agentleFS
everrunseverruns/yolop/.agents/skills/maintenance/SKILL.md

maintenance

Skill18 starsChanged 13 days agoMITView on GitHub

Goal-oriented repository maintenance and release-readiness work for yolop. Use when the user asks for maintenance, release prep, repo health review, dependency refreshes, knowledge/docs alignment, test gap review, or general cleanup without prescribing an exact sequence.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use recall.

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.
  • termdockSkill

    recall

    Retrieves cross-session memories about past decisions, lessons, and patterns. Use when user asks about prior work, past decisions, or mentions a feature. Triggers include check memory, what did we decide, how did we solve.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 4

    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. Distinctive:

    Use the scope the user gave.

    line 21
  2. Distinctive:

    Prefer fixing over reporting, and keep findings in the pass.

    line 38
  3. Distinctive:

    Keep each change PR-sized and independently reviewable.

    line 48
  4. Distinctive:

    blocked: if main CI is red and out of reach

    line 69
  5. Very specific:

    If the user asks to ship the result, hand off to /ship.

    line 71

“Common” is measured: kept by at least 6 in 10 of the 13 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

Maintenance

Goal: leave the repo materially healthier and closer to release-ready, with evidence.

knowledge/specs/maintenance.md owns the success bar and the rationale behind each surface. This skill owns how to work a pass. surfaces.md holds the per-surface commands and heuristics, open it for the surfaces your scope actually covers.

Scope

Use the scope the user gave; otherwise state the one you inferred before starting. Typical scopes: release readiness, CI health on main, everruns-* and tuika refresh including deep major upgrades, YEP wire compat, local inference matrix, binary size, knowledge or docs drift, knowledge versus code conflicts, feature-completeness drift across CLI, TUI, inline, print, ACP, skills, README, and tests, eval gaps, test review across coverage, obviousness, duplication, cost, and nonsense, architecture, soundness, and simplification, security reviews, README soundness, performance of recently changed code, AGENTS, skills, and command hygiene.

Working a pass

A red CI on main outranks every other scope. Fix it first, or open an issue and report the pass blocked. Otherwise go highest-signal first: recent diffs, failing checks, stale knowledge, outdated everruns-* or tuika versions.

Prefer fixing over reporting, and keep findings in the pass. Fix what is small and local; for anything larger, write a crisp finding and defer it to a GitHub issue naming the problem and its user-visible impact, then put the issue number in the report. A large diff, a long build, a missing audit, or an unfamiliar failure is work to finish, not a reason to defer. Never weaken a test, a security limit, or a supply chain criterion to ship an upgrade. If the newest upstream version cannot preserve a required contract, establish the incompatibility, retain the newest safe version with a tested and documented pin, and complete the rest of the pass.

Keep each change PR-sized and independently reviewable. Do not fold a simplification sweep into an unrelated fix. When a bug surfaces, prefer the failing test before the fix. Review touched tests on the merits: coverage of the behavior, whether the test can fail for a real reason, duplication, and cost in speed and flakiness. Skipping a surface is fine; skipping it silently is not.

Validation matches the surfaces you touched: the checks in AGENTS.md, plus a live-provider smoke through Doppler when the pass touched runtime behavior. Use isolated target directories for local-inference and cuda work so the routine target/ stays clean. Do not declare release-ready for surfaces you did not actually check.

Report

  • scope covered, and what was intentionally skipped with a reason
  • what was fixed, and what was found
  • evidence gathered: commands run, versions moved, sizes measured, tests and smoke results
  • deferred findings with their GitHub issue numbers
  • blocked if main CI is red and out of reach

If the user asks to ship the result, hand off to /ship.

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.