Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, GitHub Releases, annotated tags, historical release backfill, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送", "release notes", "GitHub Release", or "回填 Release".
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/release-skills/SKILL.mdQuality
Discovery
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.
This is a strong skill description that excels across all dimensions. It provides specific capabilities, comprehensive trigger terms in multiple languages, explicit 'Use when' guidance, and a clearly defined niche around release workflows. The multilingual trigger terms are a particularly thoughtful addition for international users.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and capabilities: auto-detects version files and changelogs, supports Node.js/Python/Rust/Claude Plugin/GitHub Releases/annotated tags/historical release backfill/generic projects. These are concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (universal release workflow with auto-detection, multi-platform support) and 'when' (explicit 'Use when user says...' clause with specific trigger phrases). Both dimensions are well-covered. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including English ('release', 'new version', 'bump version', 'push', 'release notes', 'GitHub Release') and Chinese equivalents ('发布', '推送', '回填 Release'). These are terms users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around release/versioning workflows with specific ecosystem mentions (Node.js, Python, Rust, etc.) and distinct trigger terms. The word 'push' could potentially overlap with git push skills, but the overall context makes the release focus clear. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent workflow clarity, providing concrete commands, clear sequencing, and proper validation checkpoints throughout a complex 10-step release process. However, it is severely over-long and monolithic—the multi-language translation tables, three-language changelog examples, hook contract details, configuration reference, and backfill workflow all belong in separate referenced files. The verbosity significantly undermines token efficiency, making this skill expensive to load for what could be a much leaner overview with progressive disclosure.
Suggestions
Extract the section title translation table, multi-language changelog examples, and hook contract/placeholder tables into separate reference files (e.g., TRANSLATIONS.md, HOOKS.md) and link to them from the main skill
Move the .releaserc.yml configuration reference and backfill workflow into their own files (CONFIG.md, BACKFILL.md) to reduce the main skill to an overview with clear navigation
Remove redundant multi-language examples—one language pair (en + zh) is sufficient to demonstrate the pattern; Claude can extrapolate to other languages
Condense the Language Detection Rules and Common README Updates tables, which explain concepts Claude already understands, into brief bullet points or omit entirely
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It includes extensive translation tables, multiple detailed examples in three languages, lengthy configuration file examples, and exhaustive explanations of concepts Claude already understands (conventional commits, semver, git commands). Much of this could be condensed significantly—the multi-language changelog examples alone repeat the same pattern three times, and the section title translation table is a large inline reference that could be a separate file. | 1 / 3 |
Actionability | The skill provides fully executable bash commands, specific git commands, concrete gh CLI usage, exact file paths and JSONPath expressions for version files, and detailed examples of expected outputs. Every step has copy-paste ready commands and clear format specifications. | 3 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with explicit validation checkpoints: user confirmation before release commit (Step 8), dry-run mode for preview, checking GitHub release existence before creating/editing, tag verification with --verify-tag, and explicit rules about when to stop (e.g., 'stop rather than creating an empty tag or GitHub Release when notes cannot be found'). Error recovery is addressed in backfill mode with skip/ask behavior. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files despite being ~400+ lines. The translation tables, multi-language examples, configuration reference, backfill workflow, and hook contract documentation could all be split into separate reference files. No bundle files are provided, and nothing is referenced externally—everything is inlined into a single massive document. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (579 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
bd5745f
Table of Contents
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.