More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    sdd openspec planner

    1

    Enforce spec-driven development by generating OpenSpec artifacts and mandatory human-in-the-loop approval gates.

    Free

    1 useSecurity scanned
    sdd openspec planner

    sdd openspec planner

    Example session with this skill installed

    I need to add a dark mode toggle to our React dashboard. Plan the change using OpenSpec.

    • Read your context and instructions
    • Compiled the sdd openspec planner
    • Generated the document

    I have researched the dashboard architecture and created the OpenSpec planning artifacts at openspec/changes/add-dark-mode-toggle/.

    Plan: Add Dark Mode Toggle to React Dashboard

    Files created at: openspec/changes/add-dark-mode-toggle/

    This plan covers the implementation of a theme provider, a persistence layer for user preference, and the UI toggle component. We will use the existing Tailwind configuration for styling and a Context API approach for state management.


    Proposal

    Intent: Improve accessibility and user comfort by allowing a switch between light and dark themes.
    Change classification: New feature with behavior modification to existing UI components.
    Scope:

    • In: ThemeProvider, toggle component, Tailwind dark-mode config, localStorage persistence.
    • Out: Automatic system-theme detection (v2), per-page theme overrides.

    Phase 1: Core Infrastructure

    Setup the theme state and configuration.

    Steps

    1. Configure tailwind.config.js to use the class strategy for dark mode.
    2. Create ThemeContext.tsx and a custom hook useTheme.

    Deliverables

    • openspec/changes/add-dark-mode-toggle/design.md (updated)
    • src/context/ThemeContext.tsx (planned)

    Human Approval Gate (Mandatory)

    • GATE 1: STOP. Present the Tailwind config and Context provider design to the human. Do not begin Phase 2 without approval.

    Specs (Delta Specs)

    ADDED Requirements

    • Theme Persistence: The system SHALL store the user's theme selection in localStorage.
      • Scenario: Given a user selects "Dark", When the page reloads, Then the theme SHALL remain "Dark".

    Design Decisions

    Tailwind Class Strategy: Chose class over media to give users explicit control rather than relying solely on OS settings.

    • React Context: Chose Context API over Redux for theme state to minimize boilerplate for a simple global string.

    Next steps

    1. Review the generated tasks.md in the openspec/ folder.
    2. Approve Phase 1 to allow the implementation agent to begin.
    3. Verify the tailwind.config.js requirements in the specs.

    ThemeContext.tsx

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    When complex features fail during implementation, the root cause is often ambiguous requirements or lack of human oversight. This skill enforces a strict, spec-driven development (SDD) workflow using the OpenSpec framework. It prevents "autopilot" errors by requiring architectural research and human approval at every phase.

    What it does

    • Multi-artifact generation creates a complete set of planning files including proposals, technical designs, and task checklists.
    • Automated research inventories existing features, dependencies, and data flows before proposing any changes.
    • Execution guardrails embed non-negotiable human-in-the-loop gates directly into the task files for the implementation agent.
    • Delta specifications define precise behavior changes using Given, When, and Then scenarios.
    • Architecture assessment evaluates SOLID principles, design patterns, and TDD feasibility for every change.

    How it works

    1. Discovery: The agent researches the codebase and classifies the request as a bug fix, refactor, or new feature.
    2. Artifact Creation: It writes the proposal.md, design.md, specs/, and tasks.md files to the openspec/ directory.
    3. Guardrail Embedding: A verbatim set of execution rules is injected into the checklist to ensure the next agent pauses for approval.
    4. Human Review: You review the generated artifacts and provide feedback or approval before any code is touched.

    Frameworks & tools

    This skill implements the OpenSpec SDD framework. It is designed to work with any language or framework, specifically targeting environments where an implementation agent (like Claude Code or Cursor) will execute the resulting Markdown-based tasks.

    Why this beats prompting it yourself

    Generic prompts often lead to agents jumping straight into code, missing edge cases or breaking existing patterns. This skill forces a professional SDD workflow that produces permanent documentation and prevents autonomous agents from bypassing your approval gates.

    Use cases

    • Planning complex feature additions in large, unfamiliar codebases.
    • Managing safe refactoring projects that must preserve observable behavior.
    • Documenting technical debt and migration paths with clear success criteria.
    • Orchestrating multi-agent handoffs between a planner and an implementer.

    Known limitations

    This skill only produces plans and artifacts; it never writes or modifies application code. It requires an environment that supports file-writing tools.

    The skill is strictly for planning and writing documentation; it will not execute code or perform implementation. Requires file-system access to create the /openspec/ directory.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The planner generates a structured 'openspec/' directory containing a proposal, technical design, behavior-driven specs, and a task checklist, all designed to guide subsequent implementation agents.

    This skill acts as a standalone planning architect; it is compatible with any implementation agent that can read Markdown, including Claude Code, Cursor, and Windsurf.

    Unlike generic prompting, this skill forces the agent to conduct exhaustive codebase research and hardcode 'human-in-the-loop' gates that prevent implementation agents from proceeding without your sign-off.

    No, this skill is strictly for the planning and architectural phase; it identifies what needs to be changed and how, but it never modifies your source code directly to ensure 100% safety.

    You will receive the complete prompt logic for the OpenSpec planning agent, a set of Markdown templates for the artifacts, and a guide on integrating the 'human-in-the-loop' gates into your workflow.

    New in Agents & Orchestration