deepchat-release

Prepare and publish DeepChat releases in this repository. Use when Codex needs to bump the app version, update CHANGELOG.md, keep release notes bilingual from v1.0.1 onward with English bullets first and Chinese bullets second, run release checks, create or update versioned release branches such as release/v1.0.1, continue a half-finished release, fast-forward main with the documented release flow, create or push version tags, or clean up release branches after publishing.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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, lean release skill body with concrete commands, a clear gated workflow, and appropriate one-level-deep reference split. Minor gains are possible by inlining a few common git commands and adding an explicit validate-retry loop in the recovery case.

Suggestions

Inline the exact git commands for the most common 'cut release branch' and 'publish' steps so the common path is copy-pasteable without opening the checklist.

Add an explicit validate-then-retry feedback loop in the Common Recovery Case (e.g. re-run format/lint after the metadata fix and only force-push when checks pass).

Trim a few explanatory lead-ins like 'Inspect git state before changing anything' to keep every token earning its place.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, avoiding explanations of basic git or release concepts; every section earns its place. Not a 5 because a few lead-in sentences ('Inspect git state before changing anything', 'When preparing a release on dev:') could be trimmed slightly.	4 / 5
Actionability	Provides concrete, copy-pastable commands inline (pnpm run format/i18n/lint, pnpm run release:ff -- release/<version> --tag v<version>, --force-with-lease) and an exact changelog format block, with full command sequences delegated to the checklist. Not a 5 because several exact git commands live only in the reference rather than being inline for the common cases.	4 / 5
Workflow Clarity	A clear four-mode sequence (prepare metadata, cut release branch, update existing, publish) with validation checkpoints (format/i18n/lint/typecheck), an explicit 'only after the release PR is approved' gate, and a 'stop and ask before replacing a tag' guardrail; validation is present so the destructive-operation cap does not bind. Not a 5 because the recovery case lacks an explicit validate-then-retry feedback loop and some checkpoints are implicit.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview pointing to one clearly-signaled, one-level-deep in-bundle reference (references/release-checklist.md, verified to exist) for exact commands, with policy kept inline; content is appropriately split and easy to navigate. Not below 5 because the single in-bundle reference is real, well-signaled, and only one level deep.	5 / 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, specific description that clearly states what the skill does and when to use it, with concrete release-specific triggers and low conflict risk. Trigger term coverage is very good but a few natural synonyms (cut/publish/ship a release) could be added.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete release actions (bump version, update CHANGELOG, bilingual English-then-Chinese notes, run release checks, create/update versioned release branches, continue a half-finished release, fast-forward main, create/push version tags, clean up release branches) with comprehensive coverage. Not a 4 because the action list is broad and specific rather than having only minor gaps.	5 / 5
Completeness	Explicitly answers both 'what' ('Prepare and publish DeepChat releases in this repository') and 'when' ('Use when Codex needs to...') with concrete trigger phrases. Not below 5 because neither component is missing or only weakly implied.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('bump the app version', 'update CHANGELOG.md', 'run release checks', 'fast-forward main', 'create or push version tags', 'clean up release branches', 'continue a half-finished release'). Not a 5 because a few common synonyms are missing (e.g. 'cut a release', 'publish a release', 'ship a release').	4 / 5
Distinctiveness Conflict Risk	A clear, narrow niche (this repository's DeepChat release flow) with distinct triggers (versioned release branches, version tags, bilingual changelog) making wrong-skill triggering unlikely. Not below 5 because the triggers are specific to one repo's release process rather than overlapping with general skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: ThinkInAIXYZ/deepchat
Path: .agents/skills/deepchat-release/SKILL.md
Commit: fa769d4

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.