CtrlK
BlogDocsLog inGet started
Tessl Logo

fix-bug

Guide for fixing bugs in ClaudeBar following Chicago School TDD and rich domain design. Use this skill when: (1) User reports a bug or unexpected behavior (2) Fixing a defect in existing functionality (3) User asks "fix this bug" or "this doesn't work correctly" (4) Correcting behavior that violates the user's mental model

66

Quality

80%

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/fix-bug/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 tight, actionable bug-fix workflow with strong validation checkpoints and a feedback loop. The two weakest spots are the redundant ASCII diagram (conciseness) and the single-file monolithic structure with template placeholders (actionability, progressive disclosure).

Suggestions

Remove or shrink the ASCII workflow box (lines 17-43): it duplicates the 'Phase 1/2/3' headings detailed immediately below, saving ~26 lines of pure decoration.

Replace the bare template placeholders ({Component}Tests, {describes correct behavior}) with a worked concrete example (e.g. QuotaMonitorSelectionTests) so the test pattern is copy-paste-ready, keeping the template form as a secondary note.

Consider moving the Domain Design Principles Swift patterns into a references/ file and linking to it from Phase 3, so the main SKILL.md stays a concise overview and the detailed invariant patterns are one level deep.

DimensionReasoningScore

Conciseness

The body is lean and states non-obvious codebase conventions (Chicago School, state-based testing, no verify() calls) rather than padding with basics; the decorative ASCII workflow box restates the phase headings immediately below it and is the one trim candidate keeping it from the top score.

4 / 5

Actionability

Provides a concrete Swift @Suite/@Test pattern with Given/When/Then, executable `swift test --filter` commands, and location-mapping tables; template placeholders like `{Component}Tests` and `{describes correct behavior}` are the minor gap versus copy-paste-ready code.

4 / 5

Workflow Clarity

A clear three-phase sequence (Reproduce -> Red -> Green) carries explicit validation checkpoints (test FAILS before fix, PASSES after, all existing tests still pass), a red->green feedback loop, and a closing checklist, matching the top anchor.

5 / 5

Progressive Disclosure

Well-organized into clear sections with one clearly-signaled, one-level-deep reference (docs/ARCHITECTURE.md); it remains a single monolithic document rather than splitting detail into bundle files, so it sits just below the 'appropriately split' top anchor.

4 / 5

Total

17

/

20

Passed

Description

78%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 clearly and explicitly answers both 'what' and 'when' with natural, concrete trigger phrases and a well-scoped niche. Its weakest area is specificity, since the action side is carried by methodology labels rather than an enumerated set of concrete actions.

DimensionReasoningScore

Specificity

Names the domain and methodology ('fixing bugs', 'Chicago School TDD', 'rich domain design') but enumerates only one core action; the concrete action list is thin compared to the trigger detail, matching the 'names domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

Clearly states the 'what' ('Guide for fixing bugs in ClaudeBar following Chicago School TDD and rich domain design') and an explicit 'Use this skill when:' block with four concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes several natural user phrases ('reports a bug', 'fix this bug', 'doesn't work correctly', 'defect', 'violates the user's mental model') with good coverage; a few common synonyms (e.g. 'broken', 'crash', 'error') are absent, so it sits just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Scoped to a named app and a specific methodology with bug-fixing-only triggers, giving a clear niche; minor overlap risk remains with general TDD or refactoring skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
tddworks/ClaudeBar
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.