checkup skill
✓ VerifiedPerforms periodic audits of verification skills and feature maps to identify documentation drift and product regressions.
- GitHub stars
- 113
- Files
- 1
- Last commit
- Nov 1, 2026
- License
- MIT
- Allowed tools
- —
What does the checkup skill do?
checkup performs periodic audits of verification skills and feature maps to identify documentation drift and product regressions.
Summary generated from the skill's SKILL.md.
About the checkup skill
Maintaining the accuracy of verification skills and feature maps is the primary function of this tool. It is designed for developers who need to identify documentation drift or product regressions within project-local verification skills, such as those generated by vital-signs. By auditing feature files against actual source code and live application behavior, it ensures that the feature map remains an honest representation of the software.
An agent should load this skill when tasked with maintaining a verification skill or auditing a feature map. The process involves using the team-avatar:toph tool to perform read-only source analysis for every feature, followed by a live driving pass to exercise the application. The skill produces one of three outcomes: a clean report, a single pull request containing proven corrections via yip-yip, or a blocked status if coverage cannot be completed. It operates strictly within the verification skill's own directory, focusing on its SKILL.md, features folder, and harness scripts without modifying product code.
What an agent can do with it
- 1Audit feature map accuracyCheck if the current feature map still correctly describes the application's behavior.
- 2Identify documentation driftFind discrepancies between the source code and the verification skill's documentation.
- 3Detect product regressionsDetermine if actual application behavior has broken compared to the documented feature map.
- 4Maintain verification skillsPerform a periodic upkeep loop to ensure a verification skill remains reliable.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the checkup skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the checkup skill in Plugin
/plugin marketplace add tmcfarlane/team-avatar /plugin install team-avatar@team-avatar
Install the checkup skill in Claude Code
~/.claude/skills/checkup/SKILL.md
$ npx degit tmcfarlane/team-avatar/plugins/team-avatar/skills/checkup ~/.claude/skills/checkupInstall the checkup skill in Claude Code (project)
.claude/skills/checkup/SKILL.md
$ npx degit tmcfarlane/team-avatar/plugins/team-avatar/skills/checkup .claude/skills/checkupInstall the checkup skill in Codex
~/.agents/skills/checkup/SKILL.md
$ npx degit tmcfarlane/team-avatar/plugins/team-avatar/skills/checkup ~/.agents/skills/checkupInstall the checkup skill in Gemini CLI
~/.gemini/skills/checkup/SKILL.md
$ npx degit tmcfarlane/team-avatar/plugins/team-avatar/skills/checkup ~/.gemini/skills/checkupInstall the checkup skill in Claude.ai
npx degit tmcfarlane/team-avatar/plugins/team-avatar/skills/checkup checkup && zip -r checkup.zip checkup # claude.ai → Customize → Skills → + → Create skill → Upload a skill → checkup.zip
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachabletmcfarlane/team-avatar/plugins/team-avatar/skills/checkup is public and reachablegithub.com/tmcfarlane/team-avatar/tree/HEAD/plugins/team-ava ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-01github.com/tmcfarlane/team-avatar/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/tmcfarlane/team-avatar/blob/HEAD/plugins/team-ava ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/tmcfarlane/team-avatar/blob/HEAD/plugins/team-ava ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 42 linesgithub.com/tmcfarlane/team-avatar/blob/HEAD/plugins/team-ava ↗Pass
SKILL.md
View on GitHubKatara's checkup
A healer does not check a patient once and call them well forever. Bodies change. So do apps. The feature map in a verify skill starts to rot the moment the app changes, and a checkup finds the drift before it misleads the next agent.
On Codex, read avatar-mode/references/codex.md for tool equivalents.
This is the upkeep loop for a skill generated by vital-signs, or any project-local verification skill with a feature map. The unit of rigor is the feature, not every sentence. Cover every feature file from source and exercise every feature live, without turning every bullet into a terminal command.
Outcomes
Pick one, and say which.
- clean. Every feature got source and live coverage, and nothing is worth shipping. No branch, no PR.
