maintain-verification-skill
Skill5 starsChanged 28 days agoMITView on GitHub
Audit Lahe's verification skill and feature map against current source and real browser journeys; repair documentation or harness drift and report product regressions. Use for a maintenance automation or a requested verification-map refresh.
77 other projects use a version of this.
Adopted by
Most recently taken up by
- magnusrodseth/dotfilestheir own version, first seen Nov 16, 2026
- shiwenbin1617/pstacktheir own version, first seen Nov 16, 2026
- backnotprop/pstacktheir own version, first seen Nov 15, 2026
- morochena/skillstheir own version, first seen Nov 15, 2026
- sammyjoyce/prime-pstacktheir own version, first seen Nov 15, 2026
- pronvis/skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use setup-pstack, ketchup-video and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
bnemaSkillsetup-pstack
Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.
Also in 25 projects that use this
tristanphvnSkillketchup-video
Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.
Also in 13 projects that use this
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 14 projects that use this
eryzerzSkillmake-bot-ui
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Also in 19 projects that use this
ianclearySkillprinciple-explain-the-number
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Also in 27 projects that use this
drafaelSkillin-your-own-words
Restate the user's goals and the problem they are trying to solve to check understanding. Manual invocation only; use when the user explicitly invokes in-your-own-words or requests this understanding check. Do not solve the task or rewrite the assistant's last answer.
Also in 26 projects that use this
Other versions77 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 77
- paperclipai/paperclip★ 114ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- backnotprop/pstack★ 4.2ksame name
- epam/ketcher★ 932same name
- deadlock-mod-manager/deadlock-mod-manager★ 584same name
- openwong2kim/wmux★ 455same name
- jtaroreh/agystack★ 128same name
- uzairansaruzi/p3-stack★ 126same name
- Dimon94/dverity★ 107same name
67 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- laheSkill
- verify-laheSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 77 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Keep edits within skills/verify-lahe/.
- Distinctive: line 28
Check that the feature index and sibling files agree and their links resolve.
- Distinctive: line 29
Read the source anchors, relevant specs and recent changes for each feature.
- Distinctive: line 32
Use read-only source readers in parallel when useful, with one owner per feature.
- Distinctive: line 38
Use the existing fixture lifecycle: fresh isolated worlds per test, serial browser commands, no shared human helper.
- Distinctive: line 44
Follow verify-lahe's Launch, Doctor, Drive, Evidence and Cleanup instructions.
- Distinctive: line 48
Check artifacts survive cleanup.
- Distinctive: line 62
Keep run notes and artifacts outside committed source.
“Common” is measured: kept by at least 6 in 10 of the 77 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Maintain Lahe verification
Target verify-lahe and its feature map. This is a repo-specific adaptation of Lauren Tan's pstack maintenance skill. It does not schedule an automation by itself.
Outcome and boundaries
Report clean only when every mapped feature and listed entry point has source and live coverage. Report changed when proven corrections are ready to ship, and blocked when coverage or safe shipping cannot finish. Name unrun paths and prerequisites. A green seed alone cannot produce clean.
Keep edits within skills/verify-lahe/. Do not change product code or weaken
a journey to make a product regression look like documentation drift. Report
product gaps with source and failing evidence for the project's board; leave
product fixes to a separate task. Preserve the repo's PR and gate policy.
Read and reconcile
Check that the feature index and sibling files agree and their links resolve. Read the source anchors, relevant specs and recent changes for each feature. Explain the current user path and identify concrete drift. Check recent user surfaces for missing map entries; require a source path before adding one. Use read-only source readers in parallel when useful, with one owner per feature. Give them only that feature, its source anchors and the output contract: summary, source citations, drift or none, and a live recipe. Readers do not drive the app, edit files or run removal commands.
The coordinator combines overlapping recipes and owns all browser driving. Use the existing fixture lifecycle: fresh isolated worlds per test, serial browser commands, no shared human helper. Reuse evidence for overlapping paths only when it covers the same code and actions.
Prove and triage
Follow verify-lahe's Launch, Doctor, Drive, Evidence and Cleanup instructions. Exercise every feature and its listed entry points. After an unexpected result, doctor the instance and reset a wedged page by ending its owned world before restarting. Keep failed evidence. Stop owned processes even when a drive fails. Check artifacts survive cleanup.
- Wrong instructions with working product behavior: fix the map and re-drive.
- Working behavior the harness cannot drive: fix a skill-owned helper if there is one and re-drive. A change outside the edit scope is a separate task.
- Broken product behavior: report it with evidence; do not rename it expected.
- Missing OS, auth or host: report the prerequisite and attempted route. Do not count that route as passed. Fix an omitted prerequisite in the map.
Retry a doctor failure caused by a corrected skill instruction once. If the environment remains unavailable, report blocked rather than looping.
Handoff
Keep run notes and artifacts outside committed source. Record the source SHA, dirty diff, command, each feature's result, entry points exercised, failures, prerequisites and artifact paths. Read the final diff before shipping. Produce a focused PR only for proven corrections and only after the repo's required checks; clean and blocked passes need no PR. Do not merge automatically or claim board items as part of this maintenance pass.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

