CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

debug

Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 presents a clear four-step methodology with actionable checklists and a concrete output template, but the decorative ASCII diagram inflates token cost without adding guidance. Adding an explicit fix-verification step and flattening the diagram would raise workflow clarity and conciseness.

Suggestions

Replace the 24-line ASCII box with a flat numbered list of the four steps and their checkmarks — the box is decorative padding that costs ~20 lines without adding guidance (conciseness).

Add an explicit validation step after FIX, e.g. 'Re-run the reproduction to confirm the fix resolves it; if not, return to Step 3' — this closes the workflow's only checkpoint gap (workflow_clarity).

Trim the Tips section or fold it into the description's trigger examples, since 'share error messages exactly' and 'mention what changed' largely restate content already surfaced (conciseness).

DimensionReasoningScore

Conciseness

The 24-line ASCII box diagram ("│ Step 1: REPRODUCE │ ...") conveys nothing beyond what a flat four-item list would, and the 'Tips' section partly repeats the description's trigger phrases; the rest is efficient, so this sits at 'could be tightened' rather than anchor 4's only-minor-trimming.

3 / 5

Actionability

Concrete per-step checklists ("Check recent changes (deploys, config changes, dependencies)", "Review logs and error messages") plus a copy-paste output template make the guidance mostly executable; directives like "Form hypotheses and test them" remain high-level, keeping it below the fully concrete anchor 5.

4 / 5

Workflow Clarity

Four clearly numbered steps with implicit checkpoints ("Consider side effects and edge cases", "Suggest tests to prevent regression") give a clear sequence with most checkpoints present; the missing explicit 're-run the reproduction to verify the fix' step is the minor validation gap that distinguishes this from anchor 5.

4 / 5

Progressive Disclosure

Sections are well-organized under clear headers with the single external reference (CONNECTORS.md) clearly signaled at the top; at ~90 body lines the under-50-line simple-skill exception does not apply, and the inlined ASCII diagram and full output template are content that could live more granularly, fitting 'good structure with minor organization gaps'.

4 / 5

Total

15

/

20

Passed

Description

96%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 is strong: it states four concrete actions, provides explicit when-to-use guidance with natural trigger phrases, and carves out a recognizable niche. The only weakness is the broad fallback trigger that slightly raises overlap risk with adjacent skills.

DimensionReasoningScore

Specificity

"Structured debugging session — reproduce, isolate, diagnose, and fix" names the domain and four concrete actions spanning the full debugging lifecycle, matching the comprehensive-coverage anchor with no gaps; anchor 4's 'minor gaps' caveat does not apply.

5 / 5

Completeness

The 'what' is explicit (reproduce, isolate, diagnose, fix) and the 'when' is explicit via 'Trigger with an error message or stack trace... or when behavior diverges from expected', matching the anchor with both answers plus concrete trigger phrases.

5 / 5

Trigger Term Quality

"error message or stack trace", "this works in staging but not prod", and "something broke after the deploy" are exactly the natural phrases users say when hitting a bug, going beyond anchor 4 by including colloquial synonyms rather than missing them.

5 / 5

Distinctiveness Conflict Risk

Debugging is a clear niche with distinct error/stack-trace triggers, but the catch-all clause "when behavior diverges from expected and the cause isn't obvious" is a broad net that could overlap adjacent troubleshooting or code-review skills, fitting 'minor overlap risk' rather than anchor 5's minimal conflict risk.

4 / 5

Total

19

/

20

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.

Validation — 14 / 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

anthropics/knowledge-work-plugins

Path

engineering/skills/debug/SKILL.md

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.