slate-ar-quality

Slate v2 quality-gap Autoresearch shortcut. Runs deep-research and quality-gap loops for API/DX/architecture/test coverage gaps, then routes accepted findings to slate-patch, slate-plan, slate-ar-gate, or slate-ar-perf.

Quality

61%

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 ./.agents/skills/slate-ar-quality/SKILL.md

Quality

Content

65%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 lean, well-sectioned body that avoids over-explanation entirely, but its commands lean on placeholders and an undefined 'slate-ar' wrapper, and the multi-stage workflow is listed rather than sequenced with validation checkpoints. Resolving the command placeholders and numbering the steps would lift actionability and workflow clarity.

Suggestions

Resolve the '<autoresearch-cli>' placeholder to the actual command (or state how to resolve it via 'slate-ar'), and briefly define '<slug>' and '<goal>' inputs.

Number the workflow steps explicitly (setup -> list gaps -> inspect candidates -> apply -> route) with a validation checkpoint before routing, e.g. re-check the accepted checklist after apply.

Trim the closing slate-patch guidance that duplicates the Routing section's first bullet to remove the small redundancy.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean and operational with no padding or explanation of concepts Claude already knows; every section (Contract, Commands, Routing) earns its tokens. Not 5 because there is mild redundancy — the closing slate-patch guidance repeats the Routing section's first bullet, and the description already carries the routing map.	4 / 5
Actionability	Commands are concrete in form but use unresolved placeholders ('<autoresearch-cli>', '<slug>', '<goal>') with no definition of what autoresearch-cli resolves to, and the 'slate-ar' wrapper the skill hinges on is never shown as an executable invocation. Not 4 because the placeholder CLI and undefined wrapper are more than minor gaps; not 2 because real command syntax and flags are given for each step.	3 / 5
Workflow Clarity	The sequence (research-setup -> quality-gap --list -> gap-candidates -> inspect -> --apply -> route) is implied by the command listing but never explicitly ordered, and the only checkpoint ('Use gap-candidates --apply only after inspecting the candidates and deciding the write scope is safe') is a caution rather than a validate-fix-retry loop. Not 4 because there is no explicit step ordering or validation of the research output before routing; not 2 because the stages and their safety precondition are at least present.	3 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is cleanly sectioned (Contract, Commands, Routing) with each part easy to navigate — matching the simple-skill exception for progressive disclosure. No bundle files exist, so nothing is misplaced or buried.	5 / 5
	Total	15 / 20 Passed

Description

58%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 distinctive within its niche, with concrete actions and explicit downstream routing, but it is written almost entirely in project-internal jargon and omits any 'Use when...' trigger guidance. Adding natural trigger phrases and a use-when clause would raise both completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user wants to find and close API, architecture, or test-coverage gaps in Slate v2, or asks to broadly improve a surface beyond a single bug.'

Include natural trigger terms users would actually say ('find coverage gaps', 'what's missing', 'audit the API/DX', 'improve the surface') alongside the jargon terms.

Clarify the concrete action 'runs deep-research and quality-gap loops' in plainer language so the capability is understandable outside the Slate tooling context.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('Runs deep-research and quality-gap loops', 'routes accepted findings to slate-patch, slate-plan, slate-ar-gate, or slate-ar-perf') plus the gap domains (API/DX/architecture/test coverage), but the heavy internal jargon leaves minor gaps in what the actions concretely entail. Not 5 because coverage relies on project-specific shorthand rather than fully comprehensible actions; not 3 because multiple specific actions and targets are explicitly listed.	4 / 5
Completeness	The 'what' is clear (runs research/quality-gap loops and routes findings), but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. Not 4 because the 'when' is entirely absent rather than merely imprecise.	3 / 5
Trigger Term Quality	Some relevant keywords are present ('quality-gap', 'API/DX/architecture/test coverage gaps', 'deep-research') but they are project-internal jargon; common natural variations a user would say ('find what's missing', 'improve coverage', 'audit the API') are absent. Not 4 because the natural-phrasing coverage is thin; not 2 because domain-relevant gap terminology is genuinely present.	3 / 5
Distinctiveness Conflict Risk	Clear niche ('Slate v2 quality-gap Autoresearch shortcut') with explicit routing to sibling skills (slate-patch, slate-plan, slate-ar-gate, slate-ar-perf), making it mostly distinct. Not 5 because it sits in a family of closely related slate-ar skills whose descriptions could overlap on similar research-gap phrasing; not 3 because the routing list and quality-gap framing distinguish it reasonably well.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/slate-ar-quality/SKILL.md
Commit: babb3c2

Reviewed: 2 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.