gap-surfacer

Reference: shared gap- and comment-tracker framework backing /regulatory-legal:gaps and /regulatory-legal:comments. Tracks open policy gaps with remediation status, ingests gaps from policy-diff, surfaces what's open and aging, routes to owners, and notifies gap owners via Slack with per-send confirmation. Loaded by the gaps and comments skills before doing substantive work.

Quality

65%

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 ./regulatory-legal/skills/gap-surfacer/SKILL.md

Quality

Content

77%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 highly actionable and workflow-clear, with concrete templates, exact paths, and strong validation checkpoints around irreversible Slack sends and compliance certifications. Its main weaknesses are repeated per-send-confirmation phrasing that could be tightened and a monolithic structure that does not leverage the existing bundle reference files for progressive disclosure.

Suggestions

State the per-send confirmation rule once at the top and reference it briefly ('per the per-send gate above') in each mode instead of restating the full instruction repeatedly.

Move the status-report markdown template and the full tracker schema into reference files under references/ and link to them from the body, signaling the existing bundle files that are currently unlinked.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific content Claude does not already know, but the phrase 'wait for per-send confirm before sending' is repeated ~6 times across modes and the citation-verification footer and consequential-action gate could be tightened.	2 / 3
Actionability	Provides exact tracker file paths, a complete YAML schema with field semantics, copy-ready Slack message templates, explicit CLI commands ('/regulatory-legal:gaps --close GAP-001'), and precise cadence rules (30/21 days, 7-day dedup) — fully actionable for an instruction-only skill.	3 / 3
Workflow Clarity	The per-send confirmation is a numbered sequence with explicit validation checkpoints for batch/destructive Slack sends, and feedback loops (reminder-timestamp dedup, rule-status re-verification before overdue escalation) are present.	3 / 3
Progressive Disclosure	The body is well-sectioned but monolithic — the tracker schema, Slack templates, and status-report template are all inline; the existing bundle references (references/gap-tracker.yaml, references/comment-tracker.yaml) are not linked or signaled from the body.	2 / 3
	Total	10 / 12 Passed

Description

52%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 specific and distinctive, naming concrete actions and the exact skills it backs, but it lacks natural user trigger terms and an explicit 'Use when...' clause because it is a non-user-invocable reference framework. Specificity and distinctiveness are strong; trigger-term quality and completeness are the weak spots.

Suggestions

Add an explicit 'Use when...' clause (or equivalent trigger guidance) even for a reference skill, e.g. 'Loaded by /regulatory-legal:gaps and /regulatory-legal:comments when tracking or surfacing open policy gaps.'

Reduce internal jargon ('per-send confirmation', 'policy-diff') in favor of plain terms so the description reads as natural language rather than implementation shorthand.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Tracks open policy gaps with remediation status, ingests gaps from policy-diff, surfaces what's open and aging, routes to owners, and notifies gap owners via Slack' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	'What' is clearly answered, but 'when' is loading semantics ('Loaded by the gaps and comments skills before doing substantive work') rather than an explicit 'Use when...' trigger, so completeness is capped at 2 per the guideline.	2 / 3
Trigger Term Quality	Terms are internal jargon ('gap- and comment-tracker framework', 'policy-diff', 'per-send confirmation') with no natural keywords a user would say; the skill is user-invocable: false, so there are no user-facing triggers.	1 / 3
Distinctiveness Conflict Risk	Names the exact skills it backs ('/regulatory-legal:gaps and /regulatory-legal:comments') and is non-user-invocable, giving it a clear niche unlikely to conflict with other skills.	3 / 3
	Total	9 / 12 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: anthropics/claude-for-legal
Path: regulatory-legal/skills/gap-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.