find-skills

Run this BEFORE any package install (pip / npm / apt / brew / cargo / gem / go install) you would otherwise execute via the exec tool — including when the user asks for a deliverable that needs third-party libraries (PDF generation, image processing, scrapers, dashboards, charts, OCR, audio/video, …). It searches the open agent-skill ecosystem (skills.sh) for an installable skill that already does the job; only fall back to direct package install if find-skills returns no credible match. Also covers explicit "find a skill for X" / "how do I do X" / "is there a skill that can..." requests, and any time the user expresses interest in extending agent capabilities.

Quality

85%

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

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 body is highly actionable with executable commands and a clear step sequence, but it leans verbose in its persuasive passages and lacks an explicit install/search failure-recovery loop. Progressive disclosure is good for a single-file skill but the document is longer than necessary.

Suggestions

Tighten the install-count rationale in Steps 4-5: the 'install counts in the high tens are FINE' point is made three times across Step 4, Step 5, and the 20-install example — collapse to one statement.

Add an explicit feedback loop in Step 3 or 6 for failed searches/installs (e.g. 'if `npx skills find` returns nothing on-topic, narrow the query or fall through to direct package install with justification').

Trim repeated anti-reinvention warnings: Step 7 and the anti-pattern section both forbid `npm install -g <library>` reimplementations; consolidate so the directive appears once.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but several padded rhetorical sections (e.g. the install-count justification paragraphs in Steps 4-5 and the repeated 'DO NOT reimplement' emphasis) restate the same point multiple times and could be tightened.	3 / 5
Actionability	Fully executable guidance throughout: concrete `npx skills find`/`add` commands with the ANSI-striping sed pipe, copy-paste example phrasings, and exact install flags (`-g -y`) plus file paths to inspect.	5 / 5
Workflow Clarity	Clear seven-step sequence with explicit decision points (check leaderboard, search, pick, install, use) and a verification step (read the installed SKILL.md before using); not quite 5 because there is no explicit error-recovery feedback loop for a failed search or failed install.	4 / 5
Progressive Disclosure	Well-organized sections with clear headers and an inline command table; the body is a single self-contained overview with no bundle files, so there are no multi-level references to navigate, but it is slightly long for a monolithic skill doc which keeps it from 5.	4 / 5
	Total	16 / 20 Passed

Description

95%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 strong: it explicitly defines what the skill does and when to use it, packs in natural trigger terms and concrete package-manager examples, and carves out a distinct niche. Minor specificity gap is the only thing keeping it from being perfect.

Dimension	Reasoning	Score
Specificity	Names the concrete actions (searches the skills ecosystem for an installable skill, then installs/falls back to direct package install) but the search-then-install actions are somewhat generic rather than a comprehensive list of distinct operations; not quite the multi-action coverage of a 5.	4 / 5
Completeness	Explicitly answers both 'what' (searches skills.sh for an installable skill that already does the job, only falls back to direct install if no credible match) and 'when' (before any package install, including when a deliverable needs third-party libraries, and explicit find-a-skill requests).	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including concrete package managers (pip/npm/apt/brew/cargo/gem/go install), deliverable examples (PDF generation, image processing, scrapers), and natural phrasings like 'find a skill for X', 'how do I do X', 'is there a skill that can...'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (pre-install skill discovery) with distinct triggers (package install interception) and minimal conflict risk; unlikely to fire for the wrong skill.	5 / 5
	Total	19 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: fastclaw-ai/fastclaw
Path: internal/agent/bundled_skills/find-skills/SKILL.md
Commit: dcd4ccb

Reviewed: 6 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.