release

Cut a versioned release and publish everos to PyPI via the tag-triggered workflow

Quality

73%

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 ./.claude/skills/release/SKILL.md

Quality

Content

82%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 tight, highly actionable runbook rich with project-specific operational knowledge and clear validation checkpoints, with only minor gaps in explicit failure-loop guidance and progressive-disclosure structure.

Suggestions

Add an explicit "if the PyPI verify step shows nothing" branch (e.g., re-run the release job / check Actions logs) to close the failure loop.

Consider extracting the one-time setup and release-page template into a reference file so the main flow stays a concise overview.

Move or tag the version-numbered evidence (1.1.3–1.2.2) into a dated "known issues / history" note so stale references are isolated from the live procedure.

Dimension	Reasoning	Score
Conciseness	Lean and competence-assuming, with every section earning its place via non-obvious project facts (the untagged-<hash> URL gotcha, the 1.2.2 API draft-tag-drop bug); minor time-sensitive version references used as evidence keep it just below a 5.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (git tag/push, the gh api PATCH with tag_name), exact pyproject and CHANGELOG edits, and a concrete verification URL covering the common cases.	5 / 5
Workflow Clarity	An 8-step sequence with a preconditions checklist, automatic validation (the workflow refuses on version mismatch), a verify step, and recovery guidance (re-run is safe, fix in CHANGELOG not the draft); the explicit failure loop if PyPI verify fails is not spelled out, holding it at 4.	4 / 5
Progressive Disclosure	Single well-sectioned file (Preconditions, Steps, The release page, Pre-releases, One-time setup) with no bundle files present and no need for external references; good organization, though it exceeds the under-50-line simple-skill threshold so it does not reach the 5 for plain well-organized sections.	4 / 5
	Total	17 / 20 Passed

Description

65%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 is specific and highly distinct, pinning a concrete project workflow, but it omits an explicit trigger/"Use when" clause, which caps completeness and limits when Claude would naturally invoke it.

Suggestions

Append an explicit trigger clause, e.g. ". Use when the user asks to cut, ship, or publish a new everos release to PyPI."

Mention the CHANGELOG/GitHub Release page authoring so the action set reads as comprehensive rather than two steps.

Add a synonym such as "version bump" alongside "versioned release" to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("Cut a versioned release", "publish everos to PyPI") plus the mechanism ("tag-triggered workflow"), but coverage is not comprehensive — CHANGELOG drafting and the GitHub Release page are absent.	3 / 5
Completeness	The "what" is clear, but there is no explicit "Use when…" trigger clause, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Good natural keyword coverage with "release", "publish", "PyPI", and "versioned"; a few common variations (e.g. "version bump", "ship") are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to the everos/PyPI tag-triggered release process — a clear niche with distinct triggers and minimal risk of firing for an unrelated skill.	5 / 5
	Total	15 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: EverMind-AI/EverOS
Path: .claude/skills/release/SKILL.md
Commit: 6ff07ef

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.