create-verification-skill
Skill2 starsChanged 29 days agoApache-2.0View on GitHub
Write a verification skill for a repository: how to start it in isolation, drive what a user really does, keep evidence that survives cleanup, and map its main features, proven by running it once.
93 other projects use a version of this.
Adopted by
Most recently taken up by
- TencentBlueKing/bk-litetheir own version, first seen Nov 16, 2026
- kimkon1011/orgiast-claude-rulestheir own version, first seen Nov 16, 2026
- clnnn/playbooktheir own version, first seen Nov 16, 2026
- Schramm2/spyglasstheir own version, first seen Nov 16, 2026
- gfunc/skillstheir own version, first seen Nov 16, 2026
- magnusrodseth/dotfilestheir own version, first seen Nov 16, 2026
Used with
Projects with it also use setup-pstack, principle-explain-the-number and 9 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 31 projects that use this
shiwenbin1617Skillprinciple-explain-the-number
Apply before you measure, and 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 35 projects that use this
shiwenbin1617Skillpoteto-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 17 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 32 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 22 projects that use this
instructureSkillketchup
Rebuild context after /clear by analyzing uncommitted changes across Canvas LMS and all plugin repositories
Also in 28 projects that use this
- +3 more from shiwenbin1617
Other versions93 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 93
- paperclipai/paperclip★ 114ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- milind-soni/OpenMausBot★ 23ksame name
- tester-army/e2e★ 14ksame name
- backnotprop/pstack★ 4.2ksame name
- epam/ketcher★ 939same name
- deadlock-mod-manager/deadlock-mod-manager★ 617same name
- openwong2kim/wmux★ 455same name
- jtaroreh/agystack★ 128same name
83 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 repository43 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- architectSkill
- benchmark-checklistSkill
- correct-recurring-errorsSkill
- create-verification-skillSkill
- independent-reviewSkill
- maintain-verification-skillSkill
- monitor-and-shipSkill
- orchestrate-cloud-workSkill
- setup-laterdogSkill
- verify-laterdogSkill
- architectSkill
- benchmark-checklistSkill
- correct-recurring-errorsSkill
- create-verification-skillSkill
- independent-reviewSkill
- maintain-verification-skillSkill
- monitor-and-shipSkill
- orchestrate-cloud-workSkill
- setup-laterdogSkill
- verify-appSkill
- verify-laterdogSkill
- architectSkill
- benchmark-checklistSkill
- correct-recurring-errorsSkill
- independent-reviewSkill
- maintain-verification-skillSkill
- monitor-and-shipSkill
- orchestrate-cloud-workSkill
- setup-laterdogSkill
- verify-laterdogSkill
- architectSkill
- benchmark-checklistSkill
- correct-recurring-errorsSkill
- create-verification-skillSkill
- independent-reviewSkill
- maintain-verification-skillSkill
- monitor-and-shipSkill
- orchestrate-cloud-workSkill
- setup-laterdogSkill
- verify-laterdogSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 80 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Use the harness that exists: If it is broken, fix it first in a draft PR.
“Common” is measured: kept by at least 6 in 10 of the 80 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
Create verification skill
Use when a repository gives agents no dependable way to show that a change works, or when asked for a verification skill. later.dog's own setup is the model: docs/verification/README.md with scripts/control-laterdog.ts, and the verify-laterdog skill with its feature map. Use the later.dog MCP server. Tool prefixes depend on the client; discover tools by their names below.
Procedure
- Find out how the app really runs, from its code and docs: how people reach it (screens, CLI, API), the start command and the signal that it is ready, any test harness or control CLI already there, stable handles (accessible names, routes, commands, test IDs), the side effects worth checking, and how to keep a run's data separate (temporary directory, fake provider, its own port).
- Use the harness that exists. If it is broken, fix it first in a draft PR; instructions written around a broken harness teach the wrong steps. If there is none, say so and propose the smallest script that would do. Never invent commands or selectors.
- Write
verify-<app>/SKILL.mdwhere the repository's agents look for skills: in a repository laid out like later.dog, the canonical folder and then its export command; otherwise.agents/skills/. Give it anameand adescription, then:- Start: the exact command, isolated data and the ready signal.
- Check: one read-only health check whose failure says what to do next.
- Drive: commands and stable handles taken from the code, never screen coordinates.
- Evidence: the action, the state it produced and any side effect, kept outside anything cleanup deletes.
- Stop: end only what this run started, and leave the evidence.
- Map the features:
features/README.mdand one page per important feature, saying where a person meets it, how to drive it, what proves it worked and what that proof leaves open. - Run it once, end to end, on one mapped feature: start, check, drive, keep evidence, stop, then confirm the evidence is still there. A skill nobody has run is not finished. Fake only services outside the repository and say which results came from a fake: fixture success does not qualify a live provider.
- Feed cloud verification. From the map, pick the CI checks and isolated commands that really exercise behaviour; they become the repository's recipe through
configure_verification_recipe. That tool needs the admin connection, so a dog asks its person to enter the checks in Cloud jobs → Connect repository. - Leave upkeep to the
maintain-verification-skillskill.
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.

