ce-debug

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

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ce-debug/SKILL.md

Quality

Content

77%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 a well-orchestrated, multi-phase debug workflow with strong sequencing, explicit gates, and clean progressive disclosure into real reference files. Its only meaningful weakness is conciseness: several justificatory asides and repeated consequence warnings could be trimmed without losing clarity.

Suggestions

Tighten the long parenthetical justifications (e.g. the origin/HEAD prefix-stripping aside) into a single terse clause.

Reduce repeated consequence-emphasis tails such as 'Skipping the read ships an unreviewed fix, lets review reach into unrelated branch work...' — the directive to read the reference already carries the weight.

Consolidate the multiple `mode:pipeline` override callouts so the non-interactive path is stated once and referenced rather than restated in each phase.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no explaining of git, branches, or PRs), but several long parenthetical justifications and repeated consequence-emphasis passages (e.g. the origin-prefix stripping aside, the 'skipping the read ships an unreviewed fix' tail) could be tightened.	3 / 5
Actionability	Concrete commands and templates are present (`git rev-parse --show-toplevel`, `git checkout -b <name>`, the Debug Summary block, exact status spellings), but much of the body is conditional routing logic rather than direct executable steps, with the core fix mechanics delegated to references.	4 / 5
Workflow Clarity	Five phases (0 Triage → 4 Handoff) are explicitly sequenced with hard gates (causal-chain gate, Phase 2 fix-choice gate) and explicit validation/feedback loops (escalation table, failed-fix rule, validate-before-edit) for the risky commit/push operations.	5 / 5
Progressive Disclosure	The body is a clear overview that delegates detailed procedures to one-level-deep, well-signaled references (investigate.md, fix.md, pipeline-mode.md, post-fix-handoff.md) — all real files — with mechanics appropriately split out and easy to navigate.	5 / 5
	Total	17 / 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 cleanly answers both what and when with natural trigger terms and a distinct debugging niche. Its main weakness is specificity: it states the overarching action ('diagnosis loop') without naming the concrete operations the skill actually performs.

Suggestions

Expand the 'what' to name 1-2 more concrete actions, e.g. 'Diagnose root cause, apply a test-first fix, and hand off the result for bugs and failing behavior.'

Add a common synonym to the trigger clause such as 'error' or 'broken behavior' to broaden natural-term coverage.

Consider naming the regression-test emphasis to further distinguish this skill from a generic fix helper.

Dimension	Reasoning	Score
Specificity	"Diagnosis loop for bugs and failing behavior" names the domain and one concrete action (diagnosis), but does not enumerate the concrete actions the skill performs (root-cause tracing, test-first fix, handoff), so coverage is not comprehensive.	3 / 5
Completeness	Both halves are explicit — "Diagnosis loop for bugs and failing behavior" (what) and "Use when asked to debug or fix failing behavior" (when) — but the 'what' is terse relative to the anchor example, keeping it just below a 5.	4 / 5
Trigger Term Quality	"debug or fix failing behavior" and "bugs and failing behavior" include natural terms a user would say, but common synonyms like "error", "broken", or "stack trace" are missing.	4 / 5
Distinctiveness Conflict Risk	"Diagnosis loop for bugs" carves a distinct debugging niche with minimal conflict risk against feature-creation skills, though it could overlap with other general fix/triage skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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
Commit: 26bf5b1

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.