slate-ar-status

Read-only status shortcut for Slate v2 Autoresearch. Shows current session state, dashboard URL, next recommended action, blockers, and latest metric evidence without running packets or editing files.

Quality

83%

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

Quality

Content

92%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, contract-style skill body that gives unambiguous direction for a single read-only task with concrete commands, paths, an explicit do-not-run list, and a closing scope statement. The only minor gap is that executable command syntax is delegated to the referenced `slate-ar` skill rather than inlined.

Dimension	Reasoning	Score
Conciseness	The body is roughly 20 lines with zero padding: no explanation of concepts Claude already knows, no restated context, and every line either directs action or bounds scope ("This skill is a read-only operator view, not a loop runner."). Matches anchor 5's lean-and-efficient profile; anchor 4 would require at least minor over-explanation to trim.	5 / 5
Actionability	Concrete guidance includes named commands (`state`, `onboarding-packet`, `recommend-next`), an exact flag (`--cwd .tmp/slate-v2`), concrete state file globs (`.tmp/slate-v2/autoresearch.*`), and an explicit prohibition list. It falls short of anchor 5's copy-paste-ready bar because the actual executable invocations are delegated to the `slate-ar` skill rather than shown, leaving a minor gap.	4 / 5
Workflow Clarity	This is a simple single-purpose skill under 50 lines whose single action — load `slate-ar` and run its read-only status mode, reporting state, dashboard URL, next action, blockers, and packet counts — is unambiguous, with the one conditional step (`serve`) explicitly bounded ("only to provide a live dashboard URL"). The simple-skill exception applies; it is not 4 because no validation gaps exist given the skill is read-only by contract.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are all absent) and none are needed at this size; the body is under 50 lines, well-organized into a title, argument handling, trigger line, Contract section, and scope statement. Per the under-50-lines guideline this matches anchor 5; anchor 4 would require organization gaps.	5 / 5
	Total	19 / 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.

A specific, distinctive description with concrete capability enumeration and an explicit read-only scope boundary, written in third person with no fluff. Its main weakness is the absence of a 'Use when...' trigger clause, which caps completeness at 3 despite the body containing such a line.

Suggestions

Append a 'Use when...' clause to the description, e.g. 'Use when the user asks where the Slate v2 Autoresearch loop stands or wants its current status.' — this would raise completeness from 3 to 5.

Add one or two natural trigger synonyms users might actually say (e.g. 'progress', 'status report') to broaden keyword coverage.

Consider naming the state file location or command family briefly so the description also signals what evidence backs the status view, further reinforcing distinctiveness.

Dimension	Reasoning	Score
Specificity	"Shows current session state, dashboard URL, next recommended action, blockers, and latest metric evidence" enumerates multiple concrete capabilities with a clear read-only boundary, matching the comprehensive-coverage anchor; score 4 would require identifiable gaps in coverage, and none are present.	5 / 5
Completeness	The description clearly answers "what" but contains no "Use when..." clause or equivalent trigger guidance, which the judging guidelines explicitly cap at 3. Score 4 is ruled out because it requires both 'what' and 'when' to be present.	3 / 5
Trigger Term Quality	Natural phrases like "status", "session state", "dashboard URL", and "blockers" are present and would be said by a user of this system, but common variations such as "progress", "report", or "where things stand" are missing. It sits between anchor 3 (missing variations) and anchor 5 (comprehensive synonyms), noticeably above the midpoint.	4 / 5
Distinctiveness Conflict Risk	"Read-only status shortcut for Slate v2 Autoresearch" carves out a clear niche tied to a specific named system, making accidental triggering for unrelated skills minimal. It matches anchor 5's clear-niche example; anchor 4 would require noticeable overlap with a closely related skill.	5 / 5
	Total	17 / 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-status/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.