tool-discovery

Recommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool). Triggers on: which agent, which skill, what tool should I use, help me choose, recommend agent, find the right tool.

5.26x

Quality

78%

Does it follow best practices?

Impact

100%

5.26x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/tool-discovery/SKILL.md

Quality

Content

78%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 concise and well-structured, with a clear decision flowchart and concrete launch syntax that make the routing workflow actionable. The main weakness is progressive disclosure: the body advertises two reference catalog files that are not present in the bundle, breaking the navigation it sets up.

Suggestions

Create the advertised ./references/agents-catalog.md and ./references/skills-catalog.md (or remove the broken references) so progressive disclosure points to real, navigable material.

Expand the launch examples into fully copy-paste-ready invocations including a sample prompt argument to lift actionability from 4 to 5.

Add a brief fallback/error branch to the decision flowchart (e.g., "if neither catalog matches, ask the user to clarify") to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and table-driven with a compact flowchart and brief tips, adding nothing Claude doesn't already know and with every line earning its place, matching the anchor for an efficient, competence-assuming skill.	5 / 5
Actionability	Provides concrete launch syntax ("Skill tool → skill: file-search", "Task tool → subagent_type: python-expert") and a task-type mapping table, but the code blocks are schematic invocation patterns rather than fully copy-paste-ready examples with all arguments, leaving a minor gap below 5.	4 / 5
Workflow Clarity	The Decision Flowchart gives a clear, explicit decision tree (reference/lookup vs reasoning/decisions vs catalogs) that sequences the routing workflow unambiguously, with only minor gaps (no error/fallback branch) keeping it below 5; no destructive or batch operations are involved so the validation cap does not apply.	4 / 5
Progressive Disclosure	The body is well-sectioned and points to two one-level-deep catalogs ("./references/agents-catalog.md", "./references/skills-catalog.md"), but those reference files do not exist in the bundle, so the references are dead rather than usable, which is more than a minor organization gap.	3 / 5
	Total	16 / 20 Passed

Description

78%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 clearly answers both what the skill does and when to trigger it, with strong natural trigger-term coverage and a distinct routing purpose. Its main weakness is specificity — the core action ("recommend") is generic and coverage is framed as "any task" rather than listing concrete capabilities.

Suggestions

Replace the generic "for any task" framing with 2-3 concrete capabilities (e.g., "Match a request to the right skill or agent, explain the heavyweight-vs-lightweight tradeoff, and point to the full catalog") to lift specificity from 3 toward 4-5.

Add a few common-synonym trigger terms (e.g., "which tool", "pick a skill", "should I use an agent") to push trigger-term quality from 4 to 5.

Narrow the scope or add a discriminator phrase to reduce overlap risk with domain-specific skills, supporting a 5 on distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ("Recommend the right agents and skills") plus the heavyweight/lightweight distinction, but the action set is generic ("for any task") and not comprehensive, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	Clearly states what it does ("Recommend the right agents and skills for any task. Covers both heavyweight agents... and lightweight skills...") and explicitly when to use it ("Triggers on: which agent, which skill..."), answering both what and when with concrete triggers.	5 / 5
Trigger Term Quality	Lists several natural trigger phrases a user would actually say ("which agent, which skill, what tool should I use, help me choose, recommend agent, find the right tool") with good coverage, missing only a few common synonyms to reach 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a distinct routing niche between agents and skills with specific trigger phrases, though the broad "for any task" scope creates minor overlap risk with domain-specific skills, keeping it just below 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NeverSight/skills_feed
Path: data/skills-md/0xdarkmatter/claude-mods/tool-discovery/SKILL.md
Commit: 2f57aec

Reviewed: about 22 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.