agentleFS
7xuanlu7xuanlu/wenlan/.claude/skills/prove/SKILL.md

prove

Skill358 starsChanged 4 months agoApache-2.0View on GitHub

Per-surface verification loops for wenlan — daemon, cli, mcp, plugin, suite strength (mutation), behavior trace, weekly sweep. Routes to scripts; every check records evidence via attest. Deeper than the built-in verify skill — use prove for mutation audits, behavior tracing, and the weekly sweep; built-in /verify handles generic runtime observation.

13 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

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

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    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:

    Run every check through the evidence wrapper (records to .claude/attest.jsonl, which the weekly sweep audits): bash scripts/attest.sh …

    line 8
  2. Distinctive:

    No argument → pick the surfaces the current diff touches (server/core → daemon.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 12 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

/prove [surface] — wenlan verification loops

Run every check through the evidence wrapper (records to .claude/attest.jsonl, which the weekly sweep audits): bash scripts/attest.sh <command>. That wrapper ships in the repo and runs on macOS, Linux and Windows (Git Bash); the older ~/.claude/bin/attest.sh is a personal copy that does not exist on every machine, and a missing wrapper means the run is unrecorded, which the sweep reads as "the smoke never ran". Sandboxed local runs need TMPDIR=/tmp/claude prefixed (macOS mktemp gotcha).

SurfaceCommandProves
daemonread references/daemon.mdHTTP behavior on an isolated daemon
cliattest.sh bash scripts/smoke-cli.shshipped CLI black-box round-trip
mcpattest.sh bash scripts/smoke-mcp.shstdio JSON-RPC round-trip
plugin/wenlan setup verify pathplugin → MCP → daemon wiring
suitebreadth: cargo mutants -f <file> (auto-generated mutants, lib-test oracle); depth: read references/mutprove.mdtests can actually go red (mutation audit)
behaviorsattest.sh python3 scripts/check-behavior-trace.py <plan.md> <tests...>tests trace to intent, both directions
sweepread references/sweep.mdweekly verify-the-verifier

No argument → pick the surfaces the current diff touches (server/core → daemon; cli crate → cli; mcp crate → mcp; new/changed tests → behaviors + suite). App/UI surface (app/, src/, or anything rendered): rendered evidence required — drive the running app and look at the screen; unit/build green is not proof of visible correctness.

Live-smoke legs that need the real GPU model (L7) stay manual: scripts/live-smoke-*.sh — run before merging features whose e2e stubs the LLM.

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.