CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qa

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

66

Quality

83%

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-crafted, directive skill body: it teaches nothing Claude already knows, provides ready-to-use issue templates, and sequences the QA session into five clear steps with most checkpoints present. Weakest spots are a small amount of duplicated guidance, a missing example gh invocation, and no post-filing verification step.

Suggestions

Deduplicate the dependency-order guidance: 'Create issues in dependency order' appears both in the breakdown intro and in the 'When creating a breakdown' bullet list — keep it in one place.

Add a concrete example of the filing command, e.g. `gh issue create --title "<short user-facing summary>" --body-file <tmpfile>` -- or state explicitly that title/body should be passed via flags, so the filing step is copy-paste ready.

Add a post-filing verification step to the workflow: confirm each issue URL was created successfully (e.g., check the gh output/returned URL) before summarizing blocking relationships, closing the validation gap in step 4.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and teaches no concepts Claude already knows — every section is directive. One minor trimmable redundancy: 'Create issues in dependency order' appears both in the breakdown section intro ('Create issues in dependency order (blockers first) so you can reference real issue numbers') and again as a bullet ('Create issues in dependency order so you can reference real issue numbers'), keeping it just below the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: specific tools ('Agent (subagent_type=Explore) in the background', 'Create issues with `gh issue create`'), copy-paste-ready issue templates with placeholders, and explicit rules ('No file paths or line numbers', 'Reproduction steps are mandatory'). The minor gap versus anchor 5 is that no example `gh issue create` invocation (with title/body flags) is given, so the filing step relies on Claude's existing knowledge of gh flags.

4 / 5

Workflow Clarity

A clear five-step sequence (listen/clarify → explore → assess scope → file → continue) with most checkpoints present: a question limit ('at most 2-3 short clarifying questions'), a recovery path for missing repro steps ('if you can't determine them, ask the user'), and a session-level feedback point ('ask: "Next issue, or are we done?"'). The remaining gap versus anchor 5 is the absence of any post-filing verification (e.g., confirming each issue URL was created successfully or re-reading the filed issue body). Issue creation is not destructive, so the destructive/batch cap at 3 does not apply.

4 / 5

Progressive Disclosure

The body is well-structured with clear section headers, a numbered step sequence, and distinctly labeled single-issue and breakdown templates; no bundle files exist and none are strictly required at this size. It does not reach anchor 5 because the two full issue templates are inlined and could arguably be extracted to reference files, and the skill exceeds the under-50-lines threshold under which well-organized sections alone would score 5.

4 / 5

Total

16

/

20

Passed

Description

83%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 description: it clearly and explicitly states what the skill does and when to use it, in third person, with natural trigger phrases like 'report bugs' and 'QA session'. The main improvement opportunities are broader trigger synonyms (e.g., 'bug report') and surfacing the issue-breakdown behavior as a capability.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'user reports bugs or issues conversationally, and the agent files GitHub issues' and 'Explores the codebase in the background for context and domain language' — with only minor gaps (e.g., issue breakdown/scoping behavior is not surfaced). It names several specific actions but stops short of the comprehensive coverage of the anchor-5 example.

4 / 5

Completeness

It explicitly answers both what ('Interactive QA session... the agent files GitHub issues. Explores the codebase in the background for context and domain language') and when ('Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session"'), with concrete trigger phrases in third-person voice — a direct match to anchor 5.

5 / 5

Trigger Term Quality

Natural trigger phrases are present — 'report bugs', 'do QA', 'file issues conversationally', 'QA session' — giving good keyword coverage. A few natural variations are missing (e.g., 'bug report', 'report a problem', 'file a bug'), so it falls just short of the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The 'QA session' trigger and GitHub-issue-filing outcome define a mostly distinct niche with minimal conflict risk. Minor overlap remains: 'report bugs' could also fire when a user wants a bug fixed rather than an issue filed, which fits anchor 4 rather than the fully distinct anchor 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

SnowingFox/ai-skills

Path

.cursor/skills/qa/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.