Does promptscript auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Is promptscript free?

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

promptscript

Agent platform configuration as code _Define instructions, skills, agents, MCP servers, hooks, workflows, and policies once.

FLOW.md

mrwogu@mrwogu

GitHub

Plugin Signal79/100Solid

maintained99

capable68

documented75

adopted57

Install

$ npx -y skills add mrwogu/promptscript --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

TypeScript Node Bash Docker Git

+6 tags

GitHub Vitest Markdown Anthropic Gemini MCP

465

Stars

Forks

Active

Maintenance

TypeScript

Language

MIT

License

1d ago

Last commit

6mo ago

Created

Repo: mrwogu/promptscript

In this plugin

14 commands 6 agents 2 skills 1 MCP

See everything inside

What's inside

Show all 14 commands

/security-reviewReview code for security vulnerabilities /test-coverageAnalyze test coverage and suggest improvements /test-e2eWrite end-to-end tests for critical user journeys /test-integrationWrite integration tests for component boundaries /test-unitWrite unit tests following best practices /testWrite unit tests using Vitest /threat-modelAnalyze potential security threats /typeCreate TypeScript type definitions

MCP

code-review-graphstdio

README

Read on GitHub

PromptScript

Agent platform configuration as code

Define instructions, skills, agents, MCP servers, hooks, workflows, and policies once. Compile native configuration for 48 AI coding platforms.

Get started · Try the playground · Explore all features · View target matrix

AI coding tools no longer consume one instruction file. They discover skills, specialist agents, commands, MCP integrations, hooks, workflows, and platform-specific settings from different paths and schemas. Managing these files by hand creates drift between tools, repositories, and teams.

PromptScript turns that surface area into one validated, composable, Git-native source:

PromptScript source
    -> resolve inheritance, imports, and policies
    -> validate language and capabilities
    -> compile deterministic target-native files

No runtime proxy. No lowest-common-denominator output. Each formatter emits the richest native representation its platform supports.

Quick Start

npm install -g @promptscript/cli

prs init
# Edit .promptscript/project.prs
prs validate --strict
prs compile

prs init detects the project stack and installed AI tools, then creates a clean promptscript.yaml and .promptscript/project.prs. Detected targets are preselected, while other targets remain explicit choices. For automation, use prs init --yes --targets claude factory. Hooks are installed by default. Use --no-hooks to skip hook installation or --dry-run to preview all writes.

Prefer no local installation?

docker run --rm -v "$(pwd):/workspace" ghcr.io/mrwogu/promptscript:latest validate --strict

Or open the playground and compile in the browser.

Define a Complete Agent Platform

.promptscript/project.prs:

@meta {
  id: "checkout-service"
  syntax: "1.5.0"
}

@identity {
  """
  You are working on the checkout service.
  Preserve transaction integrity and auditability.
  """
}

@standards {
  @header "Engineering Standards"
  code: ["Use strict TypeScript", "Test every business rule"]
}

@shortcuts {
  "/review": {
    prompt: true
    description: "Review current changes"
    content: "Review correctness, security, tests, and operational impact."
  }
}

@skills {
  security-review: {
    description: "Review payment changes for security risks"
    allowedTools: ["Read", "Grep", "Bash"]
    content: "Inspect authentication, authorization, secrets, and payment data handling."
  }
}

@mcpServers {
  issue-tracker: {
    transport: "stdio"
    command: ["node", "./tools/issues.mjs"]
  }
}

@agents {
  reviewer: {
    description: "Review changes before merge"
    tools: ["Read", "Grep", "Glob", "Bash"]
    skills: ["security-review"]
    mcpServers: ["issue-tracker"]
    content: "Review changed code, tests, and operational impact."
  }
}

@hooks {
  validate-changes: {
    event: "post-tool-use"
    matcher: "Edit|Write"
    command: ["pnpm", "run", "typecheck"]
  }
}

@workflows {
  release: {
    description: "Prepare a validated release"
    content: "Run quality gates, summarize changes, and prepare release metadata."
  }
}

@plugins {
  engineering: {
    description: "Shared engineering capabilities"
    version: "1.0.0"
    skills: ["security-review"]
    hooks: ["validate-changes"]
    mcpServers: ["issue-tracker"]
  }
}

promptscript.yaml:

id: checkout-service
syntax: '1.5.0'

input:
  entry: .promptscript/project.prs

targets:
  - github:
      version: multifile
  - claude:
      version: full
  - cursor:
      version: full
  - opencode:
      version: full
  - gemini:
      version: full

prs compile maps supported capabilities to files each platform already understands:

