verify-brigade
From the author
Prove a Brigade change works by driving the real `brigade` CLI against a throwaway temp target, then capture receipts as evidence. Use when you changed anything under src/brigade/ and need proof beyond pytest - init/doctor wiring, work-verify receipts, Grok Bot connector packs, feed manifests, handoff lint. Also use before claiming a CLI behavior in a PR body, handoff, or job report.
Install
npx skills add escoffier-labs/brigade --skill verify-brigade -a claude-code
Installs to .claude/skills/verify-brigade/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 77
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- brigade-workescoffier-labs/brigadeUse at the start of any work session and whenever you verify a change in a Brigade-wired repo or workspace - routes work through Brigade so verification, outcomes, evidence export, and handoffs are captured (verify with capture → outcome from run → evidence brief next time) instead of leaving Brigade installed-but-dormant. Triggers on starting a task, running tests/checks, or finishing a session.Testing★ 81
- verify-cli-runreticlehq/reticleProve that a command-line tool actually did what it said, instead of trusting its exit code and its output. Snapshots the filesystem before and after, names the expected consequence in advance, and returns one of four verdicts with what could not be seen. Use after running a build, a migration, a scaffolder, a formatter, a codegen step, or an AI coding CLI; when a command printed success and you are about to report "done"; when you are about to write "exit code 0, so it worked"; or when a tool claims it edited files. Needs nothing installed.Engineering★ 1.3K
- verifycodeaholicguy/ai-devkitAI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when completing any task, fixing a bug, finishing a phase, running tests, building, deploying, or making any "it works" claim.Testing★ 1.7K
- enforceescoffier-labs/brigadeUse when the user asks to turn on Brigade's full work loop (verification capture, raw-check blocking, and the handoff-before-stop gate) in the current repository.Other★ 81
- evidence-driven-testingmichaelshimeles/skillsRecords visual proof while testing UI behavior — the agent tests the app hands-on via computer use while a screen recording with structured test/assertion annotations captures the session — then posts the video and a results summary to the requested destination. Use when changed runtime behavior needs observable verification, including headless environments (scripted screenshots and probes) and non-UI changes (measured numbers, output pairs).Testing★ 1.4K
- verificationhashgraph-online/awesome-codex-pluginsVerification command resolution and evidence rule for skills that run a project's tests or build before calling work done. Resolves the test and build command from project instructions, then from the stack, then to none; defines what a pass, fail, or skipped claim must quote.Testing★ 1.4K
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in