release-cog

Guide and automate the Cog release process

Quality

71%

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-cog/SKILL.md

Quality

Content

88%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 highly actionable and well-sequenced with strong validation checkpoints and troubleshooting feedback loops, making it a strong release runbook. Minor conciseness tightening (illustrative version numbers, release-notes prose) and possible splitting of the release-notes guidance could lift it further.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven, assuming Claude's competence with no padding about what Cog is; minor over-explanation in the release-notes style section and illustrative version numbers (v0.18.0, v0.20.0) scattered as examples keep it just below fully efficient.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover every common case (mise run version:bump, gh pr create, git tag, gh release edit, twine upload) with concrete examples for stable, pre-release, and dev releases.	5 / 5
Workflow Clarity	A clear 7-step sequence is paired with a pre-release checklist for validation, and the troubleshooting section provides explicit feedback loops (delete tag/release, fix, re-tag; emergency manual PyPI publish) for destructive and batch operations.	5 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections (Overview, Quick Release Commands, Process Details, Checklist, Troubleshooting, Architecture); as a single-file skill with no bundle files it needs no external references, though it is a touch dense for a pure overview.	4 / 5
	Total	18 / 20 Passed

Description

53%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 clear and distinct but terse: it states what the skill does without listing concrete actions or providing an explicit "Use when" trigger clause. Adding specific actions and a trigger phrase would lift specificity and completeness.

Suggestions

Add concrete actions, e.g. "Guide and automate the Cog release process: bump versions, create release tags, monitor builds, and publish to PyPI, crates.io, and Homebrew."

Append an explicit trigger clause, e.g. "Use when releasing a new version of Cog or cutting a stable, pre-release, or dev tag."

Include natural synonyms users might say ("publish Cog", "cut a Cog release", "version bump") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("Cog release process") and two actions ("Guide and automate") but lists no specific concrete actions like version bumping, tagging, or publishing; matches the anchor for domain plus 1-2 actions without comprehensive coverage.	3 / 5
Completeness	Has a clear "what" (guide and automate the release process) but no "when" / "Use when..." trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant natural keywords ("Cog", "release") a user would say, but misses common synonyms and variations like "publish", "version bump", or "cut a release".	3 / 5
Distinctiveness Conflict Risk	"Cog release process" carves a clear, distinct niche unlikely to conflict with other skills, though the single-sentence brevity leaves minor overlap risk with generic release tooling.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: replicate/cog
Path: .agents/skills/release-cog/SKILL.md
Commit: ec8082f

Reviewed: 5 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.