CtrlK
BlogDocsLog inGet started
Tessl Logo

x-bugfix

Use when the user reports a bug, error, test failure, or unexpected behavior — routes through investigation, hypothesis testing, and verified fix with structured evidence collection

68

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 a dense, well-sequenced debugging workflow with strong validation gates and concrete tool guidance. Its main weakness is conciseness — anecdotal asides and redundant rationale add tokens that Claude does not need.

Suggestions

Trim anecdotal padding such as the Slack-streaming anecdote and rationale clauses like 'Speculation without evidence is the #1 reason debugging stalls'; keep the rule, drop the sermon.

Move the lengthy Instrumentation Pivot and Pre-Flight --wt/isolation contract detail into a dedicated reference file, leaving SKILL.md as a concise overview with signaled links.

Consolidate the repeated tool/agent dispatch tables (Available Tools, Proactive OMO Delegation) to avoid restating the same OMO/OMC/agy rows twice.

DimensionReasoningScore

Conciseness

Mostly efficient but includes some unnecessary explanation and anecdotal padding, e.g. the '~10 hours of speculative Slack-streaming fixes' anecdote and rationale phrases like 'Speculation without evidence is the #1 reason debugging stalls' that Claude does not need.

3 / 5

Actionability

Provides concrete commands (`git log --oneline -10`, `npx tsc --noEmit`, `mcp__basic-memory__search_notes({...})`) and specific tool-dispatch tables, with only minor gaps where dispatch is described rather than shown.

4 / 5

Workflow Clarity

Clear sequence from Detection through Post-Fix with explicit mandatory validation checkpoints, checklists, feedback loops (3-Strike, Instrumentation Pivot, re-validate), and a status-label report table.

5 / 5

Progressive Disclosure

Well-organized sections with one-level-deep references to real bundle files (all 7 referenced reference files verified present) and a Dependencies listing; minor gaps from heavy inlining and dependence on many external sibling/shared files outside this bundle.

4 / 5

Total

16

/

20

Passed

Description

95%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 is well-formed: it explicitly states when to use the skill and what it does, using natural user-facing trigger terms. Specificity is strong but the listed actions are slightly more abstract than the most concrete examples.

DimensionReasoningScore

Specificity

Names several concrete actions — 'investigation, hypothesis testing, and verified fix with structured evidence collection' — but these remain somewhat abstract rather than fully concrete actions like specific code commands.

4 / 5

Completeness

Explicitly answers both what ('routes through investigation, hypothesis testing, and verified fix with structured evidence collection') and when ('Use when the user reports a bug, error, test failure, or unexpected behavior') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes the exact natural terms users say when reporting problems — 'bug, error, test failure, or unexpected behavior' — covering common variations and synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear bugfix niche with distinct triggers ('bug, error, test failure') unlikely to fire for unrelated skills.

5 / 5

Total

19

/

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: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
quangtran88/x-skills
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.