related-skills-surfacer

Suggest community skills based on recent activity in other plugins. Checks whether the community has built something relevant to a task and mentions it once, non-intrusively. Use when the user says "is there a community skill for this", "what else is out there", or asks for skill recommendations; also runs passively as part of other plugins' workflows.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./legal-builder-hub/skills/related-skills-surfacer/SKILL.md

Quality

Content

57%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and appropriately compact for a single-file skill, with concrete output templates and decision logic. Its main weaknesses are redundancy between the opening step list and the detailed sections, and an abstract description of the matching step that lacks a concrete procedure.

Suggestions

Remove the redundant 4-step list at the top (or make it a true one-line summary) since its steps are restated verbatim in the sections below, and load the CLAUDE.md path once instead of repeating it three times.

Replace the abstract matching guidance ("keyword overlap", "strong match") with a concrete procedure or scored checklist so Claude knows exactly how to rank and threshold candidate skills.

Tighten the workflow into a single explicit sequence with the decision checkpoints (match threshold → output vs. silent → frequency-limit check → user-control filter) called out as labeled steps rather than split across sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-explanation fluff, but the opening 4-step list duplicates the detailed sections below and the CLAUDE.md path is repeated three times, so it could be tightened; not the lean level-3 case.	2 / 3
Actionability	Provides concrete elements (an exact output template, the `references/surfaced.json` tracking path, user-control settings) but the core matching method stays abstract ("keyword overlap", "strong match") without a concrete procedure, fitting the level-2 anchor.	2 / 3
Workflow Clarity	A sequence exists and there are clear decision points (threshold, no-match→silent, frequency limit), but the top step list is redundant with the body and "Use the workflow below" is circular, leaving the sequence present but checkpoints implicit rather than crisp.	2 / 3
Progressive Disclosure	This is a compact single-file skill with no need for external documentation; its sections (Purpose, How it runs, Load context, The match, Output, Frequency limit, User control) are well-organized and self-contained, meeting the simple-skill allowance for level 3.	3 / 3
	Total	9 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 states a concrete purpose, gives multiple natural trigger phrases, and includes an explicit "Use when" clause covering both what and when. The only weak spot is specificity, where the actions are named but not enumerated in depth.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple of actions ("Suggest community skills", "Checks whether the community has built something relevant", "mentions it once, non-intrusively") but does not enumerate multiple distinct concrete actions, so it falls short of the level-3 anchor.	2 / 3
Completeness	Explicitly answers both what it does (suggest/check/mention community skills) and when to use it via a clear "Use when..." clause with concrete triggers, matching the level-3 anchor.	3 / 3
Trigger Term Quality	Quotes several natural phrasings a user would actually say — "is there a community skill for this", "what else is out there", "asks for skill recommendations" — giving good coverage of trigger variations.	3 / 3
Distinctiveness Conflict Risk	It occupies a clear niche (community-skill surfacing tied to the legal-builder-hub) with distinct triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	11 / 12 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-for-legal
Path: legal-builder-hub/skills/related-skills-surfacer/SKILL.md
Commit: 4a6c651

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.