agentleFS
Sign inStart free
HeyvhuangHeyvhuang/ship-faster/skills/skill-improver/SKILL.md

skill-improver

Skill337 starsChanged 10 months agoMITView on GitHub

Improve skills and workflows by analyzing run artifacts and execution logs (events.jsonl/state.json) under runs/ (or OpenSpec changes/). Use when you want to iterate on skills based on real runs: find failure modes, bottlenecks, unclear prompts, missing I/O contracts, and propose concrete edits.

19 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 0

    Distinctive

    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
  1. Very specific:

    Read logs/state.json and logs/events.jsonl, extract:

    line 21

“Common” is measured: kept by at least 6 in 10 of the 19 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill Improver

Retrospect and improve Skills/Workflows based on real execution artifacts, making the skill chain more stable with use.

Input (pass path only)

  • run_dir: runs/<workflow>/active/<run_id>/ (or openspec/changes/<change-id>/)

Output

  • improvements.md: Improvement suggestions (can be directly converted to change tasks)
  • Optional: Minimal patch to relevant SKILL.md (only change what's necessary)

Process

  1. Read logs/state.json and logs/events.jsonl, extract:
    • Failure points (error types, frequency, missing context)
    • Time bottlenecks (repetitive steps, ineffective searches, excessive context)
    • Manual confirmation points (whether too early/too late/missing)
  2. Check artifact contracts:
    • Whether each step has persisted output
    • Whether only paths are passed instead of content
    • Whether there are inconsistent naming/paths
  3. Output improvement suggestions (sorted by benefit):
    • Prompt/trigger word optimization
    • I/O contract completion (add required fields, fix artifact file names)
    • Error handling and rejection strategies
    • Suggest new deterministic scripts (only when necessary)

Output Template (recommended)

  • Overview: Core issues from this run
  • Top Issues (high → low): Each includes "symptom/root cause/fix suggestion/related skill/suggested change point"
  • Suggested Minimal Change List: Listed by file

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free