CtrlK
BlogDocsLog inGet started
Tessl Logo

release-process

Step-by-step release checklist for Squad — prevents v0.8.22 and v0.9.4-style disasters

60

Quality

72%

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 ./.copilot/skills/release-process/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A highly actionable, well-sequenced release runbook with strong validation feedback loops, held back by cross-section repetition and a monolithic single-file structure that lacks progressive disclosure into bundle files.

Suggestions

De-duplicate the GITHUB_TOKEN, CHANGELOG, and version-drift rules so each appears once; consolidate version-specific incident detail (PR #1042/#1043/#1044) into a single 'Incident learnings' reference file linked from the body.

Split the v0.9.4 incident learnings into a references/ bundle file (e.g. INCIDENTS.md) and link to it from the gotchas table to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Dense earned knowledge without basic-concept padding, but it is verbose: the GITHUB_TOKEN limitation, CHANGELOG rule, and version-drift rule each recur across the checklist, gotchas table, and v0.9.4 learnings, and version numbers/PR refs are scattered throughout rather than isolated in a deprecated section.

2 / 3

Actionability

Provides copy-paste-ready executable commands throughout — e.g. 'cd packages/squad-sdk && npm publish --access public', 'gh workflow run squad-npm-publish.yml --ref main -f version=X.Y.Z', 'npm version $VERSION --workspaces --include-workspace-root --no-git-tag-version'.

3 / 3

Workflow Clarity

The sequenced release checklist, fallback protocol (retry once then local publish), and explicit validation gates ('If anything matches, STOP', post-publish smoke test with rollback) provide clear checkpoints and error-recovery feedback loops.

3 / 3

Progressive Disclosure

Well-sectioned but monolithic: no bundle files exist and all detail (including the lengthy v0.9.4 incident learnings) is inline in one ~210-line file; the 'Related' links point to external repo paths rather than one-level-deep skill references.

2 / 3

Total

10

/

12

Passed

Description

67%

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 occupies a distinct niche, but lacks an explicit 'Use when...' trigger clause, leaving the 'when to use' half of completeness implicit.

Suggestions

Add an explicit trigger clause, e.g. 'Use when preparing an npm release, publishing @bradygaster/squad packages, or recovering from a failed publish workflow.'

Include natural-language variations users might say ('release', 'publish to npm', 'cut a release', 'post-publish checks') to broaden trigger term coverage.

DimensionReasoningScore

Specificity

Lists three concrete actions across the release lifecycle — 'Pre-release validation', 'npm publish procedures', 'post-publish verification' — matching the multiple-specific-actions anchor rather than the single-domain level 2.

3 / 3

Completeness

Clearly answers 'what' (validation, publish, verification) but has no explicit 'when/Use when' trigger; per the judging guidelines a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

'npm publish' is a natural term a user would say, but 'pre-release validation' and 'post-publish verification' are process jargon with no common variations or explicit 'Use when' trigger phrasing.

2 / 3

Distinctiveness Conflict Risk

The npm-release/publish niche is narrow and unlikely to trigger for unrelated skills; conflict risk is low even without explicit trigger wording.

3 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
bradygaster/squad
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.