CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-debug

Diagnosis loop for bugs and failing behavior. Use when asked to debug or fix failing or slow behavior.

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

92%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 is an exceptionally well-engineered orchestration layer: a five-phase workflow with explicit gates, escalation thresholds, and routing rules, deferring all detail to six clearly signaled, one-level-deep references that all exist. Its only weakness is minor — a few justification passages in the Routing section could be trimmed for token efficiency.

DimensionReasoningScore

Conciseness

The body is dense, rule-only prose with no explanation of concepts Claude already knows, matching 'efficient; minor instances of over-explanation that could be trimmed'. Justification passages (the rationale for the two handoff questions, the host output-truncation aside) keep it from a 5, but nothing reads as padding, so it is well above 3.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: exact commands ("git checkout -b <name>", "git rev-parse --abbrev-ref origin/HEAD" with the origin/-prefix-stripping rule), exact status enum spellings with a never-rename rule, a copy-paste Debug Summary template, and numbered fix-choice options. Concrete specifics cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

"Five phases in order: 0 Triage -> 1 Investigate -> 2 Root Cause -> 3 Fix -> 4 Handoff" with explicit validation gates ("do not proceed to Phase 3 until you can explain the full chain... with no gaps"), error-recovery feedback loops ("2-3 hypotheses exhausted... or 3 failed fix attempts, means diagnose why"), and a pre-commit preview check. Not 4: checkpoints and recovery loops are explicit at every stage, including destructive commit/push routing.

5 / 5

Progressive Disclosure

Six one-level-deep references, all verified present on disk, each signaled at the exact point of need ("Read references/fix.md before editing any file", "read references/pipeline-mode.md and follow it") with a stated summary of its contents, and an explicit body/reference split ("None of that appears in this body"). The scripts/packs-resolve.py helper is reached only via fix.md, which is normal bundle structure, not a nested reference chain — matching the top anchor.

5 / 5

Total

19

/

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 is concise, in third person, and pairs a clear what with an explicit 'Use when' trigger clause. Its main weakness is that the 'what' covers only the diagnosis half of the skill and the trigger vocabulary misses several common synonyms (error, broken, crash, test failure).

Suggestions

State the full capability set in the 'what' clause, e.g. "Diagnoses root causes of bugs and failing or slow behavior, then applies test-first fixes with structured handoff" — this would lift both specificity and completeness.

Broaden trigger coverage with natural synonyms users actually say: "Use when asked to debug, fix a bug, investigate an error, a crash, a broken feature, a failing test, or slow behavior."

Consider naming the deliverable (root-cause diagnosis with file:line evidence) to sharpen distinctiveness against generic fix-it or code-review skills.

DimensionReasoningScore

Specificity

"Diagnosis loop for bugs and failing behavior" names the domain and a single concrete action (diagnosis), matching the anchor for 1-2 concrete actions without comprehensive coverage. It omits the fix, test-first, and handoff halves of the skill entirely, so it cannot score 4; it is more than a bare domain label, so it is above 2.

3 / 5

Completeness

Both what ("Diagnosis loop for bugs and failing behavior") and an explicit when ("Use when asked to debug or fix failing or slow behavior") are present. It falls short of 5 because the 'what' under-describes the skill — fixing, verification, and handoff are never mentioned.

4 / 5

Trigger Term Quality

"Use when asked to debug or fix failing or slow behavior" captures the most natural trigger phrasings (debug, fix, failing, slow), matching good coverage with a few natural terms missing. It is not 5 because common synonyms users say — "error", "broken", "crash", "test failure" — are absent.

4 / 5

Distinctiveness Conflict Risk

The trigger carves a clear debugging niche that is mostly distinct with only minor overlap risk against performance or test-related skills. Not 5: "fix failing or slow behavior" is broad enough to overlap with adjacent skills (e.g., performance tuning or CI-fix skills).

4 / 5

Total

15

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

EveryInc/compound-engineering-plugin

Path

skills/ce-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.