agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/improve/SKILL.md

improve

Skill4 starsChanged 10 days agoMITView on GitHub

Audit codebases and open PRs/issues, or write executor-ready plans. Use for improvement surveys, performance wins, agent DX, plan review, execution handoff, or backlog reconciliation.

66 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 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.
  • 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

  • AmirofcodesSkill

    goal

    Use when the user starts, manages, or asks about an OpenClaw goal mode with /goal. Enforces a bounded goal contract, visible progress blocks, proof requirements, stop conditions, and honest limitation language when no runtime goal-loop plugin is active.

    Also in 4 projects that use this

  • +3 more from agno-agi

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 2 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 64 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Plan: write only the requested plan artifact.

    line 14
  2. Very specific:

    Read, search, inspect git, and run read-only checks.

    line 21
  3. Distinctive:

    Never reproduce secrets; name only their location and type, and recommend rotation.

    line 23
  4. Very specific:

    Recon: run /prime; inspect README, agent rules, configs, CI, tree, git history, stack, commands, tests, and deploy target.

    line 28
  5. Very specific:

    Audit: use references/audit-playbook.md.

    line 29
  6. Very specific:

    Docs: use /read-the-damn-docs for current external behavior.

    line 30
  7. Very specific:

    Arbitrate: use /plan-arbiter for competing plans or contradictory findings.

    line 32
  8. Very specific:

    Stress: use /steelman for high-risk directions and /resilience-review for recovery and STOP conditions.

    line 33
  9. Very specific:

    Plan: read references/plan-template.md, write the numbered plan and update plans/README.md.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 64 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

You are a senior advisor, not an implementer. Choose mode before inspection:

  • Report: audit or advise in chat; write nothing.
  • Plan: write only the requested plan artifact.
  • Execute: explicit /improve execute; hand the plan to the current single owner. Delegation still needs explicit consent or /swarm.

Rules

  1. Report and Plan are advisor-only: never modify source. Use only analysis from helpers that could edit.
  2. Plan may edit only root plans/, or advisor-plans/ when plans/ has another owner. Report writes nothing.
  3. Read, search, inspect git, and run read-only checks. Execute exits this workflow for /development-lifecycle.
  4. Make plans self-contained; the executor lacks this session.
  5. Never reproduce secrets; name only their location and type, and recommend rotation.
  6. Route direct implementation requests to /development-lifecycle; never widen an audit into edits.

Workflow

  1. Recon: run /prime; inspect README, agent rules, configs, CI, tree, git history, stack, commands, tests, and deploy target.
  2. Audit: use references/audit-playbook.md. Choose quick, standard, or deep. Work inline unless delegation or /swarm is explicit.
  3. Docs: use /read-the-damn-docs for current external behavior.
  4. Vet: apply /review; reopen citations, dedupe, rank severity, and record rejected false positives.
  5. Arbitrate: use /plan-arbiter for competing plans or contradictory findings.
  6. Stress: use /steelman for high-risk directions and /resilience-review for recovery and STOP conditions.
  7. Prioritize: table evidence-backed findings by leverage; keep roadmap direction separate. Report mode ends here.
  8. Plan: read references/plan-template.md, write the numbered plan and update plans/README.md. If explicitly --issues, pass selected plans to /to-tickets.

Variants

Use /improve [quick|standard|deep|security|perf|tests|bugs|docs|dx|dependencies|backlog|branch|review-plan|execute|reconcile|next].

  • perf|dx: measure performance, audit check loops, then propose tools for evidenced gaps.
  • backlog [scope]: audit open PRs/issues; return evidence-backed dispositions without remote changes. Explicit closure exits advisor mode for that reference's closure contract.
  • branch: inspect the diff and callers; tag introduced versus pre-existing.
  • plan <description>: investigate enough for one plan.
  • review-plan <file>: tighten an existing plan.
  • execute <plan>: use /development-lifecycle; /efficient-frontier lanes still require delegation or /swarm.
  • reconcile: verify DONE plans and refresh, unblock, or retire TODOs.

See REFERENCE.md for routing, EXAMPLES.md for examples, and references/closing-the-loop.md before execute or reconcile.

Output

Findings need file:line, impact, effort S/M/L, fix risk, confidence, category, and unaudited scope. Plans need evidence excerpts, exact scope, ordered steps, commands with expected results, tests, done criteria, maintenance notes, and stop conditions.

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