CtrlK
BlogDocsLog inGet started
Tessl Logo

debugging

系统化 bug 定位:根因调查 → 模式分析 → 假设验证 → 修复。 Use when: 遇到 bug、测试失败、unexpected behavior。 Not for: 新功能开发、重构、已知原因的简单修复。 Output: Bug report(5件套)+ 根因 + 修复(含回归测试)。

71

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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

The skill is highly actionable with a clear, gated workflow and concrete executable diagnostics, but it is slightly verbose (motivational prose and triple-repeated phases) and its progressive disclosure is undermined by a dead link to the bug-diagnosis-capsule template and three referenced deep-dive files that are not present in the bundle.

Suggestions

Add the missing refs/bug-diagnosis-capsule.md template file to the bundle (or inline the 8-field capsule template), since the body directs users to it as the entry point but the file does not exist.

Restore or re-summarize root-cause-tracing.md, defense-in-depth.md, and condition-based-waiting.md as actual bundle files rather than only referencing them as git-history archives, so the one-level-deep references resolve.

Trim motivational/repetitive prose (e.g. the duplicated phase descriptions across the main section, the flowchart, the Quick Reference table, and Common Mistakes table) to tighten conciseness.

DimensionReasoningScore

Conciseness

Mostly efficient and action-oriented, but padded with motivational prose ("随机尝试修复浪费时间,症状修复掩盖真正问题", "这不是懒,是推甩责任") and the 4 phases are restated three times (full section, flowchart, Quick Reference table, Common Mistakes table) where one canonical statement plus one reference table would do.

2 / 3

Actionability

Provides fully executable, copy-paste-ready bash (lsof/ps/git/grep with real flags, env-var fallback) and concrete field-collection templates; the preflight gate, capsule 8-field template, and red-flag self-checks are specific and operational.

3 / 3

Workflow Clarity

Clear sequenced 4-phase pipeline with explicit gating ("没有根因分析,不能提出修复方案"), a hard preflight gate with evidence requirements, feedback loops (failed hypothesis → new hypothesis; 3-failure → escalate to architecture), and a validation checkpoint (fail-test-first then verify) — matching the score-3 anchor.

3 / 3

Progressive Disclosure

Section organization is good, but the body repeatedly points to a bundle file that does not exist ("../refs/bug-diagnosis-capsule.md" for the entry-point template, with no refs/ directory present), and three referenced deep-dive files (root-cause-tracing.md, defense-in-depth.md, condition-based-waiting.md) are absent from the bundle — noted as merged/archived to git history — so navigation pointers are partly broken and the actual deep content is unavailable at any level.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 concise, third-person, and explicit: it states concrete capabilities, an explicit "Use when" trigger set, a "Not for" scope guard, and a defined output artifact. It answers what, when, and how-to-distinguish cleanly with no fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "根因调查 → 模式分析 → 假设验证 → 修复" and a concrete "Bug report(5件套)+ 根因 + 修复(含回归测试)" output, matching the score-3 anchor of several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (systematic bug localization pipeline + 5-piece report output) and when ("Use when: 遇到 bug、测试失败、unexpected behavior") with an explicit trigger clause, plus a "Not for" guard.

3 / 3

Trigger Term Quality

Natural trigger terms users would actually say are covered: "bug", "报错", "test failure", "unexpected behavior", plus the explicit "Use when" clause; good coverage, not jargon.

3 / 3

Distinctiveness Conflict Risk

Clear debugging niche with distinct triggers and an explicit "Not for: 新功能开发、重构、已知原因的简单修复" boundary that prevents overlap with tdd/quality-gate, making conflict unlikely.

3 / 3

Total

12

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
zts212653/clowder-ai
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.