolve.py` and the steps it runs, are not on `main` yet, so the commands below do not run today. They land with plan tasks 2 to 9 in `.metagpt/plan.md`: task 2 `ledger.py` through task 8 `evolve.py`, and task 9 `run_fixtures.sh` with the CI join. ## The one rule **The loop proposes. The owner decides.** There is no confidence level, budget or green gate that lets it land a change on its own. This is a design invariant, not a setting: a system that edits the repository that measures it has no natural stopping point. ## What a cycle does Five steps, and only the second one calls a model. | Step | Script | Model? | Output | | --- | --- | --- | --- | | 1. Observe | `scripts/observe.py` | no | `signals/<cycle>.json`, pinned to one commit | | 2. Propose | `scripts/propose.py` | yes, one lane | `proposals/<id>.json` and `proposals/<id>.patch` | | 3. Validate | `scripts/validate.py` | no | accept or refuse, with a reason | | 4. Open | `scripts/evolve.py` | no | one branch, one pull request | | 5. Record | `scripts/ledger.py` | no | a ledger row per event, and `CYCLE.md` | Run it: ``` python3 scripts/evolve.py run --window 30d # the real cycle, needs credentials python3 scripts/evolve.py run --window 30d --dry-run # stops before opening a branch python3 scripts/evolve.py run --window 30d --lane stub # no network at all python3 scripts/evolve.py status # last cycle, open proposals ``` ## What the guard refuses `validate.py` is the only thing standing between a model's output and a branch. It refuses, with the reason named, when any of these hold: - **Out of scope.** v1 may change a skill's `description` frontmatter, its `references/` and its `SKILL.md` prose, and may add or remove example blocks. A persona file, a command file, a count file, a workflow or this skill's own scripts are all out of bounds. - **An unresolvable citation.** Every proposal cites its evidence by file and line, or by receipt id, and the citation must resolve at the pinned commit. - **Over a cap.** Proposals per cycle and diff size per proposal are both capped in `references/lanes.json`. A cycle that hits the cap states the remainder rather than truncating silently. - **Already rejected.** A diff whose hash a ledger row rejected inside the two cycle window is not proposed again. - **A count that moved alone.** If a proposal changes a published number, the coupled files must move with it, checked by running the repository's own checkers rather than a private copy of their rules. See `docs/rules.md` R7. ## Exit codes Three valued, like every gate in this repository: **0** pass, **1** blocked by a guard, **2** unrunnable or unmeasured. An empty cycle is exit 0 with nothing to propose, which is a valid result and not a failure. ## Cost Every model call goes through `scripts/lane.py`, which reads `references/lanes.json`, checks the cycle budget **before** spending, obeys the model routing policy, and records the lane id and token count on the proposal it produced. The expensive review lane refuses unless the owner has explicitly authorised it for that cycle. ## Where things live - `references/lanes.json` - the allowed lanes and their budgets. - `references/proposal-schema.json` - the proposal shape, and the only fields a proposal may carry. - `references/signal-sources.md` - what `observe.py` reads and what it deliberately does not. - `state/ledger.jsonl` - the committed ledger. Append only. One record per event, and the record of why something was rejected is the part that matters. - `state/CYCLE.md` - the rendered human artifact for the most recent cycle. ## Testing `bash scripts/run_fixtures.sh` runs every suite and prints `N/N passed`. Every case uses the stub lane, so the suite needs no network and no model. CI runs the same command, so a proposal pipeline that stops working fails the build rather than shipping quietly. ## Changing this skill Changing the loop's own scripts is out of scope for a loop proposal by design, which means a change here is an ordinary pull request from a human or an agent working under review. If a change alters a rule in this file, say so in the PR title and update `docs/rules.md` in the same commit.
Files in this package (8)
- SKILL.md 5 KB
- references/lanes.json 3 KB
- references/proposal-schema.json 4 KB
- references/signal-sources.md 3 KB
- scripts/ledger.py 15 KB
- scripts/fixtures/ledger/chain.jsonl 2 KB
- scripts/fixtures/ledger/malformed.jsonl 1 KB
- state/README.md 2 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · coco-research/coco | 100 | MIT |
| Lin-Yu-kuan/mySkill | 100 | MIT |
| Sirius-Ji/dsh-disciplinary-skills-for-greenhands | 100 | MIT |
| beita6969/scienceclaw | 100 | MIT |
| echoleesong/claude-skills-plugin | 100 | MIT |
Database snapshot: 13.11.2026 · package version 89b30b7da52a (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100coco-loop
Start a safe, governed autonomous loop from a plain-language goal. Use when the user says /coco-loop, "run an autonomous loop", "keep my build green for N hours", "work on X autonomously for a while", or wants a bounded self-improving loop that proposes fixes and never commits… - 100self-evolution
复盘已经发生的工作并沉淀改进,不是“我们来进化 X”的产品入口。 Use when: operator scope 发散偏离愿景、同类错误反复出现、SOP 流程缺口、有价值的知识/方法论值得沉淀。 Not for: 用户询问“能进化什么”、能力进化边界,或要求“我们来进化 X”(用 capability-evolution);日常 SOP 推进(正常执行);一次性个案 bug fix。 Output: Scope Guard Log 记录 / Evolution Proposal 提案 / Episode Card → Method/Skill 蒸馏 → Eval 验证。 - 100evolution-loop
Use after meaningful task closeout, repeated failure, review loops, stale triggers, or user feedback that an agent/skill/workflow should improve. Turns verified signals into auditable, bounded evolution proposals for agents, skills, memory, and README guidance. DO NOT USE FOR:… - 100skill-evolution-engine
Manages skill version history and automated improvement cycles. Use for: evolve skills, version skills, skill maintenance, `skill-evolver`. - 95evolve
Opt-in self-evolution. One backlog class per alarm, evolve/* branch, separate reviewer, pull request on the fork only. Use for /evolve, evolution, self-modify. - 98coco
COCO (Claude Orchestrating Cheaper Agents). Use whenever the user says "use coco" or mentions COCO, and proactively to Offload token-heavy work (web research, browsing URLs, bulk/boilerplate coding, code review, summarising large files, simple rewrites) to cheaper worker agents…