dependency-doctor

Checks requirements.txt, pyproject.toml, and package.json dependency manifests for surface-level direct-dependency footguns: standard-library shadowing pins, abandoned backports, unpinned dependencies, and obvious intra-manifest conflicts, plus opt-in PyPI yanked releases. Use when the user asks to check a manifest for dependency problems, asks why dependencies won't install or whether anything is wrong with their dependencies, wants a dependency autopsy, or suspects dependency manifest rot. Runs offline by default as a local tool for the user's own project, not repository CI.

Quality

93%

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

Quality

Content

86%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 body with executable commands, a documented report format, and a validation feedback loop after edits. Minor conciseness and explicit-iteration gaps keep it just below the top on two dimensions.

Suggestions

Tighten the 'When to use' / 'When not to use' lists — they overlap the frontmatter description and could be shortened to the non-obvious cases only.

Make the post-edit feedback loop explicit: state what to do if the rerun of the offline diagnosis surfaces new findings (iterate: fix → rerun until clean).

Add a one-line note on how findings should be ordered/presented when both online yank findings and offline findings coexist, to remove ambiguity in the 'Explain the diagnosis' step.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence, but the 'When to use' / 'When not to use' lists partially restate what the description already covers and could be trimmed slightly. Not below 4 because no concepts Claude already knows are over-explained.	4 / 5
Actionability	Provides copy-paste-ready commands ('python3 scripts/dep_doctor.py /path/to/requirements.txt --json' and the --online variant), a concrete JSON report shape, and a specific enumerated list of fix actions covering the common cases.	5 / 5
Workflow Clarity	Clear sequence (choose manifest → run offline diagnosis → explain → optional online check → offer fixes) with an explicit validation feedback loop (rerun offline diagnosis + project install/test command after approved edits). Held at 4 rather than 5 because the error-recovery iteration on a failed rerun is implied rather than spelled out.	4 / 5
Progressive Disclosure	Well-organized overview with clearly signaled, one-level-deep references to real bundle files ('Read references/dependency-pitfalls.md', a 'Files' section listing scripts/dep_doctor.py and references/dependency-pitfalls.md), both of which exist on disk. Easy navigation with no nested references.	5 / 5
	Total	18 / 20 Passed

Description

100%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 strong, specific description that clearly defines both capability and trigger conditions with natural user language and explicit boundaries. All four dimensions land at the top anchor with no notable gaps.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete, specific checks (standard-library shadowing pins, abandoned backports, unpinned dependencies, intra-manifest conflicts, opt-in yanked releases) across three named manifest formats — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (checks manifests for surface-level direct-dependency footguns) and 'when' ('Use when the user asks to check a manifest for dependency problems...') with concrete trigger phrases, matching the score-5 anchor exactly.	5 / 5
Trigger Term Quality	Includes natural user phrases ('check a manifest for dependency problems', 'why dependencies won't install', 'whether anything is wrong with their dependencies', 'dependency autopsy', 'dependency manifest rot') plus file extensions (requirements.txt, pyproject.toml, package.json) and synonyms — comprehensive coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (direct, surface-level manifest footguns) and actively carves boundaries against adjacent skills ('not a full vulnerability audit', 'not repository CI'), minimizing conflict risk.	5 / 5
	Total	20 / 20 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: Shubhamsaboo/awesome-llm-apps
Path: agent_skills/dependency-doctor/SKILL.md
Commit: 9848ec8

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.