speckit-workflow
Complete Spec-Driven Development (SDD) orchestrator for OpenClaw. Initializes SpecKit and manages the full engineering lifecycle.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- speckit-workflow
- metadata
- { "author": "vinayak", "source": "custom/speckit-workflow" }
- description
- Complete Spec-Driven Development (SDD) orchestrator for OpenClaw. Initializes SpecKit and manages the full engineering lifecycle.
- compatibility
- Requires OpenClaw and a project repository
03 SKILL.md 正文
Speckit Workflow Skill 🦞
This is the master orchestrator for the SpecKit for OpenClaw engineering workflow.
⚠️ Security & Credentials
This workflow is designed to automate git operations to save progress and isolate work.
Agent Requirement: Before starting the workflow or initializing a new project, you MUST ask the user:
"Do you want to enable automated
git commit,git push, and branch creation for this project? (Yes/No)"
- If YES: Proceed with automated commits, pushes, and branch creation as described in the workflow. Ensure you have write access.
- If NO: You MUST NOT perform any git operations (commits, pushes, or branch creation). You will only write files locally. The user is responsible for version control.
🚀 Step 1: Initialization
If this project has not been initialized with SpecKit yet, you MUST ensure the .specify/ directory is present in the project root.
Initialization Instructions for Agent:
- Ask for Git Permission (see above).
- Check if
.specify/exists in the project root. - If missing, copy the
.specify/directory from this skill package (located at./.specify/) to.specify/in the project root.- Create the destination directory if it doesn't exist.
- Confirm successful initialization.
🔄 Resuming Workflow
Before starting or when returning to a project, you MUST determine the current state by checking for the existence of SpecKit artifacts:
- Check for Initialization: Verify if
.specify/exists. - Determine Current Phase:
- If
.specify/memory/constitution.mdexists -> Constitution complete. - If
specs/<feature>/spec.mdexists -> Specify complete. - If
specs/<feature>/plan.mdexists -> Plan complete. - If
specs/<feature>/tasks.mdexists -> Tasks complete. - If tasks in
tasks.mdare partially marked[X]-> Implementation in progress.
- If
Always resume from the first incomplete phase in the Execution Order.
🏗️ Step 2: Workflow Orchestration
Once initialized, you MUST follow the canonical Spec-kit order by delegating to sub-agents.
When to Create a Sub-Agent:
For each phase below, you should create or delegate to a specialized sub-agent that uses the corresponding skill found in the subskills/ directory relative to this skill file (./subskills/).
The Execution Order:
- 📜 Constitution: Delegate to
speckit-constitution. Establish code quality, testing standards, and architectural constraints. - 📝 Specify: Delegate to
speckit-specify. Transform requirements into a formalspec.md. - 🔍 Clarify (Optional): Delegate to
speckit-clarifyif the specification is ambiguous. - 🏗️ Plan: Delegate to
speckit-plan. Derive technical design and implementation architecture. - 📋 Tasks: Delegate to
speckit-tasks. Break the plan into actionable task lists. - ⚖️ Analyze (Optional): Delegate to
speckit-analyzefor cross-artifact consistency. - 👷 Implement: Delegate to
speckit-implement.
👷 Implementation Session Management
When executing the speckit-implement phase, you MUST:
- Isolate Context: Trigger a new agent session for implementation to ensure focus.
- Dynamic Task Chunking: Group tasks from
tasks.mddynamically based on requirements and complexity.- If tasks are small/simple, group 3-5 tasks (e.g., T001 to T005).
- If tasks are complex, group 1-2 tasks.
- Sub-Agent Execution: For each chunk, delegate to a sub-agent using
speckit-implement. - Commit & Push: After each successfully completed chunk, the sub-agent MUST commit and push the changes to the repository.
- Mark Completion: Ensure the sub-agent marks tasks as complete
[X]intasks.mdbefore returning. - Avoid Over-grouping: Do not group too many tasks in a single sub-agent session to maintain precision and manageable diffs.
User Provided Context
{{user_provided_context}}
Use this context to start or resume the workflow. If the project is not yet initialized, begin with Step 1: Initialization.
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.