CtrlK
BlogDocsLog inGet started
Tessl Logo

qa

Multi-agent, browser-driven QA pass over a branch or PR — scope it, plan it, fan out one subagent per testing area in its own isolated sandbox, compile a severity-ranked markdown report. Use for an "E2E test", "QA pass", "manual test", or "bug bash" request — broader than driving the UI to check one fix (see `playwright`) or reviewing a diff (see `code-review`).

75

Quality

94%

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

88%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 strong, highly actionable orchestration skill with clear sequencing and real validation checkpoints for an expensive batch operation. Its main weakness is conciseness and structure: minor rhetorical padding and a long single-file body that could delegate more to reference files.

Suggestions

Trim rhetorical justification flourishes (e.g. 'not a vibe', 'the guidance is what keeps the run from reaching it') to tighten the body without losing the concrete guidance.

Extract the per-lane subagent briefing checklist and the 'Whether an LLM provider is connected' section into a reference file (e.g. references/lane_briefing.md) and link to it, reducing the main SKILL.md to a leaner overview.

Consider moving the dev-server/browser isolation command blocks into a reference snippet so the isolation matrix and mechanics live one level deep rather than inline.

DimensionReasoningScore

Conciseness

Mostly efficient and concrete, but carries minor rhetorical justification that could be trimmed — e.g. 'not a vibe', 'not an allowance to use up', 'the guidance is what keeps the run from reaching it' — padding that assumes less of Claude's competence than needed.

4 / 5

Actionability

Provides copy-paste-ready bash blocks with specific env vars, concrete commands (playwright-cli -s=<name>, git log --oneline, rm -rf ...), and a concrete subagent briefing checklist covering the common cases.

5 / 5

Workflow Clarity

Clear numbered sequence with explicit validation gates (approval before launch, verify date cutoff, check provider key, stop on 402/429, cleanup before done), a feedback loop (restate updated plan mid-flight), and checklists — validation is present for this batch operation, so no cap applies.

5 / 5

Progressive Disclosure

Well-organized sections and good one-level-deep delegation to the `playwright` skill for command mechanics, but the body is a single ~230-line monolith with no bundle reference files of its own; the briefing template and provider-key sections could be split out.

4 / 5

Total

18

/

20

Passed

Description

100%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.

An excellent description: it states concrete capabilities, gives multiple natural trigger phrases, explicitly distinguishes itself from neighboring skills, and answers both what and when. No meaningful gaps to penalize.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'scope it, plan it, fan out one subagent per testing area in its own isolated sandbox, compile a severity-ranked markdown report' — giving comprehensive coverage rather than just naming the domain.

5 / 5

Completeness

Explicitly answers both what ('Multi-agent, browser-driven QA pass...') and when ('Use for an "E2E test", "QA pass", "manual test", or "bug bash" request') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes the natural phrases a user would actually say — 'E2E test', 'QA pass', 'manual test', 'bug bash' — covering synonyms and variations rather than technical jargon.

5 / 5

Distinctiveness Conflict Risk

Carves out adjacent skills explicitly — 'broader than driving the UI to check one fix (see `playwright`) or reviewing a diff (see `code-review`)' — giving a clear niche with minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
Kiln-AI/Kiln
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.