CtrlK
BlogDocsLog inGet started
Tessl Logo

release-cog

Guide and automate the Cog release process

61

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/release-cog/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a strong, highly actionable release runbook with clear sequencing, validation checkpoints, and error-recovery guidance; its main weakness is mild verbosity in the overview and architecture prose.

DimensionReasoningScore

Conciseness

The body is mostly lean actionable commands and tables, but the prose overview and Architecture Notes (CGO, Zig, wheel discovery) add context that could be tightened, matching the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

It provides fully executable, copy-paste-ready commands throughout (e.g. `mise run version:bump 0.18.0`, `gh release edit ... --notes "$(cat <<'EOF' ...)"`, `gh release download ... -p "coglet-*.whl"), matching the 'fully executable, copy-paste ready' anchor.

3 / 3

Workflow Clarity

A numbered 7-step release sequence, a pre-release checklist, and a troubleshooting section with explicit error-recovery feedback loops (version mismatch fix, rebuilding a failed release, emergency PyPI publish ordering) match the 'clear sequence with validation steps and feedback loops' anchor.

3 / 3

Progressive Disclosure

With no bundle files present and no external references needed, the single document is well-organized into clear sections with no nested reference chains, which per the scoring notes supports a 3 for a self-contained skill.

3 / 3

Total

11

/

12

Passed

Description

57%

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 to the Cog release domain and reasonably distinct, but it lacks a "Use when..." trigger clause and richer natural trigger terms, which limit its discoverability and completeness.

Suggestions

Add an explicit "Use when..." trigger clause, e.g. "Use when cutting, tagging, or publishing a Cog release, or when the user mentions shipping a new Cog version."

Expand trigger terms to cover natural phrasings users would say: "cut a release", "tag a release", "publish to PyPI/crates.io", "ship a Cog version".

List a couple of concrete actions (bump version, create release tag, publish to PyPI/crates.io, update Homebrew) instead of the generic "guide and automate".

DimensionReasoningScore

Specificity

"Guide and automate the Cog release process" names a clear domain and two actions (guide, automate), but not the concrete release tasks (bump version, tag, publish), matching the 'names domain and some actions' anchor.

2 / 3

Completeness

It states what the skill does but offers no "Use when..." clause or equivalent trigger guidance, which per the rubric caps completeness at 2.

2 / 3

Trigger Term Quality

Only "release"/"Cog release process" serve as natural triggers; common variations like "cut a release", "ship a version", "tag", or "publish to PyPI/crates.io" are absent, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

Tying the skill specifically to the Cog product's release process gives it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
replicate/cog
Reviewed

Table of Contents

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.