- changed. One PR ships proven doc, harness, or map corrections.
- blocked. Coverage could not finish, or a proven fix could not ship safely. Say exactly what blocked it.
Edit scope
Edit only the verification skill's own directory: its SKILL.md, features/, and any harness scripts it owns. Never edit product code during a run. When the map describes a behavior the app no longer has, that is either doc drift (fix the map) or a product regression (report it, and do not paper over it in the docs).
Pass
-
Locate the target. Find the verification skill to maintain. It is the project-local skill whose body has launch and drive sections and a feature map (
.claude/skills/verify/or.agents/skills/verify/, or averify-*sibling from an older generator). With several candidates, ask which one. With none, stop and point atvital-signsinstead of inventing a target. -
Index hygiene. Read the feature map README and list its sibling files. Fix missing, extra, duplicate, or dead entries. Keep this light, with no generated inventory.
-
Source wave. Dispatch one read-only
team-avatar:tophper feature file, all at once, on Toph's model from the avatar-setup sheet. Each explains "how does this user-facing feature work?" from source withseismic-sense, flags likely doc drift with citations, and returns one concise live-verification recipe. These readers never drive the app and never edit files. Their return shape is a feature summary, the source entry points, likely drift or none, and one recipe. When you are already a subagent and cannot dispatch, read each feature yourself, one after another. -
Reconcile. Confirm every feature file has a returned summary. Merge overlapping recipes into as few app states as practical. Spot-check the cited drift, and do not re-prove clean claims. Sweep recent churn for user-facing surfaces missing from the map. Require a concrete source path before calling one missing.
-
Live pass. Required even when the source looks clean. The coordinator owns all driving. Follow the verification skill's own launch model. That is one long-lived instance driven serially for servers and UIs, or a fresh isolated session per drive for short-lived CLIs. The skill's Launch section decides, not this one. Exercise every feature at least once, and hold three invariants for the whole pass, whatever fails.
- Never drive an instance you have not health-checked since it last did something surprising. Run doctor before the first drive, on each fresh session where sessions are the unit, and again after any failed drive. Where doctor cannot see the failure (a wedged UI state on a healthy process), reset to a known state or relaunch rather than hoping.
- Evidence captured so far survives every cleanup. Check it at its named location. Do not assume it.
- Nothing a drive started outlives that drive's usefulness. Clean failed-iteration residue whether the session is stuck, exited, or shared. For a shared instance, clean the residue, not the instance.
A doctor failure caused by skill drift is drift. Fix it under the edit scope and retry once, restarting only what the fix invalidated, before you call the pass
blocked. A feature that cannot be reached isverified-unreachableonly with the concrete prerequisite (auth, entitlement, OS, external state) and the route you attempted. If the map omits that prerequisite, that is drift. Re-drive any harness fix from triage live before it ships. Final teardown happens after the last drive of the run, re-proofs included, so nothing outlives the run. Evidence stays, per the skill. -
Triage. A wrong or missing user-POV description is doc drift. Fix it. Working behavior the harness cannot drive is a harness gap. Fix it, and follow the same helpers rule as
vital-signs(scripts executable, invocation shown in the skill body). App behavior that is actually broken is a product gap. Record it for the user and keep it out of this PR. -
Ship or stop. For
changed, open one PR of proven corrections withyip-yip, after you re-read every changed file. Forcleanorblocked, open no PR. Report the outcome and the coverage honestly.
Keep concise run notes (features covered, unreachable prerequisites, confirmed drift, outcome) in a scratch location. Do not commit them.
Files in this skill
1checkup skill questions
How do I install the checkup skill in Claude Code?
Run npx degit tmcfarlane/team-avatar/plugins/team-avatar/skills/checkup ~/.claude/skills/checkup. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the checkup skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What is the allowed edit scope for this skill?
You should only edit the verification skill's own directory, including its SKILL.md, features/, and harness scripts, and never edit the product code itself.
How should I handle a product regression found during a checkup?
If the app behavior is actually broken, record it for the user and keep it out of the current PR.