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

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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-sequenced debugging workflow with strong validation checkpoints and a sound reference split. Its main weaknesses are motivational prose that inflates the token budget and a missing `gotchas.md` bundle file that breaks one navigation path.

Suggestions

Trim motivational/editorial prose (the "~10 hours of Slack-streaming" anecdote, "feels like overkill until it isn't", "the bug always lives in the branch you didn't instrument") into terse imperatives to recover token budget on the lowest-scoring conciseness dimension.

Create `gotchas.md` or remove the two body references to it, since a referenced-but-missing core file breaks the otherwise clean one-level-deep navigation scored under progressive_disclosure.

Consider moving the long Pre-Flight `--wt` flag-handling block into a reference file so the SKILL.md overview stays lean and the routing structure stays uniform.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (specific flags, agent names, schemas without hand-holding), but contains motivational/editorial padding such as the "~10 hours of Slack-streaming fixes" anecdote, "feels like overkill until it isn't," and "the bug always lives in the branch you didn't instrument" that could be tightened to terse imperatives.

2 / 3

Actionability

Provides fully executable, copy-paste-ready guidance: `git log --oneline -10 -- <affected-files>`, `mcp__basic-memory__search_notes({ query: "…", page_size: 5 })`, `agy-agent --model pro --grounded`, `npx tsc --noEmit`, and a concrete debug-log.jsonl template — not pseudocode.

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced (Pre-Flight checklist, Detection table, Mode A Investigate→Hypothesize & Test→Fix & Verify numbered 1–5) with explicit validation checkpoints (test suite, tsc/eslint, before/after baseline) and feedback loops (Instrumentation Pivot, 3-Strike Rule); risky/mutating ops carry verification and a >5-file blast-radius gate, so workflow_clarity is not capped at 2.

3 / 3

Progressive Disclosure

Structure is well-signaled and one-level-deep with all seven `references/*.md` files present and correctly routed, but `gotchas.md` is referenced twice as a core "known failure patterns" resource and is absent from the bundle — a broken navigation link that prevents a clean top score.

2 / 3

Total

10

/

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 strong, third-person description that pairs an explicit "Use when" trigger with several concrete debugging actions and natural user vocabulary. It clearly answers what the skill does and when to invoke it with minimal risk of conflict.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "investigation, hypothesis testing, and verified fix with structured evidence collection" — matching the score-3 anchor that rewards several specific actions rather than a single domain label.

3 / 3

Completeness

Explicitly answers both halves: "Use when the user reports a bug…" (when) and "routes through investigation, hypothesis testing, and verified fix…" (what), with an explicit trigger clause.

3 / 3

Trigger Term Quality

"bug, error, test failure, or unexpected behavior" are exactly the natural terms a user would say when reporting a problem, with good coverage of common variations and no jargon.

3 / 3

Distinctiveness Conflict Risk

The combination of bug-report triggers with an investigation→hypothesis→verified-fix workflow carves a clear debugging niche that is unlikely to fire for adjacent skills.

3 / 3

Total

12

/

12

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.