SkillRepo
Sign InSign Up
Catalog
Yeachan-Heo/create-verification-skill

Yeachan-Heo

create-verification-skill

Generate the project's own verify skill: build/test/lint commands discovered by running them, a feature map of what each covers, manual checks, and an earned first verdict. Run once per repo.

v1.0LATEST
NewUpdated Nov 8, 2026

Create Verification Skill

The bundled verify skill demands evidence but cannot know this repo's commands. This skill generates the project-local verify skill that makes verification concrete — by discovering the commands through execution, not by guessing from a README.

When to use

  • a repo has no .claude/skills/verify/ and work will be verified here more than once
  • the generic verification flow keeps guessing commands wrong for this repo

Workflow

  1. Discover by running. For each candidate surface — build, test, lint, typecheck, format, dev server, e2e — find the command (package scripts, Makefile, CI config) and run it. Record the real invocation, the expected passing output shape, the runtime, and the known gotchas (env vars, seed data, order dependence). A command you have not run is a hypothesis, not a check. Write-mode formatters (prettier --write, eslint --fix) mutate tracked files — record the read-only check form (prettier --check, eslint --check) as the verification command, never the mutating one.
  2. Record the manual surface. What cannot be checked by command here: the pages or flows a human (or run/visual-verdict) exercises, and what "looks right" means for each.
  3. Write the feature map. A table of what each check actually covers — which entry points, which layers, what it cannot see. The map is the skill's honesty: verification strength is knowable, not assumed.
  4. Generate .claude/skills/verify/SKILL.md containing: the exact commands with expected outcomes, the manual checks, the feature map, and the escalation path (which failure means what, who owns it). Keep it short enough that a fresh session reads it whole. If a verify skill already exists at the canonical root (.omc/skills/verify/SKILL.md or .claude/skills/verify/SKILL.md), respect it: update its commands and feature map in place rather than overwriting, and say what changed.
  5. Prove it. Run the generated skill's own flow once end to end on a real change and record the result through the ledger's locked writer — appendLedgerEntry and defaultLedgerPath from the installed package's dist/features/verification-ledger/index.js (babysit's ledger step demonstrates the exact invocation); never append raw rows to .omc/state/verification-ledger.tsv — the writer owns header creation, locking, and cell sanitization. The verdict is the one the flow actually earned: a real UI exercised is live-ui-verified, a test suite run is unit-test-verified, only build/lint/typecheck passed is type-check-only, and nothing runnable is no positive row at all.

Rules

  • Every command in the generated skill was executed this session, or is marked unverified with the reason.
  • The generated skill verifies; it never fixes. Fixes route to execute.
  • When the repo's commands change shape, maintain-verification-skill re-syncs this artifact.
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

76/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

78

Quality

74

Clarity

79

Completeness

70

Summary

This skill guides an agent to discover and document a project's build, test, lint, and verification commands by executing them in the current session, then generates a `.claude/skills/verify/SKILL.md` file that captures exact command invocations, expected outputs, feature coverage, and manual verification steps. It emphasizes evidence-based verification: commands must be executed—not guessed—and recorded with their runtime characteristics, dependencies, and known gotchas.

Detected Capabilities

command executionfile writeenvironment variable readingfile readingledger writing via package API

Trigger Keywords

Phrases that agents use to match this skill to user intent.

generate verify skilldocument verification commandsdiscover build commandscreate test coverage mapfeature coverage verification

Risk Signals

INFO

Commands executed during discovery (build, test, lint, typecheck, dev server, e2e) may have side effects or environmental dependencies

Workflow step 1
INFO

Generated skill writes to `.claude/skills/verify/SKILL.md` and `.omc/skills/verify/SKILL.md` — these are project directories, expected behavior for this skill's purpose

Workflow step 4
WARNING

Uses external package API (`babysit` ledger writer) without documenting fallback behavior if package is unavailable

Workflow step 5
INFO

Distinguishes between mutating and read-only forms of commands (e.g., `prettier --write` vs `prettier --check`); mutation must not be recorded in verify skill, only read-only forms

Workflow step 1

Referenced Domains

External domains referenced in skill content, detected by static analysis.

github.com

Use Cases

  • Generate a project-specific verify skill from discovered build and test commands
  • Document feature coverage and limitations of existing verification commands in a repo
  • Transition from generic verification to repository-aware verification with exact commands and expected outputs
  • Capture manual verification steps (UI flows, visual checks) alongside automated checks in a structured skill
  • Maintain and update an existing verify skill when project commands change shape or scope

Quality Notes

  • Strength: Workflow is pragmatic and evidence-based—commands are executed, not guessed from README or package.json; this is stronger than generic verification skills
  • Strength: Step 2 (manual surface) acknowledges limits of automation and captures human verification; this is mature
  • Strength: Feature map (step 3) is explicit and honest about what each check covers and cannot see—this supports sound judgment about verification strength
  • Strength: Clear rules (write-only vs read-only commands) prevent skill from mutating tracked files during verification
  • Opportunity: No explicit guidance on handling commands that fail during discovery (e.g., missing dependencies, environment setup); should document how to mark commands as unverified and why
  • Opportunity: No example of generated skill output; a template or minimal example would help an agent understand the target format
  • Opportunity: References external package (`babysit`'s ledger writer) but does not document minimum version, availability fallback, or error handling if package is missing
  • Opportunity: Does not specify how to handle monorepos or multi-workspace projects where verification commands may differ per workspace
  • Weakness: Scope of 'manual surface' is vague; no guidance on how to identify which flows matter or how much detail 'looks right' should contain
Model: claude-haiku-4-5-20251001Analyzed: Nov 8, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use Yeachan-Heo/create-verification-skill in your dev environment

Start a Developer trial

Command Palette

Search for a command to run...