skill-debug

Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-debug/SKILL.md

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body's core strength is a clearly sequenced four-phase workflow with explicit validation and feedback loops. It is held back by significant redundancy across its self-regulation/rationalization sections, template-style code examples, and a monolithic structure with no progressive disclosure to separate reference files.

Suggestions

Collapse the three overlapping self-regulation mechanisms (3-strike rule, WTF score, Strategy Rotation) and the duplicate Red Flags / Common Rationalizations / Anti-rationalization sections into a single concise "Stop conditions" section to remove repetition.

Move the Claude-Octopus integration table, multi-agent orchestration, and detailed WTF scoring weights into a separate reference file and link to it from SKILL.md so the main file is a lean overview with one-level-deep references.

Replace the placeholder `echo` instrumentation and `orchestrate.sh` examples with concrete, copy-paste-ready snippets, or mark them explicitly as illustrative templates with the variables a user must substitute.

Dimension	Reasoning	Score
Conciseness	The body is actionable but padded with repetition: the 15-30-min vs 2-3-hours claim appears twice, "Red Flags" and "Common Rationalizations" overlap, and three overlapping self-regulation mechanisms (3-strike rule, WTF score, Strategy Rotation) restate the same idea; it also restates basics like "Read stack traces completely."	2 / 3
Actionability	It includes concrete executable commands (git diff/log, the freeze-dir script) and explicit numeric thresholds, but a substantial portion is descriptive process prose and the multi-component `echo` instrumentation and multi-agent `orchestrate.sh` blocks are template/placeholder code rather than copy-paste-ready.	2 / 3
Workflow Clarity	The four phases are explicitly sequenced with validation checkpoints throughout: a Phase 3 hypothesis-verification table, a Phase 4 fix-verification checklist, the 3-strike action table, and revert-detection feedback loops, matching the anchor 3 example.	3 / 3
Progressive Disclosure	The skill is a single ~360-line monolithic SKILL.md with clear section headers but no content split into one-level-deep reference files; the only referenced paths are external host/plugin files rather than signaled skill bundles, so content that could be separated (octopus integration, WTF scoring) stays inline.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 well-formed: it gives an explicit what-and-when trigger clause with natural language a user would say. Its main weakness is that it names only one action and the trigger surface is broad enough to risk overlap with adjacent skills.

Dimension	Reasoning	Score
Specificity	"Debug issues methodically" names the domain and a concrete action, but it is a single action rather than the multiple specific concrete actions (e.g. extract/fill/merge) that anchor 3 requires.	2 / 3
Completeness	It explicitly answers both what ("Debug issues methodically") and when ("use when stuck on errors, test failures, or unexpected behavior") with an explicit "Use when" clause, matching the anchor 3 example.	3 / 3
Trigger Term Quality	"use when stuck on errors, test failures, or unexpected behavior" uses natural phrasing a user would actually say, with several distinct trigger terms rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	"Debug issues methodically" carves a debugging niche, but the broad triggers (errors, test failures, unexpected behavior) could overlap with testing or language-specific debugging skills, so it is not a clearly conflict-free niche.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-debug/SKILL.md
Commit: 9f39f0c

Reviewed: 2 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.