cli-skill-collector

Detect installed CLI coding tools (Claude Code, Codex, Cursor, Copilot, Cline and more), search GitHub for matching agent skills, and install them to the detected tools via OmniRoute's built-in APIs.

Quality

61%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/cli-skill-collector/SKILL.md

Quality

Content

56%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 curated workflow portion is executable and well-sequenced with verification, but the large auto-generated subcommand reference is padded, duplicated, and partly broken, dragging down conciseness and structure.

Suggestions

De-duplicate and trim the subcommand reference (config list/get/set each appear twice; many entries have no description), and fix the truncated 'config opencode' line.

Move the bulk of the subcommand API reference into a separate references file and link to it from SKILL.md to improve progressive disclosure.

Replace placeholder examples like `omniroute config get <tool>` with at least one realistic concrete argument so examples are truly copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The auto-generated subcommand section is heavily padded with repeated boilerplate ('Example:' + literal `omniroute <cmd>` blocks), duplicated entries (config list, config get, config set appear twice), several subcommands with no description, and a truncated sentence ('Generate OpenCode config (alias for '), making it noticeably verbose.	2 / 5
Actionability	The curated workflow provides copy-paste-ready curl commands, JSON request/response examples, install-path mappings, and verification commands; only minor gaps (placeholder <tool>/<key> args and the broken config opencode text) prevent a 5.	4 / 5
Workflow Clarity	The curated content lays out a clear Detect → Review → Install → Verify sequence with an explicit verification step (Step 4) and a combined quick-start script, with only minor validation gaps keeping it below 5.	4 / 5
Progressive Disclosure	The body has section headers but inlines a long flat subcommand reference that would be better split into a separate file, and no bundle references exist, so structure is present but not well separated.	3 / 5
	Total	13 / 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, naming concrete actions and natural tool keywords, but it omits any explicit 'when to use' trigger guidance, which caps its completeness.

Suggestions

Append a 'Use when...' clause (e.g., 'Use when the user wants to discover or install agent skills for their coding CLIs') to satisfy the completeness 'when' requirement.

Add common synonyms/file markers users might say (e.g., 'SKILL.md repos', 'agent rules') to broaden trigger-term coverage toward 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Detect installed CLI coding tools', 'search GitHub for matching agent skills', and 'install them to the detected tools via OmniRoute's built-in APIs' — with only minor coverage gaps, matching the 'lists several specific actions' anchor.	4 / 5
Completeness	Provides a clear 'what' (detect, search, install) but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('CLI coding tools', 'Claude Code, Codex, Cursor, Copilot, Cline', 'agent skills', 'GitHub') with good coverage, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (collecting/installing agent skills for coding CLIs via OmniRoute APIs) with named tool triggers, leaving only minor overlap risk with adjacent tooling skills.	4 / 5
	Total	15 / 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: diegosouzapw/OmniRoute
Path: skills/cli-skill-collector/SKILL.md
Commit: 6435f61

Reviewed: about 20 hours 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.