maintain-verification-skill
Use when auditing a real-app verification skill.
- License 许可
- MIT
- 最近更新
- 2026-11-01
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- maintain-verification-skill
- description
- Use when auditing a real-app verification skill.
- compatibility
- Hermes skill_view, file and terminal tools, optional delegate_task, and the verification skill's live app harness.
03 SKILL.md 正文
Maintain a verification skill
A feature map rots the moment the app changes. This skill is the upkeep loop for a skill generated by /skill create-verification-skill (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 terminalising every bullet.
Outcomes
Pick one, and say which:
- clean ; every feature got source and live coverage; nothing 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
Only edit the verification skill's own directory (its SKILL.md, features/, and any harness scripts it owns). Never edit product code during a run: a behavior the map describes that the app no longer does is either doc drift (fix the map) or a product regression (report it, don't paper over it in docs).
Pass
-
Locate the target. Find the verification skill to maintain: the project-local skill whose body has launch/drive sections and a feature map (usually
.hermes/skills/verify-*/in a trusted project, or the chosen profile's installed skills directory). Useskills_listandskill_view(name="verify-<app>")when installed, orsearch_filesandread_fileon the versioned source. Several candidates: ask which one. None: stop and point at/skill create-verification-skillinstead of inventing a target. Pin the canonical source and any installed copy before editing. -
Index hygiene. Read the feature map README and list sibling files with
search_files(target="files"). Useskill_view(name="verify-<app>", file_path="features/<file>.md")for installed references. Fix missing, extra, duplicate, or dead entries. Lightweight; no generated inventory. -
Source wave. One read-only delegate per feature file, submitted through
delegate_task(tasks=[{goal, context}, ...])within runtime concurrency limits. Delegates inherit the parent model; no per-call model, reasoning, or speed controls. Pass the exact source root, feature file, edit prohibition, and return schema in each context. If delegation is unavailable, do the source wave serially and say so. Each explains "how does this user-facing feature work?" from source, flags likely doc drift with citations, and returns one concise live-verification recipe. Children never drive the app and never edit files. Return shape: feature summary / source entry points / likely drift or none / one recipe. -
Reconcile. Every feature file has a returned summary. Merge overlapping recipes into as few app states as practical. Spot-check cited drift; don't 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 source looks clean. The coordinator owns all driving; follow the verification skill's own launch model ; 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 the whole pass, whatever the failure: (1) never drive an instance you haven't health-checked since it last did something surprising ; doctor before first drive, doctor on each fresh session where sessions are the unit, doctor again after any failed drive, and where doctor can't see the failure (a wedged UI state on a healthy process), reset to a known state or relaunch rather than hoping; (2) evidence captured so far survives every cleanup, checked at its named location, not assumed; (3) nothing a drive started outlives that drive's usefulness ; failed-iteration residue is cleaned 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 edit scope and retry once ; restart whatever the fix invalidated, nothing more ; before calling the pass
blocked. A feature that can't be reached isverified-unreachableonly with the concrete prerequisite (auth, entitlement, OS, external state) and the route attempted; if the map omits that prerequisite, that's drift. Any harness fix from triage gets re-driven live before it ships. Final teardown happens after the last drive of the run ; including those re-proofs ; so nothing outlives the run (evidence stays, per the skill). -
Triage. Wrong or missing user-POV description → doc drift, fix it. Working behavior the harness can't drive → harness gap, fix it; a harness fix follows the same helpers rule as generation (scripts executable, invocation documented in the skill body). App behavior that's actually broken → product gap; record it for the user, keep it out of this PR.
-
Ship or stop. For changed: re-read every changed file, synchronize the selected installed copy if one exists, verify discovery in a fresh session, and produce at most one PR of proven corrections when repository publication is authorized. Otherwise report the proven local patch without claiming a PR exists. For clean or blocked: no PR, report the outcome and the coverage honestly. A blocked pass never counts as clean, even when all reachable features passed.
Keep concise run notes (features covered, unreachable prerequisites, confirmed drift, outcome) in a scratch location; don't commit them.
Verification
Keep a coverage row for every feature and every listed entry point: source citation, attempted live path, evidence, and result. Verify the index accounts for every feature file. Include verified-unreachable prerequisites separately rather than counting them as successful journeys. Preserve evidence after final cleanup and rerun every corrected harness path before shipping.
04 同仓库更多 Skills
using-omi-api
Use when a user wants to read, search, summarize, create, update, delete, import, or automate Omi memories, conversations, transcripts, action items, folders, goals, notifications, OAuth, webhooks, MCP, or omi-cli. Not for Omi device pairing or hardware setup.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
unslop
Cut AI tells from any writing.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
teach
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.