autoclosure

Autonomously close the current Plate work tree through source sync, proof, review, checks, GitHub delivery, and final audit without expanding product scope.

Quality

64%

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/autoclosure/SKILL.md

Quality

Content

70%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 highly actionable, rigorously sequenced closeout contract with strong validation and feedback loops, but it is long and repetitive in places and keeps all detail in a single monolithic file rather than offloading bulk procedures to reference files.

Suggestions

Extract the long Live PR Feedback Gate procedure into a reference file (e.g. references/live-pr-feedback.md) and summarize it in SKILL.md to improve progressive disclosure and reduce repetition.

De-duplicate the three-way OID/read-back/receipt equality check by stating it once and referencing it from the Closure Loop steps.

Add a short 'Prerequisites / external skills' list (resolve-pr-feedback, agent-native-reviewer, autoreview, task, major-task) so the delegated workflows are clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is instruction-dense and avoids explaining concepts Claude already knows, but the three-way OID/read-back/receipt equality check and the terminal-receipt procedure are restated nearly verbatim across the Live PR Feedback Gate and Closure Loop steps 13-17, so it could be tightened.	3 / 5
Actionability	Concrete, copy-paste-ready commands and exact templates are given (`gh pr view`, `gh pr comment`, `gh pr close`, `gh api --paginate`, the literal remediation comment, `pnpm check`), with the only gaps being delegations to external workflows ('run resolve-pr-feedback in full mode', 'run autoreview').	4 / 5
Workflow Clarity	The 17-step Closure Loop is explicitly sequenced with validation checkpoints (read-back, OID equality, state verification), feedback loops ('return to step 3'), the Closure Matrix checklist, and Stop Conditions — exemplary for a destructive/batch closeout operation.	5 / 5
Progressive Disclosure	Section headers are clear and well-named, but no bundle files exist and all content — including the very long Live PR Feedback Gate — is inlined in one ~270-line file rather than split into one-level-deep reference files.	3 / 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 gives a clear, third-person statement of what the skill does and names several concrete closeout stages, but it lacks an explicit 'Use when' trigger clause and underuses the natural synonyms (finish, ship, clean) that would help it trigger reliably.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to finish, close, ship, or clean the current Plate work tree and only closeout gates remain.'

Surface the natural synonyms ('finish', 'ship', 'clean') alongside 'close' to improve trigger-term coverage.

Clarify that it does not start new work (the body's key boundary) to further reduce overlap with the `task` and `major-task` skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete closeout actions — 'source sync, proof, review, checks, GitHub delivery, and final audit' — giving broad coverage, though each is named at a high level rather than fully enumerated, so it stops just short of a 5.	4 / 5
Completeness	The 'what' is clear (autonomously close the work tree through enumerated stages), but there is no explicit 'Use when...' trigger clause, so per the rubric guidance completeness is capped at 3.	3 / 5
Trigger Term Quality	'close the current Plate work tree' is a relevant natural phrase, but the description leans on technical jargon ('source sync', 'GitHub delivery', 'final audit') and omits the everyday synonyms ('finish', 'ship', 'clean') that the body itself lists.	3 / 5
Distinctiveness Conflict Risk	The Plate-work-tree closeout niche with its specific stage list is mostly distinct from generic skills, with only minor overlap risk against general task/PR workflows.	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/autoclosure/SKILL.md
Commit: 9ec2c8e

Reviewed: 3 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.