.github/copilot-instructions.md
.github/prompts/review.prompt.md
CLAUDE.md
.claude/agents/reviewer.md
.claude/skills/security-review/SKILL.md
.cursor/rules/project.mdc
.cursor/agents/reviewer.md
.opencode/agents/reviewer.md

One Language, Complete Platform

Capability	PromptScript source	Native result
Instructions and policy	`@identity`, `@context`, `@standards`, `@restrictions`, `@guards`	Main instructions and scoped rules
Portable skills	`@skills`	`SKILL.md` directories with references, assets, scripts, and contracts
Specialist agents	`@agents`	Native Markdown, TOML, or droid definitions with models, tools, skills, and MCP access
User commands	`@shortcuts`	Native prompts, slash commands, or documented shortcuts
Tool integrations	`@mcpServers`	Platform-specific JSON or TOML MCP configuration
Capability bundles	`@plugins`	Native plugin manifests where supported
Automation	`@hooks`, `@workflows`	Lifecycle hook configuration and workflow files
Monorepo delivery	`builds` in `promptscript.yaml`	Scoped output for packages, applications, and plugins

Target support stays explicit. Unsupported platform-specific capabilities are omitted rather than approximated with incompatible configuration.

Compose Instead of Copying

Build organization, team, and project layers with deterministic merge rules:

@inherit @company/platform
@use @team/backend
@use github.com/acme/agent-skills/database-review@1.3.0

@override standards.testing {
  ["Use Vitest", "Require 95% coverage"]
}

@extend standards {
  testing: ["Run integration tests in CI"]
}

@inherit creates a single-parent base chain.
@use composes multiple local, registry, Git, or Markdown resources.
@extend merges selected paths and supports skill-specific overlays.
@override atomically replaces one existing block or nested value.
@header customizes generated section titles without changing native schemas.
Typed parameters turn shared stacks into reusable templates.
Sealed properties, reference negation, and overlay drift warnings keep extension layers safe.
prs inspect <skill> shows property and layer provenance.

Remote imports are pinned in promptscript.lock with commit and integrity data. Vendor mode mirrors resolved dependencies into .promptscript/vendor/ for offline and air-gapped builds.

Portable Skills, Native Agents

PromptScript accepts inline skills, standalone Markdown skills, and complete skill directories:

.promptscript/skills/security-review/
├── SKILL.md
├── references/
│   └── threat-model.md
├── scripts/
│   └── scan.sh
└── assets/
    └── report-template.md

Import versioned skills without copy-paste:

@use github.com/acme/agent-skills/security-review@^2.0.0

prs skills add github.com/acme/agent-skills/security-review@2.1.0
prs skills update

PromptScript validates Agent Skills metadata, resolves dependencies and resources, then emits the native skill path for each selected platform. Agents can reference those skills and receive target-native model, reasoning, sandbox, tool, permission, and MCP settings.

48 Built-In Targets

PromptScript ships 48 output targets:

9 rich native formatters - Claude Code, GitHub Copilot, Cursor, Factory AI, Codex, Gemini CLI, OpenCode, Antigravity, and Grok
10 AGENTS.md targets - Aider, Amazon Q, Warp, Zed, Jules, Devin, Kimi, Mimo, Deep Agents, and ForgeCode
29 Markdown instruction targets - Windsurf, Cline, Roo Code, Continue, Augment, Goose, Kilo Code, OpenHands, Qwen Code, and more

See exact output paths and feature support in the formatter capability matrix.

Built for Repositories and Organizations

Git-native governance - review source and deterministic generated diffs in pull requests.
Private registries - share versioned standards through local, HTTP, or Git registries with SSH and token-based authentication.
Policy engine - enforce layer boundaries, property protection, and registry allowlists after resolution.
Reproducible builds - lockfile hashes, version pins, vendor mode, and strict validation.
Safe automation - lifecycle hook commands use arrays, while generated-file protection keeps agents pointed at .prs source.
Scoped monorepo builds - compile one package with prs build <name> or every profile with prs compile --all-builds.
CI-ready output - use prs validate --strict --format json, prs compile --dry-run, and prs diff.

Adopt Without a Rewrite

prs import CLAUDE.md
prs migrate --static --dry-run
prs migrate --static
prs migrate --llm

Import existing Claude Code, GitHub Copilot, Cursor, AGENTS.md, and other instruction files. Review the generated .prs source, preview output with prs compile --dry-run, then migrate targets at your own pace. Migration preserves existing PromptScript configuration and source instructions; if no candidates are detected, it changes nothing.

Targets with native skill support can also receive the bundled PromptScript language skill. This lets compatible agents read and maintain .prs files from plain-language requests. Disable it with includePromptScriptSkill: false.

