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

54

Quality

63%

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 well-sequenced debugging workflow with strong validation checkpoints and concrete executable diagnostics, scoring high on workflow clarity and actionability. Its main weaknesses are redundant reinforcement of the same anti-guessing message and dangling references to bundle files that are not present in the skill package.

Suggestions

Ship the referenced auxiliary files (root-cause-tracing.md, defense-in-depth.md, condition-based-waiting.md) or inline their key content so the one-level-deep links are not dead ends.

Consolidate the redundant "stop and go back to Phase 1" / "3+ failures = architecture problem" guidance currently spread across 红线, 搭档信号, and 常见借口 to trim token cost.

DimensionReasoningScore

Conciseness

The body is mostly efficient actionable methodology, but the "don't guess / find root cause / 3 failures means architecture problem" message is reinforced across 概述, 铁律, 红线, 搭档信号, and 常见借口 sections with notable redundancy that could be tightened.

3 / 5

Actionability

Concrete numbered steps per phase plus executable bash diagnostics (git diff, env | grep, security find-identity, codesign --verbose=4) give mostly executable guidance, with only minor gaps in the methodological steps.

4 / 5

Workflow Clarity

Four phases are explicitly sequenced with a gate ("你必须完成每个阶段后才能进入下一个"), validation checkpoints (Phase 3 step 3, Phase 4 step 3), feedback loops (validate → new hypothesis; 3-failures → question architecture), and a 速查表 checklist with pass criteria per phase.

5 / 5

Progressive Disclosure

References to root-cause-tracing.md, defense-in-depth.md, and condition-based-waiting.md are well-signaled and one-level-deep, but the references/, scripts/, and assets/ directories do not exist, so navigation leads to dead ends and key techniques (e.g. reverse-tracing) are only summarized inline rather than available in the referenced files.

3 / 5

Total

15

/

20

Passed

Description

56%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, natural trigger for when to use the skill but is thin on what concrete actions it performs, leaning on sequencing rather than capability specifics. It is distinct and unlikely to mis-trigger, yet under-specifies the skill's actual methodology.

Suggestions

Add an explicit 'what' clause naming concrete actions, e.g. '系统化定位根本原因:复现问题、追踪数据流、验证假设后再修复' alongside the existing 'when' trigger.

Broaden trigger-term coverage with synonyms like 错误 (error), 崩溃 (crash), 异常 (exception) so more phrasings surface the skill.

DimensionReasoningScore

Specificity

The phrase "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" names the debugging domain but the only action stated is "execute before proposing a fix", which is generic sequencing rather than concrete capabilities like reproduce, trace root cause, or form hypotheses.

2 / 5

Completeness

The "when" is explicit and strong ("遇到任何 bug、测试失败或异常行为时使用") but the "what" is only weakly implied by "在提出修复方案之前执行" — it gives workflow timing rather than describing what the skill concretely does, so it sits between the what-missing and both-present anchors.

3 / 5

Trigger Term Quality

Natural trigger terms "bug", "测试失败" (test failure), and "异常行为" (abnormal behavior) are terms users would actually say, though common synonyms like error, crash, or exception are missing.

4 / 5

Distinctiveness Conflict Risk

The debugging niche with the "before proposing a fix" framing is mostly distinct from other skills, with only minor overlap risk against general coding skills.

4 / 5

Total

13

/

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.