bug-report

Structured bug report from a description, or analyze code for potential bugs. Reproduction steps, severity.

Quality

78%

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

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.

The content is a tightly written, highly actionable multi-mode workflow with strong validation gates, explicit permission checkpoints, and well-defined verdicts and error paths. Its main weakness is structural rather than substantive: everything lives in one ~190-line file with the full report template inline, and a few passages could be phrased more cleanly.

Dimension	Reasoning	Score
Conciseness	The body is dense with project-specific instructions Claude could not know (config resolution order, bug file locations, engine test roots, triage-ladder coupling) and avoids explaining general concepts. A few passages are awkwardly phrased or repeated (the verify-mode file-finding prose), keeping it just below anchor 5's 'every token earns its place'.	4 / 5
Actionability	Guidance is fully executable for an instruction-only skill: exact glob patterns ("production/qa/bugs/BUG-*.md"), exact ask strings, exact verdict labels (VERIFIED FIXED / STILL PRESENT / CANNOT VERIFY / BLOCKED), a complete report template, and specific fallbacks for each failure path (missing bug, unset commands.test, declined write). Per the scoring notes, absence of code is not penalized when guidance is this concrete.	5 / 5
Workflow Clarity	The four modes are clearly sequenced with explicit validation checkpoints: close mode refuses anything not Verified Fixed, verify mode re-runs reproduction steps and defines BLOCKED/CANNOT VERIFY recovery paths, and every file write is gated on an explicit user confirmation. Error-recovery loops ("run /bug-report verify again once played", reopen on STILL PRESENT) match anchor 5.	5 / 5
Progressive Disclosure	The body is well-organized with clear phase sections and signals external references one level deep (.claude/docs/automation-modes.md, .claude/docs/directory-structure.md, the bug-triage SKILL.md); no bundle files exist to mis-navigate. However, the ~50-line report template and detailed verify/close procedures are all inline in a ~190-line file that exceeds the simple-skill case, leaving minor organization gaps versus anchor 5.	4 / 5
	Total	18 / 20 Passed

Description

61%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.

The description states concrete capabilities in third person with reasonable natural keywords, but it covers only two of the skill's four modes (description and analyze; verify and close are absent) and includes no explicit 'when to use' trigger clause. It is serviceable but incomplete as a routing description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user reports a bug, asks to analyze code for bugs, or wants to verify or close a filed bug."

Mention the verify [BUG-ID] and close [BUG-ID] capabilities so the description covers all four modes the skill supports.

Include a few more natural synonyms users say, such as "issue", "defect", "reproduce", or "regression", to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions — "Structured bug report from a description" and "analyze code for potential bugs", plus "Reproduction steps, severity" — but omits the verify and close capabilities the skill actually has, so coverage is not comprehensive. It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) better than anchor 4, whose 'minor gaps' would require the mode coverage to be nearly complete.	3 / 5
Completeness	The "what" is clear (generate structured bug reports, analyze code for bugs) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Anchor 4 requires both what and when; the when is entirely absent here, not merely imprecise.	3 / 5
Trigger Term Quality	Natural keywords like "bug report", "bugs", "code", "reproduction steps", and "severity" are phrases a user would plausibly say. A few natural terms are missing ("verify a fix", "close a bug", "issue", "defect"), which fits anchor 4 rather than anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The bug-reporting niche is fairly distinct, though "analyze code for potential bugs" overlaps with code-review and security-review skills. This is minor overlap with closely related skills (anchor 4) rather than the clear, minimal-conflict niche of anchor 5.	4 / 5
	Total	14 / 20 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: b21fa0f

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.