CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

72

Quality

88%

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

77%Scale 1-3

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

This is a well-crafted skill with strong actionability and workflow clarity. The step-by-step process is clearly defined with good decision points and concrete templates. The main weaknesses are minor verbosity in explanations and the fact that the relatively long content could benefit from splitting templates into a referenced file for better progressive disclosure.

Suggestions

Trim explanatory asides like the parenthetical examples in the breakdown criteria to reduce token usage while preserving clarity.

Consider extracting the issue templates into a separate TEMPLATES.md file and referencing it from the main skill to improve progressive disclosure and reduce the main file's length.

DimensionReasoningScore

Conciseness

The content is mostly efficient and well-structured, but includes some unnecessary elaboration. For example, the breakdown criteria lists ('the form validation is wrong AND the success message is missing AND the redirect is broken') could be trimmed, and some guidance like 'Do NOT over-interview' and 'the goal is NOT to find a fix' are useful but slightly verbose. The templates themselves are appropriately lean.

2 / 3

Actionability

The skill provides concrete, actionable guidance: specific issue templates with exact fields, explicit `gh issue create` command, clear rules (no file paths, use domain language, reproduction steps mandatory), and a defined subagent invocation pattern. The templates are copy-paste ready and the workflow is fully specified.

3 / 3

Workflow Clarity

The workflow is clearly sequenced (listen → explore → assess scope → file → continue) with explicit decision points (single vs breakdown), dependency ordering for issue creation, and a feedback loop ('ask the user' if reproduction steps are unclear, 'Next issue, or are we done?' to continue). The validation checkpoint of filing issues in dependency order to reference real numbers is a nice touch.

3 / 3

Progressive Disclosure

The content is well-organized with clear headers and a logical flow, but it's a fairly long single file with no references to external files (except mentioning UBIQUITOUS_LANGUAGE.md as a project resource). The issue templates could potentially be split into a separate reference file to keep the main skill leaner, though this is a borderline case given no bundle files exist.

2 / 3

Total

10

/

12

Passed

Description

100%Scale 1-3

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

This is a strong description that clearly communicates the skill's unique value proposition: an interactive, conversational QA workflow that files GitHub issues with codebase-informed context. It includes explicit trigger guidance, specific actions, and natural keywords. The description is concise yet comprehensive.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: interactive QA session, user reports bugs conversationally, agent files GitHub issues, explores codebase for context and domain language. These are specific, actionable capabilities.

3 / 3

Completeness

Clearly answers both what (interactive QA session, files GitHub issues, explores codebase for context) and when (explicit 'Use when' clause with triggers like 'report bugs', 'do QA', 'file issues conversationally', or mentions 'QA session').

3 / 3

Trigger Term Quality

Includes strong natural trigger terms: 'report bugs', 'QA', 'file issues', 'QA session', 'conversationally', 'GitHub issues'. These cover terms users would naturally say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche combining conversational bug reporting with GitHub issue filing and codebase exploration. The 'QA session' trigger and conversational aspect clearly distinguish it from generic issue-filing or code-review skills.

3 / 3

Total

12

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
SnowingFox/ai-skills
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.