CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplarily disciplined instruction-only skill: lean, dense with exact commands, paths, and API names, and a clearly sequenced workflow ending in an explicit prove-it validation step. The only gaps are the deferred ledger invocation and the absence of an error-recovery loop for failed discovery commands.

DimensionReasoningScore

Conciseness

The body is lean with zero padding: no explanations of concepts Claude already knows, tight section structure (When to use / Workflow / Rules), and every sentence carrying operational content such as "record the read-only check form (`prettier --check`, `eslint --check`)... never the mutating one". Even rhetorical lines like "A command you have not run is a hypothesis, not a check" function as enforceable rules, so the 5 anchor ("every token earns its place") fits rather than 4's "minor instances of over-explanation".

5 / 5

Actionability

Guidance is highly concrete: exact paths (`.claude/skills/verify/SKILL.md`, `.omc/state/verification-ledger.tsv`), exact API functions (`appendLedgerEntry`, `defaultLedgerPath` from `dist/features/verification-ledger/index.js`), a defined verdict vocabulary (`live-ui-verified`, `unit-test-verified`, `type-check-only`), and specific command forms. It falls just short of fully copy-paste-ready because the ledger invocation is deferred ("`babysit`'s ledger step demonstrates the exact invocation") rather than shown inline, matching 4's "concrete commands with minor gaps".

4 / 5

Workflow Clarity

Five clearly sequenced steps with an explicit final validation step ("**Prove it.** Run the generated skill's own flow once end to end") and honest-verdict checkpoints, plus the read-only-form rule guarding against mutating commands. It misses the 5 anchor's "feedback loops for error recovery" — there is no guidance for what to do when a discovery command fails mid-workflow — so it sits at 4 rather than 5.

4 / 5

Progressive Disclosure

The skill is a single self-contained SKILL.md (~55 lines, no references/, scripts/, or assets/ bundles) whose content is all core workflow that belongs inline, organized under clear sections (When to use, Workflow, Rules). Cross-references to other skills (`verify`, `execute`, `babysit`, `maintain-verification-skill`) are one level deep and well-signaled, satisfying the simple-skill exception for a 5.

5 / 5

Total

18

/

20

Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, concrete description that clearly states what the skill produces, weakened only by the missing explicit "Use when..." trigger clause — its sole when-guidance is the frequency note "Run once per repo". Trigger terms are good but lack synonyms and are buried inside the capability list.

Suggestions

Add an explicit trigger clause, e.g., "Use when a repo has no .claude/skills/verify/ and verification will run here repeatedly, or when the user asks to set up verification/build-test-lint checks for a project."

Include common trigger synonyms such as "verification", "test suite", or "CI commands" so the description matches the varied phrasings users actually say.

Briefly differentiate from the sibling maintain-verification-skill (e.g., "creating vs. re-syncing the verify skill") to reduce overlap risk between the two.

DimensionReasoningScore

Specificity

The description enumerates four concrete deliverables — "build/test/lint commands discovered by running them, a feature map of what each covers, manual checks, and an earned first verdict" — comprehensively covering the skill's outputs with no vague filler. This clearly matches the 5 anchor ("multiple specific concrete actions; comprehensive coverage") rather than 4, since no meaningful output of the skill is omitted.

5 / 5

Completeness

The "what" is clear and concrete, but the only when-guidance is "Run once per repo", which states frequency rather than triggering conditions — no "Use when..." clause or equivalent exists, capping completeness at 3 per the judging guidelines. Not 4 because the 'when' is not merely under-specified, it is absent as explicit trigger guidance.

3 / 5

Trigger Term Quality

Natural terms users would say are present ("verify skill", "build/test/lint", "manual checks", "verdict"), giving good keyword coverage, but common variations like "verification", "CI", or "test suite" are missing and the terms are embedded in the what-clause rather than surfaced as triggers. It is noticeably above the anchor-3 midpoint ("some relevant keywords but missing common variations") but short of the 5 anchor's synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The niche is distinct — generating the project-local verify skill once per repo — with "Run once per repo" separating it from the recurring bundled `verify` skill. Minor overlap risk remains with closely related skills (e.g., the `maintain-verification-skill` it delegates to, or the verify skill itself), keeping it below the 5 anchor's "minimal conflict risk".

4 / 5

Total

16

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

Yeachan-Heo/oh-my-claudecode

Path

skills/create-verification-skill/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.