Skip to content
FunCoding

agent-md-verify

Use when finishing work in a repository that has agent-md installed; runs the declared checks, updates memory/progress.md, and reports concrete verification evidence instead of self-grading.

Star
968
License
MIT
Last commit
Sep 21, 2026

.agents/skills/agent-md-verify/SKILL.md

View on GitHub

agent-md Verification

Use this skill before claiming work is complete in an agent-md repository.

  1. Read memory/verify.md and identify the checks required for this task.
  2. Run the project verification commands declared in agent-md.toml when present.
  3. If agent-md.toml is absent, use the repository's existing test/lint/typecheck scripts or the hook heuristics.
  4. For source changes, update memory/progress.md with the completed atomic task and the checks that passed.
  5. If no checks exist, say the work is unverified and add a follow-up item to define checks.
  6. Do not describe code as correct based only on inspection. Provide command output, artifact paths, or reviewer evidence.

Useful helper:

./.agent-md/bin/discover_helpers.sh

Similar Skills

subagent-driven-development

OBobra/superpowers298k2,631 new stars in the last 7 days

chief-of-staff

MAmattpocock/skills288k10,178 new stars in the last 7 days

setup-matt-pocock-skills

MAmattpocock/skills288k10,178 new stars in the last 7 days

ask-matt

MAmattpocock/skills288k10,178 new stars in the last 7 days

agent-eval

AFaffaan-m/ECC278k4,046 new stars in the last 7 days

autonomous-agent-harness

AFaffaan-m/ECC278k4,046 new stars in the last 7 days