skill-registry

Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.

Quality

77%

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 ./internal/assets/skills/skill-registry/SKILL.md

Quality

Content

80%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.

A tight, well-structured instruction skill with concrete operational details and clean sectioning. Its main weakness is the absence of an explicit validation checkpoint in the batch persist workflow, which caps workflow clarity.

Suggestions

Add an explicit validation checkpoint after rendering the registry (e.g., verify each row has a non-empty path and that duplicates were correctly deduplicated) before persisting to Engram.

Make Execution Step 1 more concrete by listing the specific user and project skill directories to scan, or referencing where they are resolved from.

Clarify the "Read frontmatter only as needed" step by specifying exactly which frontmatter fields to extract and how to handle malformed frontmatter.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of concepts Claude already knows; every section (Hard Rules, Decision Gates, Execution Steps) earns its place.	5 / 5
Actionability	Concrete specifics like the exact path `.atl/skill-registry.md`, Engram keys (`topic_key: skill-registry`, `capture_prompt: false`), and a skip list make it actionable; not 5 because several steps ("Scan all known... directories") remain abstract with no copy-paste-ready commands.	4 / 5
Workflow Clarity	A clear five-step sequence with a Decision Gates branching table is present, but a batch/destructive persist (writing the registry file, updating `.gitignore`, Engram save) lacks an explicit validate-the-output checkpoint, capping this at 3 per the destructive/batch guideline.	3 / 5
Progressive Disclosure	Under 50 lines with no bundle files and well-organized sections (Activation Contract, Hard Rules, Decision Gates, Execution Steps, Output Contract, References); the two references are clearly signaled and one level deep.	5 / 5
	Total	17 / 20 Passed

Description

75%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 concisely conveys both what the skill does and when to trigger it, with natural trigger phrases and a clearly distinct niche. It could be elevated by spelling out the "when" clause more explicitly and broadening trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the concrete indexing action ("Index available skills by trigger and path") plus trigger verbs ("update skills", "after skill changes"); falls short of 5 because only one core capability is described rather than multiple comprehensive actions.	4 / 5
Completeness	Provides both a clear "what" ("Index available skills by trigger and path") and a "when" via the explicit "Trigger:" clause; not 5 because the trigger guidance is terse and less explicitly spelled out than the anchor's "Use when..." form.	4 / 5
Trigger Term Quality	Includes natural phrases a user would say ("update skills", "skill registry", "after skill changes") plus a Spanish synonym ("actualizar skills"); not 5 because coverage lacks file extensions and broader synonym variations.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill registry indexing) with trigger terms tied to skill management; not 5 due to minor overlap risk with general skill-authoring skills, but clearly more distinct than score 3.	4 / 5
	Total	16 / 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: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/skill-registry/SKILL.md
Commit: a245f26

Reviewed: 1 day 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.