CtrlK
BlogDocsLog inGet started
Tessl Logo

release-openspec

Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is complete, what the next release step is, or to continue a release paused for human approval.

80

Quality

100%

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

100%

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

An exemplary operational skill body: executable commands, a clearly sequenced state machine with validation checkpoints and failure recovery, and a well-signaled one-level reference for release-notes detail. It assumes Claude's competence and adds only non-obvious procedural knowledge.

DimensionReasoningScore

Conciseness

The body is dense operational state-machine prose with no filler explaining concepts Claude already knows; its length reflects the genuine complexity of the resumable release workflow, and every section earns its place. It is not padded verbosity.

3 / 3

Actionability

Provides concrete, copy-paste-ready commands throughout — 'gh repo view --json nameWithOwner,url', 'git fetch origin main', 'gh release list … --jq 'max_by(.publishedAt)…'', 'pnpm exec changeset status', 'npm view @fission-ai/openspec@<version> version' — rather than abstract direction.

3 / 3

Workflow Clarity

Sequences a multi-phase state machine (audit, coverage, changeset PR, validate Version Packages PR, verify publishing, beta, failures, report) with explicit validation gates and a feedback/failure-recovery section, including checks for destructive/batch operations so the workflow-clarity cap at 2 does not apply.

3 / 3

Progressive Disclosure

SKILL.md serves as the overview/state machine while the release-notes polishing detail is appropriately split into the real, one-level-deep, well-signaled references/release-notes.md (verified to exist), giving easy navigation.

3 / 3

Total

12

/

12

Passed

Description

100%

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 precise, well-scoped description that pairs a concrete action list with explicit, natural trigger conditions for a bespoke release workflow. It avoids vague fluff and clearly distinguishes itself from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete release actions — 'audit merged work and changeset coverage', 'prepare or resume the Changesets Version Packages PR', 'cut a beta or stable release', 'verify publishing', 'polish GitHub release notes' — matching the multiple-specific-actions anchor. The imperative 'Use this skill when' form matches the rubric's own good examples rather than the penalized second-person voice, so no penalty applies.

3 / 3

Completeness

Explicitly answers 'what' (the enumerated release actions) and 'when' via two explicit trigger clauses — 'Use this skill when releasing OpenSpec' and 'Also use when asked whether…' — so the missing-trigger cap at 2 does not apply.

3 / 3

Trigger Term Quality

Natural phrases a user would actually say are well covered: 'releasing OpenSpec', 'cut a beta or stable release', 'whether an open release PR is complete', 'what the next release step is', 'continue a release paused for human approval'.

3 / 3

Distinctiveness Conflict Risk

Names a clear bespoke niche (releasing the OpenSpec repo specifically) with distinct triggers like 'Version Packages PR' and 'changeset coverage', making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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
Fission-AI/OpenSpec
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.