Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Spec-driven development with OpenSpec CLI. Use when building features, migrations, refactors, or any structured development work. Manages proposal → specs → design → tasks → implementation workflows. Supports custom schemas (TDD, rapid, etc.). Trigger on requests involving feature planning, spec writing, change management, or when /opsx commands are mentioned.
Spec-driven development with OpenSpec CLI. Use when building features, migrations, refactors, or any structured development work. Manages proposal → specs → design → tasks → implementation workflows. Supports custom schemas (TDD, rapid, etc.). Trigger on requests involving feature planning, spec writing, change management, or when /opsx commands are mentioned.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
OpenSpec structures AI-assisted development into trackable changes with artifacts (proposal, specs, design, tasks) that guide implementation.
# Install globally npm install -g @fission-ai/openspec@latest # Initialize in a project cd /path/to/project openspec init --tools claude # Update after CLI upgrade openspec update
Each change follows: new → plan → apply → verify → archive
# Create change folder with default schema openspec new change <name> # With specific schema openspec new change <name> --schema tdd-driven
Use the CLI instructions command to get enriched prompts for each artifact: # Get instructions for next artifact openspec instructions --change <name> --json # Check progress openspec status --change <name> --json Artifact sequence (spec-driven schema): proposal.md — Why and what (intent, scope, approach) specs/ — Requirements + scenarios (Given/When/Then) design.md — Technical approach and architecture decisions tasks.md — Implementation checklist with checkboxes
Read tasks.md and work through items, marking [x] as complete.
openspec validate --change <name> --json Checks completeness, correctness, and coherence.
openspec archive <name> --yes Merges delta specs into main openspec/specs/ and moves change to archive.
When the user asks to build/migrate/refactor something with OpenSpec: Check project state: openspec list --json # Active changes openspec list --specs --json # Current specs openspec schemas --json # Available schemas Create the change: openspec new change <name> [--schema <schema>] For each artifact, get instructions and create the file: openspec instructions <artifact> --change <name> --json openspec status --change <name> --json Then write the artifact file to openspec/changes/<name>/. Implement tasks from tasks.md. Validate and archive: openspec validate <name> --json openspec archive <name> --yes
CommandPurposeopenspec list [--specs] [--json]List changes or specsopenspec show <name> [--json]Show change/spec detailsopenspec status --change <name> [--json]Artifact completion statusopenspec instructions [artifact] --change <name> [--json]Get enriched creation instructionsopenspec validate [name] [--all] [--json]Validate changes/specsopenspec archive <name> [--yes]Archive completed changeopenspec schemas [--json]List available schemasopenspec templates [--json]Show template pathsopenspec configView/modify settings Always use --json for programmatic/agent use.
Schemas define artifact sequences. Create custom ones for different workflows: # Fork built-in schema openspec schema fork spec-driven my-workflow # Create from scratch openspec schema init my-workflow # Validate openspec schema validate my-workflow Schema files live in openspec/schemas/<name>/schema.yaml with templates in templates/. For schema structure details, see references/schemas.md.
project/ ├── openspec/ │ ├── config.yaml # Project config (default schema, context, rules) │ ├── specs/ # Source of truth — current system behavior │ ├── changes/ # Active changes (one folder each) │ │ └── <change-name>/ │ │ ├── .openspec.yaml │ │ ├── proposal.md │ │ ├── specs/ # Delta specs (what's changing) │ │ ├── design.md │ │ └── tasks.md │ └── schemas/ # Custom schemas └── .claude/skills/ # Auto-generated Claude integration
Changes don't rewrite specs — they describe deltas (ADDED/MODIFIED/REMOVED) that merge into main specs on archive.
openspec/config.yaml sets defaults: schema: spec-driven # or tdd-driven, rapid, custom context: | Tech stack: TypeScript, React, Node.js Testing: Jest rules: proposal: - Include rollback plan specs: - Use Given/When/Then format
Workflow acceleration for inboxes, docs, calendars, planning, and execution loops.
Largest current source with strong distribution and engagement signals.