release-skills
Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送".
77
72%
Does it follow best practices?
Impact
Pending
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
89%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 solid skill description with excellent trigger terms (including multilingual support) and a clear 'Use when' clause. Its main weakness is that the 'what' portion is somewhat vague — it says it's a 'universal release workflow' that 'auto-detects version files and changelogs' but doesn't specify the concrete actions performed (e.g., bumping versions, creating tags, publishing). The trigger term 'push' could cause minor overlap with general git skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Bumps version numbers, updates changelogs, creates git tags, and publishes releases' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (release workflow) and mentions auto-detecting version files and changelogs, plus lists supported project types. However, it doesn't list multiple concrete actions beyond 'auto-detects version files and changelogs' — it doesn't specify what it actually does (e.g., bump version numbers, generate changelog entries, create git tags, publish packages). | 2 / 3 |
Completeness | Clearly answers both 'what' (universal release workflow that auto-detects version files and changelogs, supports multiple project types) and 'when' (explicit 'Use when user says...' clause with specific trigger phrases). The 'Use when' clause is explicit and well-defined. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'release', 'new version', 'bump version', 'push', and even Chinese equivalents '发布' and '推送'. Also mentions specific ecosystems (Node.js, Python, Rust) which users might reference. Good coverage of terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'release workflow', specific language triggers including multilingual terms, and the enumerated project types (Node.js, Python, Rust, Claude Plugin) creates a clear niche. The trigger term 'push' could potentially overlap with git push skills, but the overall context makes it fairly distinct. | 3 / 3 |
Total | 11 / 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 provides an extremely thorough and actionable release workflow with clear step sequencing and validation checkpoints. However, it is far too verbose for a SKILL.md file—translation tables, three-language changelog examples, full config file examples, and dry-run output templates should be extracted into separate reference files. The monolithic structure and redundant explanations of concepts Claude already knows (semver, conventional commits, git tagging) significantly hurt token efficiency.
Suggestions
Extract the section title translation table, language detection rules, and multi-language changelog examples into a separate CHANGELOG-REFERENCE.md file, keeping only a brief summary and link in the main skill.
Move the .releaserc.yml configuration schema and dry-run output example into a separate CONFIG.md or REFERENCE.md file.
Remove explanations of concepts Claude already knows: conventional commit type descriptions, semver bump rules, and basic git commands. Replace with terse references like 'Follow conventional commits; semver bump per commit types.'
Condense the multi-language examples to show just one language pair (e.g., en + zh) instead of three full examples that repeat the same structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines. It includes extensive translation tables, multiple detailed examples in three languages, lengthy configuration file examples, and dry-run output examples that could be significantly condensed. Much of this (conventional commit types, semver rules, git commands) is knowledge Claude already has. | 1 / 3 |
Actionability | The skill provides fully executable git commands, specific file paths, concrete examples of commit messages, changelog formats, and clear command-line flags. Every step includes copy-paste ready commands and specific tool invocations like `gh pr view`. | 3 / 3 |
Workflow Clarity | The 9-step workflow is clearly sequenced with explicit validation checkpoints: user confirmation before release commit (Step 8), dry-run mode for previewing, breaking change detection with warnings, and a clear feedback loop for README updates. The workflow handles error cases and includes a confirmation gate before destructive operations. | 3 / 3 |
Progressive Disclosure | Everything is crammed into a single monolithic file with no references to external files. The translation tables, configuration examples, multi-language changelog examples, and dry-run output could easily be split into separate reference files. The content that should be in supplementary files (language tables, config schema, examples) bloats the main skill significantly. | 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 (502 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- jimliu/baoyu-skills
- Commit
9eb032a
- 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.