bug-report

Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/bug-report/SKILL.md

Quality

Content

92%

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

The content is highly actionable with a complete template, clear phased workflow, and explicit validation/permission checkpoints. The main weakness is progressive disclosure: everything lives inline in one file with no reference offloading.

Suggestions

Extract the bug-report markdown template (Phase 2A) into a reference file such as references/bug-report-template.md and link to it, reducing the inline bulk and enabling one-level-deep navigation.

Move the detailed Verify/Close procedural steps into a reference (e.g., references/verify-close-workflow.md) if they are not needed on every invocation, keeping SKILL.md as an overview.

Trim the recap redundancy in Phase 4 Next Steps where it restates verify-before-close guidance already covered in Phases 2C/2D.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no concept padding, and the large template block is the skill's core deliverable so it earns its place; it is not 2 because there is no unnecessary explanation, only mild recap redundancy in Next Steps.	3 / 3
Actionability	Provides a complete copy-paste markdown template, exact output paths ("production/qa/bugs/[BUG-ID].md"), explicit verdict labels, and named slash commands (/bug-triage, /hotfix); it is not 2 because guidance is concrete and complete rather than pseudocode or vague.	3 / 3
Workflow Clarity	Phases are explicitly sequenced with validation checkpoints — close mode stops if status is not "Verified Fixed", verify mode runs repro/test/regression checks, and writes require user permission; it is not 2 because checkpoints and feedback loops are explicit, not implicit.	3 / 3
Progressive Disclosure	Sections are well-organized into phases, but the skill is a monolithic 155-line file with no external references, and the reusable bug-report template could be split into a reference file; it is not 1 because organization is clear rather than a wall of text, and not 3 because nothing is offloaded to one-level-deep references.	2 / 3
	Total	11 / 12 Passed

Description

60%

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

The description is specific and action-oriented with strong third-person voice, but lacks an explicit "Use when..." trigger clause and has moderate overlap risk with code-review skills. Adding trigger terms and a usage clause would lift the weaker dimensions.

Suggestions

Add an explicit "Use when..." clause naming the situations that should trigger this skill (e.g., "Use when filing a bug report, when the user reports a defect or crash, or when asked to analyze a file for potential bugs").

Broaden trigger terms to include common variations users say — "defect", "issue", "crash", "error", "regression" — alongside "bug".

Sharpen the code-analysis framing to distinguish it from generic code review, e.g., "analyzes a specific file for concrete bug patterns (null refs, off-by-one, race conditions)".

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Creates a structured bug report", "analyzes code to identify potential bugs", and "Ensures...full reproduction steps, severity assessment, and context" — matching the anchor for multiple specific concrete actions; it is not the level below because the actions are named comprehensively rather than partially.	3 / 3
Completeness	The description clearly states what the skill does but offers no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the guidelines; it is not 1 because the "what" is strong and explicit.	2 / 3
Trigger Term Quality	Natural terms like "bug report", "code", "bugs", and "reproduction steps" appear, but common variations a user might say (defect, issue, crash, error) are missing, fitting the "some relevant keywords but missing common variations" anchor; it is not 3 because coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	The bug-report niche is fairly clear, but "analyzes code to identify potential bugs" could overlap with generic code-review or linting skills, matching the "somewhat specific but could still overlap" anchor; it is not 3 because of that overlap risk.	2 / 3
	Total	9 / 12 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/bug-report/SKILL.md
Commit: 984023d

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.