manage-skills

Manage the user's shared agent-skill library via skills-manager-cli — install, update, remove, deploy or undeploy skills per agent, manage presets, organize tags, search, and adopt existing skills. Use this whenever the user wants Claude Code, Codex, Cursor, or another agent to gain or lose a skill, wants to organize the central library, or asks what is installed or deployed. Prefer this over direct agent-folder installs because Skills Manager preserves source metadata, preset membership, updates, and cross-agent deployment state.

Quality

94%

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

Quality

Content

88%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 high-quality, executable command reference with strong workflow sequencing and validation gates. Its only structural weakness is that everything is inline in one monolithic file rather than split across one-level-deep reference files.

Suggestions

Move the bulk command catalogs (Tag, Presets, Adopt variants) into a references/COMMANDS.md and keep SKILL.md as an overview with one-level-deep links to improve progressive_disclosure.

Tighten the held_back_removals narrative in the Update section to a few lines plus a JSON example, trimming the longest paragraphs for token efficiency.

Consider a short 'Quick start' section near the top so the single most common flow (install + deploy) is reachable before the full command inventory.

Dimension	Reasoning	Score
Conciseness	Dense and accurate with no padding of concepts Claude already knows, but at 268 lines some sections (e.g. the held_back_removals narrative, adopt subpath variants) could be tightened without losing clarity.	4 / 5
Actionability	Copy-paste-ready commands throughout with flags, JSON/jsonc output samples, and deterministic ref-resolution rules covering the common cases — 'skills-manager-cli skills install vercel-labs/agent-skills@react-best-practices' is fully executable.	5 / 5
Workflow Clarity	Workflows are explicitly sequenced with validation checkpoints: '--dry-run' before bulk remove/deploy, 'check' before 'update', 'Always verify after install with skills list', and an error-recovery path for held_back_removals.	5 / 5
Progressive Disclosure	Sections are well-organized and clearly signaled, but all content lives inline in one 268-line SKILL.md with no references/scripts/assets bundle files to offload the command catalog or reference detail.	4 / 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.

The description is exemplary: it enumerates concrete capabilities, supplies natural trigger phrasing with named agents, answers both what and when explicitly, and draws a sharp boundary against adjacent skills. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'install, update, remove, deploy or undeploy skills per agent, manage presets, organize tags, search, and adopt existing skills' — giving comprehensive coverage of the CLI's capability surface.	5 / 5
Completeness	Explicitly answers both 'what' (manage the shared agent-skill library via skills-manager-cli) and 'when' ('Use this whenever the user wants…'), with concrete trigger phrases rather than weak implication.	5 / 5
Trigger Term Quality	Captures how users naturally phrase the need — 'wants Claude Code, Codex, Cursor, or another agent to gain or lose a skill', 'asks what is installed or deployed', 'organize the central library' — with concrete agent names and common synonyms.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche ('shared agent-skill library via skills-manager-cli') and even names the disambiguation ('Prefer this over direct agent-folder installs'), minimizing overlap with adjacent skills like find-skills.	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: xingkongliang/skills-manager
Path: skills/manage-skills/SKILL.md
Commit: e2e797c

Reviewed: 5 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.