CtrlK
BlogDocsLog inGet started
Tessl Logo

systematic-debugging

遇到任何 bug、测试失败或异常行为时使用,在提出修复方案之前执行

59

Quality

70%

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 ./skills/systematic-debugging/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 delivers a strongly sequenced, validated debugging workflow with executable instrumentation examples and excellent feedback loops, but it suffers from redundant restatement of the 3-fail rule and references auxiliary files that are not present in the bundle.

Suggestions

Provide the referenced bundle files (root-cause-tracing.md, defense-in-depth.md, condition-based-waiting.md) or remove the dangling references so progressive disclosure is not broken.

Consolidate the '3+ failed fixes → question architecture' guidance into a single canonical statement instead of restating it in phase 4, the red-lines section, and the excuses table.

Trim or fold the 常见借口 table into the existing 红线 section to reduce repetition of the same anti-patterns.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining basics Claude already knows, but the '3+ failed fixes → question architecture' rule is repeated four times and the 常见借口 table rephrases the red-lines section, so it could be tightened.

3 / 5

Actionability

Concrete, executable guidance is present (bash instrumentation snippets like `env | grep IDENTITY`, `security find-identity -v`, `codesign --sign`, plus specific hypothesis phrasing and named skills like `superpowers:test-driven-development`), with minor gaps from references to non-existent files.

4 / 5

Workflow Clarity

Four phases are explicitly sequenced with a gate between each, validation checkpoints (test passes? other tests broken?), feedback loops (fix fails → <3 attempts back to phase 1, ≥3 question architecture), and a per-phase cheat sheet with pass criteria — matching 'clear sequence with explicit validation, feedback loops, and checklists.'

5 / 5

Progressive Disclosure

The SKILL.md is well-sectioned and the 辅助技术 references (root-cause-tracing.md, defense-in-depth.md, condition-based-waiting.md) are clearly signaled one level deep, but none of those referenced files exist in any bundle directory, so the disclosed content is missing.

3 / 5

Total

15

/

20

Passed

Description

70%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 provides a clear, explicit trigger condition with natural terms and a distinct debugging niche, but it prescribes a temporal rule rather than naming the skill's concrete capabilities, leaving the 'what' somewhat implicit.

Suggestions

Add a brief clause naming what the skill actually does, e.g., '系统地排查根本原因' (systematically investigate root causes), so the capability is explicit rather than only implying it via 'execute before proposing a fix'.

Expand trigger terms with common synonyms users say (报错, 崩溃, error, 出错) to improve natural keyword coverage.

Tighten '异常行为' with more specific examples (e.g., 性能退化、集成异常) to reduce overlap with general diagnostic skills.

DimensionReasoningScore

Specificity

The description names the domain ("bug、测试失败或异常行为") and one concrete behavioral directive ("在提出修复方案之前执行"), but does not enumerate the skill's actual capabilities (e.g., root-cause investigation, hypothesis testing), so it matches 'names domain and 1-2 concrete actions, not comprehensive.'

3 / 5

Completeness

It has an explicit and specific 'when' ("遇到任何 bug、测试失败或异常行为时使用") plus a behavioral 'what' (run before proposing a fix); the 'what' could name the actual capability more concretely, matching 'both present, when could be more specific.'

4 / 5

Trigger Term Quality

Natural trigger terms a user would say are present ("bug", "测试失败", "异常行为"), giving good coverage, though common synonyms like 报错, 崩溃, or error are missing.

4 / 5

Distinctiveness Conflict Risk

Debugging before fixing is a clear niche with distinct triggers, but "异常行为" is somewhat broad and could overlap with general diagnostic or testing skills, so it is mostly distinct with minor overlap risk.

4 / 5

Total

15

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
jnMetaCode/superpowers-zh
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.