Tooling

Online playground - edit source and inspect generated output in the browser
VS Code extension - syntax highlighting, bracket matching, folding, and file icons
Docker image - portable CLI for local use and CI
prs serve - connect the online playground to local files
prs compile --watch - recompile after editor changes
prs hooks install - integrate supported AI tools and protect generated files

Documentation

Resource	Description
Getting Started	First project from initialization to native output
Agent Platform	Skills, agents, MCP, plugins, hooks, workflows, and targets
Language Reference	Complete PromptScript syntax
CLI Reference	Commands and options
Configuration Reference	Targets, registries, builds, policies, and formatting
Anonymous Usage Telemetry	Collected fields, delivery, and opt-out controls
Upgrade 1.15 to 1.16	Syntax, block shape, and hook migration guide
Enterprise Guide	Organization-wide adoption and governance

Contributing

See CONTRIBUTING.md, CODE_OF_CONDUCT.md, and open issues.

PromptScript is available under the MIT License.

File tree

1541

mrwogu/promptscriptView on GitHub

.claude/
  agents/
    code-reviewer.md
    debugger.md
    prs-expert.md
  commands/
    build.md
    cli.md
    export.md
    newpkg.md
    quality.md
    refactor.md
    security-review.md
    test-coverage.md
    test-e2e.md
    test-integration.md
    test-unit.md
    test.md
    threat-model.md
    type.md
  rules/
    code-style.md
    testing.md
  settings.json
  skills/
    promptscript/
      SKILL.md
    skill-creator/
      agents/
        analyzer.md
        comparator.md
        grader.md
      assets/
        eval_review.html
      eval-viewer/
        generate_review.py
        viewer.html
      LICENSE.txt
      references/
        schemas.md
      scripts/
        __init__.py
        aggregate_benchmark.py
        generate_report.py
        improve_description.py
        package_skill.py
        quick_validate.py
        run_eval.py
        run_loop.py
        utils.py
      SKILL.md
  workflows/
    add-block-keyword.md
    new-task.md
    verify.md
.dockerignore
.editorconfig
.factory/
  commands/
    build.md
    cli.md
    export.md
    newpkg.md
    quality.md
    refactor.md
    security-review.md
    test-coverage.md
    test-e2e.md
    test-integration.md
    test-unit.md
    test.md
    threat-model.md
    type.md
  droids/
    code-reviewer.md
    debugger.md
    prs-expert.md
  hooks.json
  mcp.json
  plugins.json
  settings.json
  skills/
    promptscript/
      SKILL.md
    skill-creator/
      agents/
        analyzer.md
        comparator.md
        grader.md
      assets/
        eval_review.html
      eval-viewer/
        generate_review.py
        viewer.html
      LICENSE.txt
      references/
        schemas.md
      scripts/
        __init__.py
        aggregate_benchmark.py
        generate_report.py
        improve_description.py
        package_skill.py
        quick_validate.py
        run_eval.py
        run_loop.py
        utils.py
      SKILL.md
.github/
  agents/
    code-reviewer.md
    debugger.md
    prs-expert.md
  copilot-instructions.md
  dependabot.yml
  instructions/
    testing.instructions.md
    typescript.instructions.md
  ISSUE_TEMPLATE/
    bug_report.md
    feature_request.md
  prompts/
    build.prompt.md
    cli.prompt.md
    export.prompt.md
    newpkg.prompt.md
    quality.prompt.md
    refactor.prompt.md
    security-review.prompt.md
    test-coverage.prompt.md
    test-e2e.prompt.md
    test-integration.prompt.md
    test-unit.prompt.md
    test.prompt.md
    threat-model.prompt.md
    type.prompt.md
  PULL_REQUEST_TEMPLATE.md
  skills/
    promptscript/
      SKILL.md
    skill-creator/
      agents/
        analyzer.md
        comparator.md
        grader.md
      assets/
        eval_review.html
      eval-viewer/
        generate_review.py
        viewer.html
      LICENSE.txt
      references/
        schemas.md
      scripts/
        __init__.py
        aggregate_benchmark.py
        generate_report.py
        improve_description.py
        package_skill.py
        quick_validate.py
        run_eval.py
        run_loop.py
        utils.py
      SKILL.md
  workflows/
    ci.yml
    dependabot-auto-merge.yml
    docker-publish.yml
    docs.yml
    integration-tests.yml
    publish.yml
    release-please.yml
    vscode-extension.yml
.gitignore
.husky/
  pre-commit
.mcp.json
.nxignore
.prettierignore
.prettierrc
.promptscript/
  automation.prs
  commands.prs
  context.prs
  examples.prs
  graph.prs
  project.prs
  restrictions.prs
  scripts/
    graph-status.sh
    graph-update.sh
  skills/
    promptscript/
      SKILL.md
  standards.prs
  workflows.prs
.release-please-manifest.json
.verdaccio/
  config.yml
.vscode/
  extensions.json
  settings.json
AGENTS.md
apps/
  vscode/
    .vscodeignore
    icons/
      prs-icon.png
    language-configuration.json
    LICENSE
    package.json
    project.json
    README.md
    syntaxes/
      promptscript.tmLanguage.json
