CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The body is an exemplary instruction-only skill: every phase has concrete, copy-paste-ready guidance, explicit verdicts, consent gates, and feedback loops for failure paths. The only real weaknesses are mild — a few sentences need re-reading, and some per-mode detail could be split into reference files to slim the main file.

Suggestions

Split the verify-mode and close-mode edge-case prose (number-matching rules, subagent question wording, engine test-root paths) into a short reference file, keeping SKILL.md as the dispatching overview.

Break the run-on sentence in verify step 2 into a short list (find test file → check commands.test → run narrowed suite) so the flags-and-runners caveat is easier to scan.

State the 'find the bug file by its number' rule once in a shared section and reference it from both verify and close modes instead of restating it.

DimensionReasoningScore

Conciseness

The body is dense and directive with almost no explanation of concepts Claude already knows, but a few passages could be trimmed — the long run-on sentence in verify step 2 and the 'find the bug file by its number' rule being restated across verify and close modes. Matches anchor 4 (efficient with minor trims); not 5 because several sentences are contorted enough to require re-reading.

4 / 5

Actionability

Fully executable guidance throughout: a complete copy-paste bug report template, exact Glob patterns ('production/qa/bugs/BUG-*.md'), exact questions to ask ('May I write this to production/qa/bugs/BUG-[NNNN].md?'), exact verdicts, the ID allocation rule, and even subagent fallback wording. Matches anchor 5 for an instruction-only skill.

5 / 5

Workflow Clarity

Clear phased sequence with mode dispatch and explicit validation checkpoints everywhere: verify requires a test run or user confirmation before any verdict, close refuses bugs not Verified Fixed, save gates on user consent, and failure paths (BLOCKED, STILL PRESENT → reopen + /hotfix, CANNOT VERIFY → re-run) form feedback loops. Matches anchor 5.

5 / 5

Progressive Disclosure

A single well-sectioned file with clearly signaled one-level-deep references (.claude/docs/automation-modes.md, .claude/docs/directory-structure.md, /bug-triage), but at ~200 lines it inlines verify/close edge-case detail that could live in reference files, matching anchor 4 rather than 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 communicates a clear, distinct capability in the bug-reporting niche with decent natural keywords, but it lacks any 'when to use' trigger guidance and its action coverage is thin relative to what the skill actually does. Adding an explicit 'Use when...' clause and naming the verify/close workflows would lift both completeness and specificity.

Suggestions

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

Mention the verify and close capabilities (confirming a fix, closing a verified bug) so the 'what' matches the skill's four modes rather than two.

Include common synonyms users say such as 'issue', 'defect', or 'regression' to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain (bug reporting) and two concrete actions ('Structured bug report from a description, or analyze code for potential bugs') plus report fields ('Reproduction steps, severity'), but coverage is not comprehensive — the fragmentary field list and omission of the verify/close capabilities keep it at anchor 3 rather than 4.

3 / 5

Completeness

The 'what' is clear (creates structured bug reports; analyzes code for bugs) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Natural terms users would say are present ('bug report', 'analyze code', 'potential bugs', 'reproduction steps', 'severity'), giving good keyword coverage, though common synonyms like 'issue', 'defect', or 'crash' are missing, so it does not reach anchor 5.

4 / 5

Distinctiveness Conflict Risk

'Structured bug report', 'Reproduction steps', and 'severity' carve a distinct QA niche, but 'analyze code for potential bugs' overlaps with code-review style skills, matching anchor 4 (mostly distinct, minor overlap risk) rather than 5.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

Revision

05ad7c8

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill