agent-skill-deploy

Deploys agent skill collections from any GitHub repository with a /skills folder to one or more distribution surfaces: GitHub releases, Claude Code marketplace, VS Code plugin marketplace, and Copilot CLI plugin marketplace. Handles pre-flight validation, conventional commit analysis, version bumping across surface configs, and surface-specific publishing with dry-run support. Use when releasing, publishing, or deploying a skills collection to any supported marketplace or creating a GitHub release for a skills repository. Don't use for deploying non-skill packages, npm modules, Docker images, or Azure resources.

Quality

88%

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

85%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 highly actionable, well-sequenced deploy workflow with strong validation gates. The main gap is progressive disclosure: a bundled reference file is unused and surface detail is inlined.

Suggestions

Link references/surfaces.md from the 'Supported Surfaces' section and move per-surface config/deploy mechanics there, keeping SKILL.md as an overview.

Trim the Step 2b changelog guidelines to the essential rules; the bullet style can be implied from the example.

Consider collapsing the version-handling prose into a short table to reduce token weight.

Dimension	Reasoning	Score
Conciseness	Dense and task-oriented, assuming Claude's competence (no explanations of git tags or conventional commits), with a few prose sections like the changelog guidelines that could be tightened.	4 / 5
Actionability	Provides copy-paste-ready bash commands, exact file paths, and fully-specified AskUserQuestion blocks covering the common deploy cases.	5 / 5
Workflow Clarity	Nine numbered steps with explicit validation checkpoints (preflight stop-gate, dry run, CRITICAL user-approval gate before push) and a dedicated error-handling section with recovery guidance.	5 / 5
Progressive Disclosure	Scripts are referenced one level deep via `node scripts/...`, but `references/surfaces.md` exists yet is never linked from the body, and surface-specific deployment mechanics are inlined rather than delegated to that reference.	3 / 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 capabilities, trigger conditions, and boundaries in third person. Minor trigger-term synonym coverage keeps it just short of perfect.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (pre-flight validation, conventional commit analysis, version bumping across surface configs, surface-specific publishing, dry-run support) across four named surfaces, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (deploys skill collections via validation, version bumping, and surface-specific publishing) and when ("Use when releasing, publishing, or deploying... or creating a GitHub release"), plus a concrete "Don't use for..." boundary.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ("releasing, publishing, or deploying", "GitHub release", "marketplace", "skills collection"), but misses a few common synonyms like "ship" that appear only in the body.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill collections to specific marketplaces) and explicitly excludes non-skill packages, npm modules, Docker images, and Azure resources, minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: webmaxru/ai-native-dev
Path: skills/agent-skill-deploy/SKILL.md
Commit: 0ddb6a6

Reviewed: 1 day 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.