slate-ar

Wrap Codex Autoresearch for Slate v2 measured loops. Delegates generic packet/dashboard/finalization mechanics to codex-autoresearch while enforcing `.tmp/slate-v2`, Slate correctness routing, target registry context, and short operator modes.

Quality

57%

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/SKILL.md

Quality

Content

70%

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

The body is a well-structured operational routing skill with a clear sequenced workflow and explicit validation checkpoints, scoring well on workflow clarity and progressive disclosure. It loses points on conciseness due to cross-section routing repetition and on actionability because most execution is delegated to another skill.

Suggestions

Consolidate the sibling-skill routing rules so they appear once rather than restated across 'Relationship To Other Lanes', 'Natural Modes', 'Start Or Resume', and 'Quality-Gap Research'.

Inline the most common Codex Autoresearch CLI invocations (packet, status, finalize) instead of fully delegating, so the skill is executable without loading another skill.

Provide a single concise routing table keyed by intent, and have the prose sections reference it instead of re-listing routes.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational without explaining concepts Claude already knows, but routing rules repeat across 'Relationship To Other Lanes', 'Natural Modes', 'Start Or Resume', and 'Quality-Gap Research', so it could be tightened.	2 / 3
Actionability	Concrete commands exist (`pnpm bench:targets:dry-run -- <target-id>`, `node tooling/scripts/bench-targets.mjs autoresearch-init <target-id>`, `finalize-preview --cwd .tmp/slate-v2`) but most execution detail is delegated to `codex-autoresearch`, so it is not fully copy-paste ready.	2 / 3
Workflow Clarity	'Start Or Resume' gives a clear numbered sequence with explicit validation checkpoints (keep only when the measured target improves and correctness checks pass; otherwise checks_failed/discard) and feedback loops after every packet.	3 / 3
Progressive Disclosure	Well-organized into clear sections with detail delegated to named sibling skills at one level deep ('Load `codex-autoresearch:codex-autoresearch` for command details'), no nested reference chains, and no bundle files needed.	3 / 3
	Total	10 / 12 Passed

Description

45%

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 names concrete domain mechanics but is written in heavy internal jargon with no natural user trigger terms and no explicit 'Use when' guidance, capping completeness. It carves a Slate v2 niche but risks overlapping sibling skills.

Suggestions

Add a 'Use when ...' clause with natural trigger phrases users would actually say (e.g., 'Use when running measured Autoresearch loops against Slate v2 targets').

Replace internal jargon like 'correctness routing' and 'target registry context' with plainer trigger terms, or pair them with user-facing equivalents.

Add a one-line disambiguator distinguishing this from `codex-autoresearch` and `slate-ar-perf` directly in the description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete mechanics ('Delegates generic packet/dashboard/finalization mechanics', 'enforcing `.tmp/slate-v2`', 'Slate correctness routing, target registry context, and short operator modes') rather than vague abstractions.	3 / 3
Completeness	Clearly states what the skill does but provides no 'Use when...' or equivalent explicit trigger guidance, so completeness caps at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Relies entirely on internal jargon ('measured loops', 'correctness routing', 'target registry context', 'operator modes') with no natural keywords a user would say when needing the skill.	1 / 3
Distinctiveness Conflict Risk	It is niche-specific to Slate v2 wrapping but still overlaps the broader `slate-ar-*` family and `codex-autoresearch`, with no distinct triggers in the description to disambiguate.	2 / 3
	Total	8 / 12 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/SKILL.md
Commit: 45116fd

Reviewed: about 13 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.