CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

release-asc-cli

Publish and verify a new release of the App-Store-Connect-CLI repository. Use only when the user explicitly asks to release, tag, or publish a specific ASC CLI version, including the full GitHub release, artifact, Homebrew, WinGet, cleanup, and release-announcement workflow.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-structured orchestration procedure with exemplary validation gates, feedback loops, and stop conditions, plus concrete commands and examples. The main improvement opportunities are adding explicit commands for the steps that currently rely on directives and moving the changelog rules block into a reference file.

Suggestions

Add executable commands for the steps that are currently directives, e.g., the GitHub release-run watch (gh run watch or gh run view with the run ID) and artifact download/hash verification, so the publish and verify stages are as copy-paste ready as the release gate.

Move the changelog writing rules and the illustrative example entry into a references/ file (like release-announcement.md) and keep only the essential inline rules in SKILL.md, improving both progressive disclosure and token efficiency.

Trim rationale sentences such as "Checks run in the old worktree do not validate the new commit" and "PRs are evidence for writing the notes, not visible labels in the notes" where the rule itself already implies the reasoning.

DimensionReasoningScore

Conciseness

The body teaches no concepts Claude already knows and every section carries repo-specific policy, but a few rationale sentences ("Checks run in the old worktree do not validate the new commit", "PRs are evidence for writing the notes, not visible labels in the notes") and long conditional passages (the WinGet throttling paragraph) could be trimmed. This is efficient with minor instances of over-explanation, not the every-token-earns-its-place level.

4 / 5

Actionability

Concrete, executable guidance dominates: the copy-paste-ready release gate block ("make format ... ASC_BYPASS_KEYCHAIN=1 make test ... ./asc version"), website checks ("pnpm run lint", "pnpm build", "git diff --check"), and a full example changelog entry. However, several steps are directives rather than commands ("Query open PRs", "Locate the tag-triggered GitHub Actions run and watch it", downloading and hashing artifacts), leaving minor gaps against the fully-executable top anchor.

4 / 5

Workflow Clarity

The multi-step process is clearly sequenced with explicit validation checkpoints: a release gate with stop-on-failure rules, feedback loops for error recovery (corrections must merge via PR, then the gate restarts from updated origin/main), a resume-vs-new-release reconciliation procedure, and a consumer-visible verification checklist including codesign and checksum verification. This matches the top anchor for complex processes.

5 / 5

Progressive Disclosure

Structure is good: clear section progression from target proof through gate, publish, verify, changelog, announcement, and cleanup, with one well-signaled, one-level-deep reference (references/release-announcement.md, which exists, with explicit read timing). It falls short of the top anchor because the changelog writing rules plus the illustrative example entry form a substantial inline detail block that could be split into a reference file, as the announcement template was — a minor organization gap.

4 / 5

Total

17

/

20

Passed

Description

92%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.

A strong description that clearly states what the skill does and when to use it, with an explicit use-only-when clause and a fully enumerated workflow scope. The only soft spot is trigger-term coverage, which hits the natural phrases but misses a few synonyms.

DimensionReasoningScore

Specificity

The description lists multiple concrete, specific actions — "Publish and verify a new release" with an enumerated scope covering "GitHub release, artifact, Homebrew, WinGet, cleanup, and release-announcement workflow" — giving comprehensive coverage of what the skill does, matching the top anchor rather than the minor-gaps level below.

5 / 5

Completeness

It explicitly answers both questions: the "what" ("Publish and verify a new release of the App-Store-Connect-CLI repository... including the full GitHub release, artifact, Homebrew, WinGet, cleanup, and release-announcement workflow") and the "when" ("Use only when the user explicitly asks to release, tag, or publish a specific ASC CLI version"), matching the top anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Use only when the user explicitly asks to release, tag, or publish a specific ASC CLI version" covers the primary natural trigger phrases users would say. It falls short of the 5 anchor because common synonyms and variations (e.g., "cut a release", "ship a version", "roll out") are absent, though coverage is otherwise good.

4 / 5

Distinctiveness Conflict Risk

The skill is pinned to one named repository ("App-Store-Connect-CLI repository") and further constrained by "Use only when the user explicitly asks", creating a clear niche with distinct triggers and minimal risk of firing for unrelated release or publishing tasks.

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

rorkai/App-Store-Connect-CLI

Path

.agents/skills/release-asc-cli/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.