release

Coordinate a full Paperclip release across engineering verification, npm, GitHub, smoke testing, and announcement follow-up. Use when leadership asks to ship a release, not merely to discuss versioning.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

85%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.

An excellent operational skill body: fully executable commands and payloads, a well-sequenced workflow with real validation checkpoints and rollback guidance, and tight token efficiency. Its one structural weakness is that everything lives inline in a single ~315-line file — the Step 8 release-content Cases API detail in particular should be split into a reference file.

Suggestions

Move the Step 8 release-content Cases detail (the parent/child case payloads, field schema, and body-document examples) into a references file such as references/release-cases.md, leaving a short summary and link in SKILL.md.

Consider extracting the full JSON field schema and the workflow_dispatch inputs for the stable publish into a compact reference table, keeping only the operational sequence in the main body.

Trim meta-commentary such as 'The fields schema intentionally uses all generic JSON value types...' — it explains design intent rather than instructing the agent what to do.

Dimension	Reasoning	Score
Conciseness	The body is dense and imperative throughout — every section is task-specific project knowledge (release model rules, workflow inputs, exact commands) with no explanation of concepts Claude already knows. It misses a 5 only for minor trimmable content, e.g. the meta-commentary 'The fields schema intentionally uses all generic JSON value types...' about the dogfood payload.	4 / 5
Actionability	Guidance is fully executable: exact shell commands ('./scripts/release.sh stable --date YYYY-MM-DD --print-version', 'PAPERCLIPAI_VERSION=canary ./scripts/docker-onboard-smoke.sh'), complete copy-paste HTTP JSON payloads with env vars and headers, and a concrete rollback command. This matches the top anchor for copy-paste-ready coverage of common cases.	5 / 5
Workflow Clarity	A clear preconditions checklist, numbered steps 0-8, explicit validation gates (typecheck/test/build, smoke test with five pass criteria, dry-run before live publish), and detailed failure-handling and rollback paths. This matches the top anchor: explicit validation steps, error-recovery feedback loops, and checklists.	5 / 5
Progressive Disclosure	Sections are clearly headed and easy to navigate, but there are no bundle files at all, and roughly 70 lines of Cases API payload schema and upsert detail in Step 8 belong in a one-level-deep references file rather than inline in SKILL.md. This matches the anchor for 'some structure... content that should be separate is inline' — better than the minimal-structure anchor of 2, but short of the well-split organization of 4.	3 / 5
	Total	17 / 20 Passed

Description

87%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 strong description that clearly states what the skill does and gives explicit, natural trigger guidance with a boundary against adjacent skills. The only gaps are minor: a few missing common trigger synonyms and surface-level rather than operation-level action enumeration.

Dimension	Reasoning	Score
Specificity	The description names several concrete coordination surfaces — 'engineering verification, npm, GitHub, smoke testing, and announcement follow-up' — matching the anchor for several specific actions with minor gaps. It falls short of a 5 because it describes release surfaces rather than enumerating the concrete operations (changelog drafting, tag creation, GitHub Release creation) that the body actually covers.	4 / 5
Completeness	It explicitly answers both questions: the 'what' ('Coordinate a full Paperclip release across engineering verification, npm, GitHub, smoke testing, and announcement follow-up') and the 'when' ('Use when leadership asks to ship a release, not merely to discuss versioning') with concrete trigger phrasing. This is a direct match for the top anchor, and clearly better than the anchor of 4 where the 'when' is present but less explicit.	5 / 5
Trigger Term Quality	'ship a release' and 'leadership asks to ship a release' are natural phrases a user would say, giving good keyword coverage. Common synonyms like 'cut a release', 'publish', or 'roll out' are missing, so it does not reach the comprehensive-synonyms anchor of 5.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (the Paperclip maintainer release workflow) and the exclusion clause 'not merely to discuss versioning' actively reduces overlap with versioning-discussion skills. Minimal conflict risk, matching the top anchor.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: paperclipai/paperclip
Path: .agents/skills/release/SKILL.md
Commit: 1c07b59

Reviewed: 1 day 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.