ce-debug

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

Quality

80%

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

81%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.

A well-structured, highly actionable debugging skill with an explicit phased workflow and validation gates. Its main weaknesses are occasional lawyerly verbosity and two bundle files not surfaced from the body.

Suggestions

Add navigation entries for references/anti-patterns.md and references/investigation-techniques.md in the body (or from a referenced file) so every bundle file is discoverable from the overview.

Tighten the long conditional sentences in the Phase 4 routing (e.g., the branch-push comparison) into shorter declarative rules to reduce token cost without losing precision.

Replace open routing prose like "Establish those however fits the repo in front of you" with one or two concrete checks to close the actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is dense and directive, assuming Claude knows git and debugging rather than explaining them; it is not a 5 because several lawyerly sentences (e.g., the branch-push comparison) and some cross-mode repetition could be trimmed.	4 / 5
Actionability	Concrete commands (`git checkout -b <name>`, `git rev-parse --show-toplevel`, `git status --short`), an exact status enum, and a copy-paste Debug Summary template give mostly executable guidance; not a 5 because some routing prose is conditional ("Establish those however fits the repo") and the bulk of executable detail is delegated to references.	4 / 5
Workflow Clarity	Five phases are sequenced in order with explicit validation gates (causal-chain gate before Phase 3, fix-choice gate) and feedback loops (failed-fix rule, 2-3-hypothesis escalation), matching the top anchor for clear sequence with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	The body is an overview with well-signaled, one-level-deep references (investigate.md, fix.md, pipeline-mode.md, return-to-caller.md, post-fix-handoff.md), all verified to exist; not a 5 because anti-patterns.md and investigation-techniques.md are present in the bundle but unreachable from the body, a navigation gap.	4 / 5
	Total	17 / 20 Passed

Description

78%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.

A tight, third-person description that answers both what and when with natural trigger terms. It is slightly under-comprehensive on concrete actions and has minor overlap with performance skills via 'slow behavior'.

Dimension	Reasoning	Score
Specificity	"Diagnosis loop for bugs and failing behavior" names the domain and a couple of actions (diagnose, fix) but frames the work as a process rather than listing multiple concrete actions, matching the anchor 'names domain and 1-2 concrete actions, but not comprehensive'; it is not a 4 because it does not enumerate several specific actions.	3 / 5
Completeness	It explicitly answers both what ("Diagnosis loop for bugs and failing behavior") and when ("Use when asked to debug or fix failing or slow behavior") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"debug or fix failing or slow behavior" and "bugs" are natural phrases users say, giving good keyword coverage; not a 5 because common synonyms (e.g., 'error', 'crash', 'stack trace', 'broken') are absent.	4 / 5
Distinctiveness Conflict Risk	Debugging is a clear niche with distinct triggers, but "slow behavior" pulls in performance-tuning territory, creating minor overlap risk with closely related skills; not a 5 because of that overlap and not a 3 because the niche is otherwise well-bounded.	4 / 5
	Total	16 / 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: 082c83e

Reviewed: 3 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.