CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

release-process

Operate Squad's automated insider, preview, and stable release channels safely

Quality

74%

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

73%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.

This is a strong operational runbook: fully concrete commands, a clearly sequenced multi-channel workflow with explicit validation gates, stop conditions, and recovery guidance, plus a consistently enforced human-only trigger boundary. The main costs are redundant repetition of the hand-off warning and a hardcoded example version that could be tightened or templated.

Suggestions

State the human-only boundary once in a dedicated 'Who may trigger what' section (or short table) instead of repeating the near-identical warning paragraph before each command block.

Define $VERSION at its first use (Preconditions) or note that it is set per channel in the following sections, so the precondition block is copy-paste runnable as-is.

Replace the hardcoded 'VERSION=0.14.0-preview.1' with a placeholder like VERSION=X.Y.Z-preview.N to keep the example version-agnostic.

DimensionReasoningScore

Conciseness

The body is dense and free of concept explanations Claude already knows, but it repeats the human-only hand-off boilerplate nearly verbatim three times ('Human-only reference command: this live publish workflow must be run by a human. Agents must stop, hand off, and not execute it directly.') on top of the boundary paragraph, and hardcodes a version number ('VERSION=0.14.0-preview.1'), which the guidelines penalize unless isolated in a deprecated section. This fits 'Mostly efficient but ... could be tightened' better than the level-4 anchor's 'minor instances'.

3 / 5

Actionability

Commands are concrete and near copy-paste ready: exact 'gh workflow run' invocations with flags, 'npm view' dist-tag checks, merge-base ancestry checks, and git diff guards. It stops short of 5 because '$VERSION' is used in the Preconditions block ('grep -F "## [$VERSION]" CHANGELOG.md') before any block defines it, and the example pins a hardcoded version, leaving minor gaps for first use.

4 / 5

Workflow Clarity

The multi-step process is clearly sequenced (Preconditions → Preview/Insider/Stable → Verify → Recovery) with explicit validation checkpoints and expected outcomes ('The ancestry command must return a commit, all three versions must match ... the changelog must contain the exact release version') plus a stop condition on version-only diffs and a dedicated recovery section with rerun/re-dispatch feedback loops. This matches the level-5 anchor's explicit validation and error-recovery pattern.

5 / 5

Progressive Disclosure

Sections are well organized with clear headers, and exact detail is delegated one level deep to a clearly signaled canonical runbook ('Read .squad/skills/release-process/SKILL.md for the canonical runbook and recovery commands'), with key commands inlined for immediate use. It is not 5 because the pointer targets an external repo path rather than bundle reference files, and the inlined channel details (secrets, Homebrew/WinGet specifics) are content that could live in a separate reference file.

4 / 5

Total

16

/

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 concise, project-specific, and names the three release channels distinctly, minimizing conflict risk. Its main weakness is the absence of any 'Use when ...' trigger guidance and the reliance on one generic action verb instead of concrete capability verbs, which caps completeness and specificity.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to publish, promote, or verify a Squad release (insider, preview, or stable), or when preparing a release PR.'

Replace the generic verb 'Operate' with concrete actions, e.g. 'Prepare, validate, and hand off Squad's insider, preview, and stable releases: version checks, changelog gates, npm/Homebrew/WinGet verification.'

Include natural synonyms users would say ('cut a release', 'ship a preview', 'promote to stable') to strengthen trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain concretely ('Squad's automated insider, preview, and stable release channels') but offers only a single generic action verb ('Operate ... safely') rather than listing specific actions such as publishing, promoting, or verifying releases. This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' ('Processes PDF files and extracts content') and falls short of the level-4 anchor, which expects several specific listed actions.

3 / 5

Completeness

The 'what' is stated (operate Squad's three release channels safely) but there is no 'Use when ...' clause or equivalent trigger guidance, and per the rubric guideline a missing explicit trigger clause caps completeness at 3. It does not merit 4 because the 'when' is entirely absent, not merely implicit-but-present.

3 / 5

Trigger Term Quality

Natural channel keywords are present ('insider', 'preview', 'stable', 'release channels') that a team member would say when needing this skill, giving good coverage. It stays at 4 rather than 5 because common variations like 'publish', 'promote', 'cut a release', or 'ship' are missing, though it is clearly above the level-3 anchor ('Works with PDF files' — some keywords, missing variations).

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — one product's named insider/preview/stable release channels — with distinct triggers and virtually no overlap risk with generic skills. Unlike the level-4 anchor ('Works with PDF and Word document files', minor overlap), no closely related skill would plausibly collide with these project-specific channel names.

5 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

bradygaster/squad

Path

.copilot/skills/release-process/SKILL.md

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.