By ali5ter
Common workflow skills for Claude Code sessions: promote changes through the full release cycle, audit Claude Code plugins/skills/agents, audit project standards compliance, analyse projects for improvements, triage open GitHub issues, and review pull requests
Performs a deep review of the Claude Code plugin, skill, or sub-agent defined in the current project against official best practices. Documents findings as GitHub issues and writes a prioritised fix plan to the project CLAUDE.md. Use when the user says audit this plugin, review this skill, check this agent, or audit addon.
Audits the current project against the development standards defined in ~/.claude/CLAUDE.md. Documents non-compliant findings as GitHub issues and writes a prioritised fix plan to the project CLAUDE.md. Use when the user says audit against settings, audit standards, check standards compliance, or audit this project.
Analyses the current project across code quality, feature gaps, documentation, security, competitive landscape, and monetisation opportunities, then files prioritised GitHub issues. Use when the user says improve this, analyse this project, find improvements, or fill the backlog.
Runs the full release workflow for the current project. Commits any uncommitted changes, pushes to remote, creates and merges a PR if on a feature branch, determines the next semver version from conventional commits, creates an annotated git tag and GitHub release with generated notes, cleans up merged branches, and returns to a clean main. Use when the user says promote, ship, release, commit and push, tag and release, or get back to main.
Reviews an open pull request against coding standards, security, and test coverage, then posts a structured review comment and either approves or requests changes. Use when the user says review this PR, check the PR, look at PR
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Common workflow skills for Claude Code sessions. Install once via the
ali5ter plugin marketplace and invoke with / in any
Claude Code session.
| Skill | Invoke | Description |
|---|---|---|
promote | /promote | Full release workflow: commit, push, PR, semver tag, GitHub release, branch cleanup |
audit-plugin | /audit-plugin | Deep review of a Claude Code plugin/skill/agent against official best practices |
audit-standards | /audit-standards | Audit project against personal dev standards in ~/.claude/CLAUDE.md |
improve | /improve | Analyse project for bugs, feature gaps, docs, security, competitive opportunities, and monetisation — file as GitHub issues |
triage | /triage | Validate all open issues, close invalid ones, flag complex ones for planning, fix and promote the rest |
review-pr | /review-pr | Review an open PR against coding standards, security, and test coverage, then post a structured review and approve or request changes |
/plugin marketplace add ali5ter/claude-plugins
/plugin install claude-workflow-skills@ali5ter
/plugin update claude-workflow-skills@ali5ter
Each skill is invoked with its / prefix from any Claude Code session:
/promote
/audit-plugin
/audit-standards
/improve
All skills have disable-model-invocation: true — they must be invoked explicitly via their /
prefix. Claude will not fire them automatically, even if the conversation matches a trigger phrase.
This prevents accidental side effects (commits, issue creation, PR reviews) without explicit user
intent.
Recognised trigger phrases (for reference — always invoke manually):
| Skill | Trigger phrases |
|---|---|
/promote | "ship this", "release", "get back to main", "tag and release" |
/audit-plugin | "audit this plugin", "review this skill", "check this agent" |
/audit-standards | "audit standards", "check standards compliance", "audit against settings" |
/improve | "improve this", "analyse this project", "find improvements", "fill the backlog" |
/triage | "triage issues", "validate issues", "fix issues", "work through the backlog" |
/review-pr | "review this PR", "check the PR", "look at PR #N", "review pull request" |
/promoteRuns the full release workflow for the current project:
mainRequires gh (GitHub CLI) to be authenticated.
/audit-pluginPerforms a deep review of the Claude Code addon defined in the current project:
plugin.json, SKILL.md, and agent .md filesCLAUDE.md/audit-standardsAudits the current project against the seven development principles in ~/.claude/CLAUDE.md:
Creates GitHub issues for non-compliance and writes a prioritised fix plan to CLAUDE.md.
/improveAnalyses the current project from multiple angles and files GitHub issues for every finding:
Produces a prioritised summary table with top issues and highest-leverage opportunities.
Note: Steps 6 and 7 (competitive landscape and monetisation) require
WebSearchandWebFetchpermissions. In restricted permission mode, approve these when prompted or those steps will be skipped.
/triageWorks through every open GitHub issue and resolves them:
/promote to commit, tag, and releasenpx claudepluginhub ali5ter/claude-plugins --plugin claude-workflow-skillsAutomatically documents technical projects in Obsidian vaults during Claude Code sessions
Expert UX evaluator for command-line interfaces, CLIs, terminal tools, shell scripts, and developer APIs
Graduated assistance framework to prevent skill atrophy when coding with AI
Evidence-based health, fitness, nutrition, and longevity guidance for adults 50+
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.