slate-plan

Review Slate v2 architecture/API plans against React 19.2 runtime performance, Slate-close unopinionated DX, legacy-regression proof, research evidence, and shadcn-style composability; write a scored plan and keep completion pending until every required pass and closure gate is complete.

Quality

72%

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 ./.agents/skills/slate-plan/SKILL.md

Quality

Content

77%

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

The content is highly actionable and workflow-rich with concrete commands, templates, and validation feedback loops, but it is a long monolithic document whose heavily repeated ledger/verification rules could be extracted into reference files and de-duplicated.

Suggestions

Extract the plan-shape, confidence-scorecard, and objection-ledger schemas into a reference file (e.g. `references/plan-shape.md`) and link to it, reducing the inline wall of text and lifting progressive disclosure.

De-duplicate the issue-ledger / ClawSweeper / verification rules that recur across 'Required Artifacts', 'Issue Ledger Pass', 'PR Reference And Issue Accounting', 'Pass Schedule', and 'Pressure Passes' into a single canonical statement with cross-references, to improve conciseness.

Keep the executable commands and pass schedule up front; move the long 'Read First' file enumeration into a checklist reference so the core workflow stays lean.

Dimension	Reasoning	Score
Conciseness	The body is ~1250 lines of dense policy that does not teach basics Claude already knows, but the issue-ledger, ClawSweeper, and verification rules are restated across 'Required Artifacts', 'Issue Ledger Pass', 'PR Reference And Issue Accounting', 'Pass Schedule', and 'Pressure Passes', so it could be tightened substantially — 'mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	It provides fully executable commands (`node .agents/skills/autogoal/scripts/create-goal-scratchpad.mjs --template slate-plan`, `rg -n "..." .tmp/slate-v2/...`, `bun --filter slate ...`), concrete goal/plan templates, and exact table schemas, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear 12-pass schedule plus a pass-state ledger, conjunctive closure gates, and a verification feedback loop (run the `.tmp/slate-v2` command, record result, keep pending on failure, fix and re-validate) match the 'clear sequence with explicit validation steps; feedback loops' anchor.	3 / 3
Progressive Disclosure	Sections are well organized and references to repo files (e.g. `docs/plans/templates/slate-plan.md`, `docs/slate-v2/ledgers/*`) are one level deep, but SKILL.md is itself a monolithic inline wall of policy with no bundle files splitting the plan-shape, scoring, and objection-ledger detail out, so it is 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 niched, naming concrete review actions and criteria, but lacks an explicit 'Use when...' trigger clause and leans on specialized jargon over natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause naming the user situations that should trigger this skill (e.g., 'Use when reviewing Slate v2 architecture/API plans, React 19.2 runtime/ DX tradeoffs, or repeated best-shape review prompts') to lift completeness to 3.

Soften jargon ('closure gate', 'pass schedule', 'unopinionated DX') with natural phrasings users would actually say, to improve trigger-term coverage.

Keep the named criteria but lead with the most common trigger phrasing so a user naturally matches the skill.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions against named criteria — 'Review Slate v2 architecture/API plans against React 19.2 runtime performance, Slate-close unopinionated DX, legacy-regression proof, research evidence, and shadcn-style composability; write a scored plan and keep completion pending' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	The 'what' is explicit (review plans, write a scored plan, keep completion pending) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2; it is not a 1 because the what is clear.	2 / 3
Trigger Term Quality	It includes relevant domain terms ('Slate v2 architecture/API', 'React 19.2 runtime performance', 'shadcn-style composability') but they are jargon-heavy and it misses common natural variations a user might phrase, so it sits at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	It carves a clear narrow niche — Slate v2 architecture/API plan review with a scored, gate-gated plan — with distinct triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1261 lines); consider splitting into references/ and linking	Warning
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
relative_links	Relative link issues: 4 missing, 4 deeper-than-1-level, 1 suspicious	Warning

	Total	11 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/slate-plan/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.