CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

verifier-setup

Set a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a one-command dev stack (`dev-local`) exists, asks whether verification runs locally or in a sandbox (crabbox), confirms/installs the driver (the `playwright-cli` skill for web by default). Outputs three artifacts: a committed `/verify` skill (per-task verification SOP — spawn a verifier sub-agent → drive the app → screenshot/video proof → open a PR with the proof embedded), the `/dev-local` skill + script, and the installed driver skill. Use when someone says "set up verification", "make this repo verifiable", "scaffold a verify skill", "set up the verifier".

Quality

87%

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

75%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.

A well-structured setup SOP with concrete commands, a clear conditional workflow, and a properly externalized template. It loses points mainly for mild redundancy in the Principles section and feedback loops that are implied rather than explicit.

Suggestions

Tighten the Principles section so it states the philosophy once instead of restating Step 0–2 inventory/reuse guidance, freeing token budget.

Add an explicit error-recovery loop for the destructive-adjacent case where an existing setup is found but broken (e.g. "if the found launcher fails to bring the stack up, fix it before proceeding") to lift workflow_clarity.

Move any remaining inlined boilerplate (e.g. the full placeholder list in Step 5) into the template file or a short table so SKILL.md reads as a cleaner overview.

DimensionReasoningScore

Conciseness

Lean and actionable with no padding explaining concepts Claude already knows, but the closing "Principles" section reiterates guidance already stated in Steps 0–2, a minor redundancy that could be trimmed.

4 / 5

Actionability

Provides concrete, executable anchors — `npx --yes @playwright/cli --version`, `gh release upload`, `cbx.sh pw`, `scripts/dev-local.sh up` — and names specific skills to invoke (dev-local-setup, crabbox-setup, playwright-cli), with only minor abstract guidance interspersed.

4 / 5

Workflow Clarity

Steps 0–6 are clearly sequenced with explicit checkpoints (the Step 0 "check before you add ANYTHING" inventory, idempotent reuse-or-provide decisions in Step 2), though error-recovery feedback loops are less explicit than the rubric's top anchor.

4 / 5

Progressive Disclosure

Well-organized into labeled sections with a clearly signaled one-level-deep reference to the real `assets/verify.template.md`; most detail is appropriately externalized to that template, with only minor bulk carried inline in SKILL.md.

4 / 5

Total

16

/

20

Passed

Description

96%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 strong, third-person description that clearly states what the skill does and when to invoke it, with concrete actions and natural trigger phrases. Only minor overlap risk with the closely related `/verify` and `dev-local-setup` skills keeps distinctiveness from a 5.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions — "Investigates the repo, ensures a one-command dev stack (`dev-local`) exists", "confirms/installs the driver", and enumerates three specific output artifacts (the `/verify` skill, the `/dev-local` skill + script, the installed driver skill).

5 / 5

Completeness

Explicitly answers both what (investigate, ensure dev stack, ask local/sandbox, install driver, output three artifacts) and when ("Use when someone says...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes comprehensive natural trigger phrases a user would actually say — "set up verification", "make this repo verifiable", "scaffold a verify skill", "set up the verifier" — covering several synonymous phrasings of the intent.

5 / 5

Distinctiveness Conflict Risk

The setup-vs-run framing and setup-specific triggers carve a clear niche, but it sits adjacent to the `/verify` skill it generates and to `dev-local-setup`, leaving minor overlap risk with those closely related skills.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

14

/

16

Passed

Repository

AI-Builder-Club/skills

Path

skills/verifier-setup/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.