agentleFS
Cassandra-CollectiveCassandra-Collective/Ephesus/.claude/skills/improve/SKILL.md

improve

Skill2 starsChanged 3 months agoMITView on GitHub

File a Gymnasium self-improvement proposal for Ephesus — scan the repo and its records for the highest-leverage improvement, write a structured proposal with measurable success criteria, and queue it for the Architect. Use when asked to find improvements, when a retro/review surfaces recurring friction, or on a scheduled improvement pass.

70 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use deploy-platform, setup-platform and 8 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.
  • agno-agiSkill

    deploy-platform

    Deploy this AgentOS using its own provider instructions, configure JWT verification, and verify the public service. Use for first deployment, redeployment, or production configuration changes.

    Also in 4 projects that use this

  • agno-agiSkill

    setup-platform

    Set up this AgentOS from a fresh clone — confirm Docker, configure .env, boot the containers, prove the MCP endpoint live, connect the AgentOS UI, then build the user's first agent. Use when the user asks to set up the platform, get started, or bring this repo up on a new machine.

    Also in 4 projects that use this

  • MicrosoftSkill

    create-agent

    Create a new MCS2 Copilot Studio agent and PAC-connected local workspace with `pac copilot init`, then optionally add modern instructions, skills, tools, knowledge, and settings before synchronizing it. Use when the user asks to create, scaffold, initialize, or build a Copilot Studio agent.

    Also in 5 projects that use this

  • HeshamFSSkill

    loop

    Run a command or check on a recurring interval

    Also in 5 projects that use this

  • admin-remixSkill

    workspace

    Google Workspace administration - manage users, groups, email, Drive, calendars, and devices through natural conversation. Triggers on: Google Workspace, G Suite, user management, group management, admin tasks, offboarding, onboarding, email forwarding, Drive permissions, suspended users, organizational units, ChromeOS devices, audit logs, admin reports.

    Also in 3 projects that use this

  • AWSSkill

    map

    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 3 projects that use this

  • +3 more from agno-agi

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 67 edited versions we read keep these.

  • 0

    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
  1. Very specific:

    test flakiness / slowest suites.

    line 17
  2. Very specific:

    Add a row to docs/gymnasium/LEDGER.md (id · title · status: proposed · metric · dates), commit as docs(gymnasium): propose GYM-<NNN> …

    line 35
  3. Very specific:

    Never bundle an unapproved improvement into unrelated work.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 67 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

Gymnasium improvement proposal

Self-improvement is the company's primary standing mission (ADR-0015), and it is governed: improvements are proposed → approved → implemented → measured. This skill produces the proposal; implementation only happens after an explicit Architect verdict.

  1. Gather evidence. Improvement hunts start from records, not vibes:
    • docs/PROGRESS.md + past session reports (recurring blockers, split packages, 3-attempt failures);
    • docs/DECISIONS-LOG.md (clusters of minor decisions = a missing convention);
    • test flakiness / slowest suites; CI failures; /doc-sync drift history;
    • once the system runs: the Agora's log.jsonl, breaker trips, budget burn, memo rejection patterns, org metrics (SDD, Odeon artifacts).
  2. Pick ONE improvement — the highest leverage-to-risk item. Not three. Scope it to ≤ 1 work package.
  3. Write the proposal to docs/gymnasium/proposals/GYM-<NNN>-<slug>.md (next NNN from the directory; create it if missing) using exactly this structure:
    • Evidence — the observed friction, with refs (file, log line, report date).
    • Proposal — the change, concretely (files, mechanism, doc sections affected).
    • Cost & risk — effort, blast radius, what could regress.
    • Success metric — a number or binary check measurable within 2 weeks of landing (e.g. "median package completion needs ≤ 1 session", "zero drift findings in next /doc-sync"). No metric → not a valid proposal.
    • Rollback — how to undo it.
  4. Classify the gate (ADR-0015 authority table): process/docs/tooling improvements → Architect approval; anything touching invariants (BUILD-PROMPT §3), ADRs, gates, secrets, or dependencies → Architect approval AND a decision memo when the system is live. Nothing self-approves.
  5. Add a row to docs/gymnasium/LEDGER.md (id · title · status: proposed · metric · dates), commit as docs(gymnasium): propose GYM-<NNN> <title>, and present the proposal to the Architect ending with the explicit question: approve, amend, or reject?
  6. On a later approval: implement via /build-package discipline, flip the ledger row to landed, and schedule the metric check; when the metric is measured, record the result in the ledger (validated or regressed → rollback per the proposal).

Never bundle an unapproved improvement into unrelated work. Never delete a rejected proposal — mark it rejected with the Architect's reason; rejections teach the next proposal.

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.