CtrlK
BlogDocsLog inGet started
Tessl Logo

release-skills

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

Quality

77%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/release-skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

55%

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

This skill is highly actionable with excellent workflow clarity—every step has concrete commands, validation checkpoints, and clear sequencing. However, it is severely over-long and monolithic, cramming translation tables, multi-language examples, configuration schemas, and multiple workflow modes into a single file. The content would benefit enormously from splitting into a concise overview with references to detailed sub-documents for translations, configuration, backfill mode, and examples.

Suggestions

Split the multi-language translation table, changelog format examples, and configuration schema into separate reference files (e.g., TRANSLATIONS.md, CONFIG.md) and link from the main SKILL.md

Remove redundant multi-language changelog examples—showing the pattern once with a note that it applies to all languages would save ~30 lines

Condense the Language Detection Rules table and hook placeholder table into briefer inline references or a separate REFERENCE.md

Remove explanations of concepts Claude already knows, such as what conventional commit types mean (feat = New features, fix = Bug fixes, etc.)

DimensionReasoningScore

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, git commands, JSON paths). Much of this could be dramatically condensed—e.g., the multi-language changelog examples repeat the same pattern three times, and the section title translation table could be a simple reference.

1 / 3

Actionability

The skill provides fully executable bash commands, concrete git workflows, specific file paths, exact command-line flags, and copy-paste ready code blocks throughout. Every step includes specific commands and expected outputs, making it highly actionable.

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 previewing, checking GitHub release existence before creating/editing, and explicit rules about when to skip or stop (e.g., 'stop rather than creating an empty tag or GitHub Release when notes cannot be found'). The backfill workflow also includes validation steps like checking for existing releases and requiring user confirmation for tag conversion.

3 / 3

Progressive Disclosure

This is a monolithic wall of text with no references to external files despite being ~400+ lines. The translation tables, configuration examples, multi-language changelog examples, and backfill workflow could all be split into separate reference files. No bundle files are provided, and nothing is delegated to supporting documents, making this a single massive file that must be loaded entirely into context.

1 / 3

Total

8

/

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.

This is a strong skill description that excels across all dimensions. It provides specific capabilities (auto-detection, multi-ecosystem support), comprehensive trigger terms in multiple languages, explicit 'Use when' guidance, and a clear niche that distinguishes it from other skills. The multilingual trigger terms are a particularly thoughtful addition for international users.

DimensionReasoningScore

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, supporting multiple ecosystems) 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 and Chinese variations: 'release', '发布', 'new version', 'bump version', 'push', '推送', 'release notes', 'GitHub Release', '回填 Release'. Covers multiple languages and common phrasings users would naturally use.

3 / 3

Distinctiveness Conflict Risk

The description carves out a clear niche around release/versioning workflows with specific ecosystem mentions. The trigger terms are focused on release-related actions, making it unlikely to conflict with general coding, deployment, or other skills.

3 / 3

Total

12

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (579 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Repository
jimliu/baoyu-skills
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.