Communitygithub.com

verify-skillsmith

Prove the skillsmith repo works end to end. Validates the skills and plugin manifest, installs the plugin into a throwaway Claude Code config from the working tree, checks what the npx skills CLI discovers, and tests the skill-audit script on a known-bad fixture. Use before pushing or tagging a release, after adding or editing any skill, or when a skill is missing from an install route.

verify-skillsmith 是什麼?

verify-skillsmith is a Claude Code agent skill that prove the skillsmith repo works end to end. Validates the skills and plugin manifest, installs the plugin into a throwaway Claude Code config from the working tree, checks what the npx skills CLI discovers, and tests the skill-audit script on a known-bad fixture. Use before pushing or tagging a release, after adding or editing any skill, or when a skill is missing from an install route.

相容平台✓Claude Code✓Codex CLI✓Cursor
npx skills add https://github.com/Atou4/skillsmith/tree/main/.agents/skills/verify-skillsmith

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Verify skillsmith

skillsmith is a library of agent skills with no server. Its "app" is the install paths users run: the Claude Code plugin and the npx skills CLI, plus three scripts. A change is verified when both install routes see exactly the skills the repo defines, and the checks are green.

This skill is agent-neutral. The one real copy lives in .agents/skills/verify-skillsmith/ (read by Codex); .claude/skills/verify-skillsmith (Claude Code) and .cursor/skills/verify-skillsmith (Cursor) are symlinks to it. Edit the real copy only. Everything runs from the repo root. The helper does the work; the feature map in features/ says what each check proves.

Launch

There is no process to keep alive. "Launch" means create an isolated Claude Code config and install into it:

.agents/skills/verify-skillsmith/scripts/verify.sh install

Ready when it prints PASS: install: version <x>, <n> skills registered from the working tree. The helper sets CLAUDE_CONFIG_DIR to a throwaway directory for every subcommand and refuses to run against ~/.claude. Never run claude plugin install for this repo without it: that would install into the user's real setup.

The plugin is copied into the isolated cache at install time. After editing a skill, run a fresh install (a new RUN_ID gives a new isolated config) rather than expecting the old install to update.

Doctor

Read-only. Run it first, and again whenever a result looks wrong:

.agents/skills/verify-skillsmith/scripts/verify.sh doctor

It reports the repo path, claude, python3, uv and npx availability, the plugin.json version, the skill names found under skills/, and how many files are uncommitted. It fails if claude or npx is missing. If the git dirty count is not what you expect, stop and find out why before trusting a result: the install route reads the working tree, not the last commit.

Drive

One command runs everything, and each step has its own subcommand:

StepCommandWhat it asserts
Staticverify.sh staticscripts/validate-skills.py prints OK: (with PyYAML, so invalid YAML frontmatter fails), and claude plugin validate . prints Validation passed.
Plugin installverify.sh installInstall succeeds from the local path, the installed version equals plugin.json, "Read from" is this repo, and the registered skills equal the folders under skills/.
CLI discoveryverify.sh discovernpx skills add <repo> --list lists exactly the repo's skills, and no skill folder or lock file changed.
Audit fixtureverify.sh audit-fixtureskill-audit's script finds the broken symlink, name mismatch and missing SKILL.md in a fixture built for the purpose.
Everythingverify.sh allAll of the above, then cleanup. Prints ALL PASSED. Evidence: <dir>.

Prefer all. Use single steps to localize a failure. Set RUN_ID=<name> to keep a run's files together across steps.

The two install routes can disagree, and that is the point of checking both: Claude's plugin loader tolerates frontmatter that the skills CLI rejects (an unquoted : in a description is invalid YAML, and the CLI silently skips that skill).

Evidence

Everything lands in .agents/skills/verify-skillsmith/artifacts/<RUN_ID>/ (git-ignored):

  • summary.txt: one PASS: line per step. A missing line means the step did not pass.
  • doctor.txt, validate-skills.txt, plugin-validate.txt: static results.
  • install.txt: the add, install, list and details output, including version and "Read from".
  • skills-list.txt: the skill names the CLI discovered; skills-list-raw.txt is the raw output.
  • audit-fixture.txt: the audit report for the fixture.
  • failures.txt: only exists if something failed.

Proof standards for this repo:

  • Exercise the real routes (claude plugin install, npx skills add --list), not the validator alone. The validator passed while one skill was invisible to the CLI.
  • Compare sets, not counts: installed names against folders under skills/.
  • npx skills add --list is read-only. This was observed, not assumed: skill folder counts under ~/.claude/skills, ~/.codex/skills, ~/.agents/skills and the lock file's modification time were identical before and after. The helper re-checks this each run. Never run npx skills add without --list as part of verification: it installs into the user's machine.
  • Do not run npx skills update or update --help: it performs a real update.
  • Report a skipped step with the command you ran and why it could not run. Do not count a step as verified through a different path.

Cleanup

.agents/skills/verify-skillsmith/scripts/verify.sh clean   # with the same RUN_ID

It removes the isolated marketplace and config and deletes the throwaway directory. all runs it automatically on exit. It never deletes artifacts/. Do not kill processes by name; this verification starts none that outlive a command.

Helpers

  • scripts/verify.sh <doctor|static|install|discover|audit-fixture|clean|all>: described above. Executable; requires claude, npx and python3; uses uv for PyYAML when present.

Feature map

Read features/README.md, then the feature file that matches what changed. Each lists the entry points, the exact commands and the end state that proves it.

Individual skills in this repo

This repo contains 1 individual skill — each has its own dedicated page.

相關技能