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 procedural skill: every step is concrete and executable, writes are gated by explicit user confirmation, and each mode has defined verdicts with error-recovery paths. The only minor improvements are tightening the long parenthetical sentences in verify mode and moving the report template to a reference file.

DimensionReasoningScore

Conciseness

The body is dense with project-specific specifics (exact paths, ID allocation rules, engine test directories, the gdUnit4 remote-debug flag) and teaches nothing Claude already knows; the long parenthetical sentences in Phase 2C steps 2 and 4 could be tightened, matching anchor 4 rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Fully executable guidance throughout: a copy-paste-ready report template, an exact ID allocation algorithm ("Glob production/qa/bugs/BUG-*.md, take the highest number and add 1, zero-padded to four digits"), scripted user questions with named options, explicit verdict definitions, and a complete closure record template.

5 / 5

Workflow Clarity

Clear phase sequencing with explicit validation checkpoints (ask-before-every-write, BLOCKED verdicts, status must be Verified Fixed before closing) and error-recovery feedback loops (STILL PRESENT reopens and suggests /hotfix; CANNOT VERIFY re-runs after the user plays the steps; no matching bug ID stops with a named message), matching anchor 5.

5 / 5

Progressive Disclosure

A single-file skill with no bundle, organized into clearly headed phases and clearly signaled one-level references to project docs (.claude/docs/automation-modes.md, .claude/docs/directory-structure.md) and the sibling /bug-triage skill; the ~50-line report template is inlined — defensible since two modes use it, but splitting it into a references file would push this to 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 communicates the core capability concisely in third person with reasonably natural trigger terms, but it is incomplete: it covers only two of the skill's four modes and lacks any explicit "when to use" guidance. Distinctiveness is good, with minor overlap risk against code-review skills.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user reports a bug, asks to file/write a bug report, or wants code analyzed for bugs."

Mention the verify and close capabilities, e.g. "verify a reported fix (BUG-ID) and close verified bugs with a resolution record", so the description covers all four modes.

Include common synonyms such as "issue" or "defect" and file-format hints like the BUG-NNNN IDs to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ("Structured bug report from a description", "analyze code for potential bugs") plus output fields ("Reproduction steps, severity"), but omits the skill's verify and close modes entirely — a major coverage gap that keeps it below anchor 4.

3 / 5

Completeness

The "what" is clear (generate structured bug reports, analyze code for bugs) but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines; not 2 because the "what" is not vague.

3 / 5

Trigger Term Quality

Includes natural phrases users would say — "bug report", "potential bugs", "reproduction steps", "severity", "analyze code" — matching anchor 4's good coverage; common synonyms like "issue", "defect", or "verify the fix" are missing, so not anchor 5.

4 / 5

Distinctiveness Conflict Risk

Bug reporting is a clear niche with distinct triggers ("bug report", "reproduction steps"), but "analyze code for potential bugs" overlaps with code-review skills, matching anchor 4's minor overlap risk rather than anchor 5's minimal conflict.

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

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.