skill-doctor

Environment diagnostics — check providers, auth, config, hooks, scheduler, and more

Quality

68%

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-doctor/SKILL.md

Quality

Content

71%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 content is highly actionable with executable resolver and remediation code and a clear sequenced workflow, but it is a long monolithic file that underuses progressive disclosure and could be tightened.

Suggestions

Move the reference-style sections (Hook Profile, Intensity Profile, Project Tier Hint, Remote Session Checks, Runtime Context) into a separate reference file and link to it from SKILL.md to improve progressive disclosure and conciseness.

Add an explicit verify step after remediation (e.g., re-run `doctor --verbose` to confirm the issue is resolved) to close the workflow feedback loop.

Reduce repetition of the resolver by extracting it once and referencing the snippet, trimming length without losing executability.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient commands and tables without explaining concepts Claude already knows, but at ~357 lines with several reference-style sections (Hook Profile, Intensity Profile, Tier Hint, Remote Session, Runtime Context) and a repeated resolver pattern, it could be tightened.	3 / 5
Actionability	Provides a complete, copy-paste-ready resolver script, exact per-category commands, and fully executable AskUserQuestion remediation blocks covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced five-step process with an explicit MANDATORY remediation step and error handling in the resolver (exit 1 if not found), though it lacks an explicit re-run-doctor-to-verify checkpoint after fixes.	4 / 5
Progressive Disclosure	Internal section structure is well organized with headers and tables, but no bundle files exist and all content (including reference tables that could live in separate files) is inlined in a single 357-line SKILL.md with no one-level-deep references.	3 / 5
	Total	15 / 20 Passed

Description

66%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 specific and reasonably distinctive, listing concrete diagnostic categories, but it omits an explicit "Use when" trigger clause (capping completeness) and relies on the separate trigger field for the most natural user phrases.

Suggestions

Add an explicit "Use when..." clause to the description itself (e.g., "Use when something isn't working or after installing/updating the plugin") so completeness is not capped at 3.

Fold one or two of the most natural trigger phrases ("doctor", "health check", "is everything working") into the description so it scores on its own rather than depending on the trigger field.

Replace the vague "and more" with the remaining categories or a bounded phrase to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("Environment diagnostics") and lists several concrete check areas ("providers, auth, config, hooks, scheduler"), but the trailing "and more" leaves coverage slightly open rather than comprehensive.	4 / 5
Completeness	Provides a clear "what" but no "Use when..." clause in the description itself; per the rubric, a missing explicit trigger guidance caps completeness at 3 even though the trigger field supplies it elsewhere.	3 / 5
Trigger Term Quality	Includes natural terms like "diagnostics", "check providers", "check auth", "check hooks", and "scheduler", but misses the most natural user phrases ("doctor", "health check", "is everything working") which only appear in the separate trigger field.	4 / 5
Distinctiveness Conflict Risk	The specific check categories (providers, auth, hooks, scheduler) carve a mostly distinct niche, though without naming the Claude Octopus plugin there is minor overlap risk with generic diagnostics skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-doctor/SKILL.md
Commit: 6a1fd2b

Reviewed: 1 day 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.