CHANGELOG.md
CLAUDE.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
docker-compose.yaml
Dockerfile
docs/
docs_extensions/
  __init__.py
  mkdocs_hooks.py
  promptscript_lexer.py
  pyproject.toml
  __snapshots__/
    docs/
      examples/
        agent-platform.md/
          checkout-agent-platform_L27/
            claude.md
            cursor.mdc
            github.md
          field-replacement_L145/
            claude.md
            cursor.mdc
            github.md
        agents.md/
          my-project_L24/
            claude.md
            cursor.mdc
            github.md
        custom-section-headers.md/
          localized-service_L10/
            claude.md
            cursor.mdc
            github.md
        enterprise.md/
          @acme/
            base_L88/
              claude.md
              cursor.mdc
              github.md
            compliance_L250/
              claude.md
              cursor.mdc
              github.md
            security_L157/
              claude.md
              cursor.mdc
              github.md
        fix-block-shapes.md/
          shape-remediation_L38/
            claude.md
            cursor.mdc
            github.md
        git-registry.md/
          @org/
            base_L341/
              claude.md
              cursor.mdc
              github.md
        index.md/
          api-service_L213/
            claude.md
            cursor.mdc
            github.md
          my-project_L146/
            claude.md
            cursor.mdc
            github.md
          react-app_L171/
            claude.md
            cursor.mdc
            github.md
        merge-vs-replace.md/
          merge-vs-replace_L10/
            claude.md
            cursor.mdc
            github.md
        minimal.md/
          minimal-example_L26/
            claude.md
            cursor.mdc
            github.md
        real-life-checkout-service.md/
          commerce-org-base_L66/
            claude.md
            cursor.mdc
            github.md
          payment-policy_L108/
            claude.md
            cursor.mdc
            github.md
        skills-and-local.md/
          my-fullstack-app_L30/
            claude.md
            cursor.mdc
            github.md
        team-setup.md/
          @team/
            frontend_L35/
              claude.md
              cursor.mdc
              github.md
      features/
        agents.md/
          agent-team_L11/
            claude.md
            cursor.mdc
            github.md
        index.md/
          checkout-service_L44/
            claude.md
            cursor.mdc
            github.md
      getting-started.md/
        api-service_L465/
          claude.md
          cursor.mdc
          github.md
        my-project_L144/
          claude.md
          cursor.mdc
          github.md
      guides/
        ai-migration-best-practices.md/
          api-service_L480/
            claude.md
            cursor.mdc
            github.md
          copilot-instructions-migration_L399/
            claude.md
            cursor.mdc
            github.md
          project-name_L221/
            claude.md
            cursor.mdc
            github.md
        enterprise.md/
          @org/
            base_L87/
              claude.md
              cursor.mdc
              github.md
            security_L142/
              claude.md
              cursor.mdc
              github.md
        examples.md/
          code-review-examples_L145/
            claude.md
            cursor.mdc
            github.md
          commit-style_L52/
            claude.md
            cursor.mdc
            github.md
          my-project_L235/
            claude.md
            cursor.mdc
            github.md
          my-project_L24/
            claude.md
            cursor.mdc
            github.md
          naming-examples_L194/
            claude.md
            cursor.mdc
            github.md
          project-skills_L108/
            claude.md
            cursor.mdc
            github.md
          refactoring-examples_L77/
            claude.md
            cursor.mdc
            github.md
        guard-dependencies.md/
          my-project_L31/
            claude.md
            cursor.mdc
            github.md
        inheritance.md/
          @company/
            base_L612/
              claude.md
              cursor.mdc
... 1515 more

FAQ

promptscript is a Claude Code plugin with 4 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes promptscript, skill-creator, promptscript. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is promptscript?: Agent platform configuration as code _Define instructions, skills, agents, MCP servers, hooks, workflows, and policies once.
How do I install promptscript?: Run these in Claude Code: npx -y skills add mrwogu/promptscript --agent claude-code. Then prompt normally.
Does promptscript auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is promptscript free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.