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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured debugging skill with clear workflows and excellent one-level-deep reference organization. Its only weakness is conciseness — the body carries rationale and dense conditional prose that pushes past the token-efficiency ideal.

Suggestions

Move rationale/justification sentences (e.g. "Speculation without evidence is the #1 reason debugging stalls", "Observation beats speculation") into the relevant references and keep SKILL.md to the imperative rule.

Condense the capability-loading, worktree DOCKER CONTEXT, and agentmemory HTTP-route contracts into their reference files, leaving only the dispatch rule and a pointer inline.

Trim repeated justifications of the Iron Law / 3-Strike Rule where the numbered steps already convey the requirement.

Dimension	Reasoning	Score
Conciseness	Per-line content is operational and dense, but the ~190-line body includes rationale sentences (e.g. "Speculation without evidence is the #1 reason debugging stalls") and lengthy conditional prose around capability/worktree contracts that could be tightened or moved to references.	2 / 3
Actionability	Provides concrete executable commands (npx tsc --noEmit, git log --oneline -10 -- <files>, a full agentmemory curl template) and exact MCP tool-call signatures plus a JSONL append example — copy-paste ready.	3 / 3
Workflow Clarity	Mode-based routing (Q/A/B/C), a MANDATORY pre-flight checklist, and numbered Fix & Verify steps with explicit validation checkpoints and feedback loops (instrumentation pivot, 3-Strike Rule, prevention gate) match the top anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview that routes to one-level-deep, clearly-signaled references (mode-b-deep, prevention-gate, debug-report-template, etc.), all verified to exist as real files in references/.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, third-person description that covers what, when, and distinct triggers with concrete actions. It hits all four dimension anchors at the top of the scale with no over-claiming or fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "investigation, hypothesis testing, and verified fix with structured evidence collection" — matching the anchor for listing several specific actions rather than vague domain naming.	3 / 3
Completeness	Explicitly answers both what it does (routes through investigation/hypothesis/fix) and when to use it via a clear "Use when the user reports..." trigger clause.	3 / 3
Trigger Term Quality	Includes natural user-facing terms ("bug, error, test failure, or unexpected behavior") a user would actually say; coverage is good enough that it does not fall to the "some keywords, missing common variations" level.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear debugging/bugfix niche with distinct triggers unlikely to fire for unrelated skills; no overlap risk with general coding or doc skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: quangtran88/x-skills
Commit: 6381b15

Reviewed: 2 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.