create-verification-skill
Generate a project-local verify-<app> skill that drives this repo's real app the way a user does.
Skill by kevherro
Chalk Labs
Need help deploying create-verification-skill?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kevherro-create-verification-skill
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/create-verification-skill
What's inside
- Skill name
create-verification-skill- Description
- Generate a project-local verify-<app> skill that drives this repo's real app the way a user does. Use for /create-verification-skill, "make a verify skill for this repo", or when /prove has no scripted way to exercise the product.
- License
- MIT
- Instructions
- 77 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- feature-map.md · references/
- generated-skill.md · references/
- location.md · references/
SKILL.md (first lines)
# Create a verification skill A `verify-<slug>` skill is how later agents prove behavior on **this** app. Write it for a cold agent mid-task. Apply **encode-the-rule**: the skill is the encoding, not a chat note. Do not copy mestack into the generated skill. Point at Launch / Drive in the generated file. ## 1. Locate Follow [references/location.md](references/location.md). If a `verify-*` skill already exists, stop. Offer `/maintain-verification-skill` instead of writing a second one. ## 2. Interview the repo Answer from the checkout. Ask the user only what you cannot observe. - **Surface.** What a user touches: web UI, CLI/TUI, desktop, API, mobile, library. A repo can have several. Pick the primary one and name the rest. - **Run.** How it starts locally. Prefer the repo's own documented command (package scripts, Makefile, README). Ports, env, seed, auth. - **Drive.** How an agent can operate it. Existing harness first. Generic recipe only if none exists. - **Observe.** Screenshots, transcripts, response bodies, logs, exit codes, DB state. - **Isolate.** Can two instances run at once? If not, the generated skill must refuse to hijack the user's session. If the checkout does not build or start, fix that first (or report it precisely). Do not generate steps against a broken base. A library with no runnable surface: stop. Say so. Do not invent a UI. ## 3. Write the skill Create `<repo>/.agents/skills/verify-<slug>/SKILL.md` that satisfies [references/generated-skill.md](references/generated-skill.md). Fill every section from the interview. No template leftovers. If an irrelevant missing asset blocks startup (empty static dir, sample config the API never serves), the skill may create it, marked as verification scaffolding, and remove it in cleanup. ## 4. Seed the feature map Create `features/` next to that SKILL.md, following [references/feature-map.md](references/feature-map.md). Top 3–5 real user-facing features only. ## 5. Run it once Follow the generated skill end to end: launch, doctor, drive **one** mapped feature, capture evidence, clean up. After cleanup, confirm the evidence is still at the named location. Fix failures and rerun cleanup after every failed attempt so ports and processes do not leak. A skill you have not executed is a draft. Do not hand over a draft. If the proof ran on a substitute (a container standing in for a fresh VM, a local stack for a hosted one), name each setup step the substitute supplied for free that the real target will not. Treat those as unproven until something runs on the real target. ## 6. Hand off Tell the user the skill path, which feature you proved, and where the evidence is. Point at `/maintain-verification-skill` for map upkeep. Commit the new skill only if they asked. Creating it does not mean opening a PR.
From kevherro/mestack, MIT.
More from kevherro/mestack
- 0.567score
mestack
kevherro
Kevin's harness-agnostic engineering dispatcher.
SkillAFreshness: AClaude Code +9 - 0.565score
create-formal-verification-skill
kevherro
Write a repo-local formal-<area> skill that machine-checks one high-stakes promise tests rarely exercise, using the verifier that fits the question.
SkillAFreshness: AClaude Code +9 - 0.565score
maintain-formal-verification-skill
kevherro
Re-sync a repo's formal-* checks with code that moved since their last confirmation: read those commits, update the model from the code, rerun, and classify…
SkillAFreshness: AClaude Code +9 - 0.563score
interrogate
kevherro
Adversarial review of a change by one child per configured reviewer.
SkillAFreshness: AClaude Code +9 - 0.561score
ketchup
kevherro
Bring the user current on this chat since they last wrote, plainly, then lay out each pending call of theirs with what they need to make it without clicking…
SkillAFreshness: AClaude Code +9 - 0.561score
benchmark-checklist
kevherro
Vet a performance measurement before you report or act on it: limiter, tuning, physical limits, errors, repeatability, relevance, and whether the work ran.
SkillAFreshness: AClaude Code +9 - 0.561score
principle-attack-the-premise
kevherro
Two fixes on one belief failed the same check; test the belief before a third.
SkillAFreshness: AClaude Code +9 - 0.561score
help
kevherro
Print a table of the current mestack skills and a short description of each.
SkillAFreshness: AClaude Code +9 - 0.561score
correct
kevherro
Turn the mistakes agents repeat in this repo into ones they cannot make, preferring the strongest enforcement that fits.
SkillAFreshness: AClaude Code +9 - 0.556score
in-your-own-words
kevherro
Play back the user's goal and the problem behind it before any work.
SkillAFreshness: AClaude Code +9 - 0.521score
figure-it-out
kevherro
Design and run an auditable playbook when no narrower mestack playbook fits.
SkillBFreshness: BClaude Code +9 - 0.517score
nudge
kevherro
Recurring check-in in this session: ask whether to write a paste-ready team update.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kevherro/mestack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kevherro
- 0.567score
mestack
kevherro
Kevin's harness-agnostic engineering dispatcher.
SkillAFreshness: AClaude Code +9 - 0.565score
maintain-formal-verification-skill
kevherro
Re-sync a repo's formal-* checks with code that moved since their last confirmation: read those commits, update the model from the code, rerun, and classify…
SkillAFreshness: AClaude Code +9 - 0.565score
create-formal-verification-skill
kevherro
Write a repo-local formal-<area> skill that machine-checks one high-stakes promise tests rarely exercise, using the verifier that fits the question.
SkillAFreshness: AClaude Code +9 - 0.563score
interrogate
kevherro
Adversarial review of a change by one child per configured reviewer.
SkillAFreshness: AClaude Code +9 - 0.561score
correct
kevherro
Turn the mistakes agents repeat in this repo into ones they cannot make, preferring the strongest enforcement that fits.
SkillAFreshness: AClaude Code +9 - 0.561score
benchmark-checklist
kevherro
Vet a performance measurement before you report or act on it: limiter, tuning, physical limits, errors, repeatability, relevance, and whether the work ran.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get create-verification-skill running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
create-verification-skill. Agent Mart. https://agentmart.dev/skills/kevherro-create-verification-skill (last updated 2026-10-24)