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

66%

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

73%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.

The body is a well-structured routing skill with an explicit sequenced workflow, concrete commands, strong safety gates around destructive operations, and clean one-level delegation to the codex-autoresearch engine. Its main cost is redundancy — the same routing table is repeated across roughly five sections, inflating token usage without adding information.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and explains no general concepts, but the same routing map (correctness→`slate-patch`, API→`slate-plan`, perf→`slate-ar-perf`, gates→`slate-ar-gate`, quality→`slate-ar-quality`) is restated in 'Do Not Use When', 'Relationship To Other Lanes', 'Natural Modes', 'Start Or Resume' step 2, and 'Quality-Gap Research'. That repetition across five sections means it could be meaningfully tightened, matching anchor 3 rather than 4.	3 / 5
Actionability	Concrete commands are given verbatim (`pnpm bench:targets:dry-run -- <target-id>`, `node tooling/scripts/bench-targets.mjs autoresearch-init <target-id>`, `finalize-preview --cwd .tmp/slate-v2`) and the Natural Modes table maps exact user phrases to exact skills. It is not a 5 because several operations defer their executable detail to the external `codex-autoresearch:codex-autoresearch` skill, so guidance here is not fully self-contained.	4 / 5
Workflow Clarity	'Start Or Resume' is a clearly sequenced 5-step workflow with an explicit route-before-editing decision checklist; the packet loop has explicit keep/discard/checks_failed feedback criteria after every packet; and finalization defaults to preview-only with explicit user-approval gates for branch creation, commit, push, and PR (with a rule that short confirmations like 'go'/'ok' do not approve). This matches anchor 5: clear sequence, explicit validation, feedback loops, and checklists.	5 / 5
Progressive Disclosure	Structure is good — clear sections, and detail is delegated one level deep with explicit signaling ('Load `codex-autoresearch:codex-autoresearch` for command details, packet lifecycle, dashboard operation...'), and no bundle files exist to nest. It is not a 5 because dense in-file sections like 'Natural Modes' and 'Relationship To Other Lanes' could arguably live in separate reference files, leaving minor organization gaps.	4 / 5
	Total	16 / 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 clearly bounded within its niche, with a concrete 'what' and explicit delegation of generic mechanics to the underlying engine. Its main weaknesses are the complete absence of 'when to use' trigger guidance and reliance on internal jargon rather than natural user phrases, which limits discoverability.

Suggestions

Append a 'Use when...' clause with concrete trigger phrases, e.g., 'Use when the user asks for Slate v2 Autoresearch status, continuation, dashboard, finalization preview, research, or quality-gap handling.'

Swap jargon-heavy terms ('measured loops', 'correctness routing') for natural synonyms users would actually say, such as 'status', 'continue', 'finalize', 'research', and 'quality gap'.

Add one distinguishing cue against the closest neighbor (e.g., 'Performance optimization lives in slate-ar-perf') to reduce overlap risk within the slate-ar family.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — 'Delegates generic packet/dashboard/finalization mechanics to codex-autoresearch while enforcing `.tmp/slate-v2`, Slate correctness routing, target registry context, and short operator modes' — which matches anchor 4 (several specific actions, minor gaps). It is not a 5 because items like 'target registry context, and short operator modes' are stated as enforced concerns rather than fully articulated capabilities, leaving small coverage gaps.	4 / 5
Completeness	The 'what' is clear ('Wrap Codex Autoresearch for Slate v2 measured loops'), but there is no 'Use when...' clause or equivalent trigger guidance, so per the rubric guideline completeness is capped at 3. It is not a 2 because the 'what' is concrete and multi-part, not vague.	3 / 5
Trigger Term Quality	Relevant keywords exist ('Slate v2', 'Codex Autoresearch', 'dashboard', 'finalization', 'measured loops') but the phrasing leans on internal jargon ('correctness routing', 'target registry context', 'measured loops') and omits the natural phrases a user would actually say to reach this skill, such as 'status', 'continue', 'research', or 'quality gap'. This matches anchor 3 (some relevant keywords, missing common variations) rather than 4, which would require noticeably broader natural-term coverage.	3 / 5
Distinctiveness Conflict Risk	The niche is clear (Slate v2 wrapper) and it explicitly delimits itself ('Delegates generic packet/dashboard/finalization mechanics to codex-autoresearch'), giving minimal conflict with the engine skill. It is not a 5 because the description shares heavy vocabulary with the broader slate-ar-* family (e.g., no perf boundary is drawn here, unlike the body), leaving minor overlap risk with closely related skills.	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/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.