CtrlK
BlogDocsLog inGet started
Tessl Logo

pleaseai/please-plugins

Auto-detect project dependencies and recommend matching Claude Code plugins from the pleaseai marketplace

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

75%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 a well-structured, actionable guide with a clear five-step workflow and concrete commands throughout. It is concise and avoids over-explanation; the main room for improvement is converting the qualitative ranking step into more concrete criteria and optionally splitting the categories table into a reference file.

Suggestions

Make the Match/Rank step more actionable by giving a concrete scoring heuristic or tie-break rule instead of only qualitative descriptions of match types.

Consider moving the Plugin Categories table into a references file (e.g. references/categories.md) and linking to it, keeping the main body as a lean overview.

Add an explicit verification checkpoint after Step 2 (e.g. confirm at least one match was found before proceeding to ranking) to tighten the workflow sequence.

DimensionReasoningScore

Conciseness

The body is efficient and mostly assumes Claude's competence, using short steps and concrete commands rather than explaining concepts Claude already knows; minor phrases like 'The marketplace provides two layers of discovery' could be trimmed but the whole is not noticeably verbose, so it sits above the 'mostly efficient' anchor and below fully lean.

4 / 5

Actionability

It provides concrete, copy-paste-ready commands (cat, find, grep, jq, claude plugin install) with clearly marked placeholders, but the Match/Rank step is qualitative guidance rather than executable code, leaving minor gaps consistent with the 'mostly executable' anchor.

4 / 5

Workflow Clarity

Five steps are clearly sequenced (read catalog, search skills, match/rank, present, offer install) with a 'When No Plugin Exists' fallback and an explicit dedup instruction; there are no destructive/batch operations requiring validation caps, but explicit verification checkpoints are mostly implicit, fitting the 'clear sequence with most checkpoints' anchor.

4 / 5

Progressive Disclosure

The body is well-organized into clear sections with no nested external references and no bundle files to navigate; the sizable inline Plugin Categories table is a quick-reference block that could arguably live in a separate file, placing this just below the ideal 'one-level-deep, fully split' anchor.

4 / 5

Total

16

/

20

Passed

Description

90%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.

This is a strong description: it clearly states the skill's purpose and provides rich, natural trigger phrases covering explicit and implicit invocation. The only mild limitation is that the 'what' is limited to two verbs (discover, install), keeping specificity at the midpoint rather than the top.

DimensionReasoningScore

Specificity

The description names the domain (Claude Code plugins / pleaseai marketplace) and two actions ('discover and install'), which matches the 'names domain and 1-2 concrete actions' anchor; it is not below (only minimal actions) nor above (no broader action coverage beyond discover/install).

3 / 5

Completeness

It explicitly answers both 'what' (discover and install plugins from the marketplace) and 'when' (multiple concrete 'Use when...' trigger phrases), matching the anchor that requires both with concrete triggers.

5 / 5

Trigger Term Quality

It includes a comprehensive set of natural phrases users would actually say ('how do I do X', 'find a plugin for X', 'is there a plugin that can...', 'recommend a plugin', 'what plugins are available') plus synonyms and an implicit-trigger case, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (Claude Code plugins from the pleaseai marketplace) with distinct, specific triggers, giving minimal conflict risk with other skills; it is clearly distinguishable rather than merely 'mostly distinct'.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents