release-maintainer

Internal maintainer SOP for version bumps, release PRs, tagging, publishing, and post-publish verification in this repository.

Quality

78%

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/release-maintainer/SKILL.md

Quality

Content

78%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 lean, well-organized maintainer SOP that wraps a canonical process document rather than duplicating it, with concrete commands and explicit validation/recovery guidance. Actionability is slightly limited by reliance on the external doc for the detailed step list.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, with only minor over-direction such as restating guardrails and failure reminders that partly echo the referenced RELEASE-PROCESS.md.	4 / 5
Actionability	It gives concrete executable guidance such as the `gh api graphql` command and structured `gh run view ... --json` usage, but most steps defer to the external RELEASE-PROCESS.md rather than being copy-paste ready here.	4 / 5
Workflow Clarity	A clear sequenced Preflight and Execution Checklist with explicit validation (verify GH access, check CI status, verify npm + GitHub assets) and a Failure Recovery section, though some checkpoints are delegated to the external doc.	4 / 5
Progressive Disclosure	Well-structured overview that wraps a single canonical external reference (docs/RELEASE-PROCESS.md) one level deep, with clearly signaled sections and no nested or buried references.	5 / 5
	Total	17 / 20 Passed

Description

78%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, well-bounded description for an internal release-maintainer SOP that names concrete release actions clearly. Adding an explicit 'Use when...' trigger clause would lift completeness.

Suggestions

Append an explicit 'Use when asked to bump versions, cut releases, or publish packages' trigger clause to the description to satisfy the completeness 'when' requirement.

Add common synonyms or trigger phrasings (e.g., 'cut a release', 'publish to npm') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (version bumps, release PRs, tagging, publishing, post-publish verification), with only minor coverage gaps like release-notes automation.	4 / 5
Completeness	It answers 'what' (version bumps, release PRs, tagging, publishing, verification) and scopes 'when' via the phrase 'when you are asked to' in the body, but the description itself lacks an explicit 'Use when...' trigger clause.	4 / 5
Trigger Term Quality	Natural trigger terms like 'version bumps', 'release PR', 'tagging', and 'publishing' are present, though it leans on internal phrasing and omits a few common synonyms.	4 / 5
Distinctiveness Conflict Risk	The release-maintainer niche is clearly bounded with distinct triggers (version bumps, tagging, publishing) and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: coder/agent-tty
Path: .agents/skills/release-maintainer/SKILL.md
Commit: ebff2c2

Reviewed: 4 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.