Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Treat project context as a managed artifact alongside code. Use structured context documents (product.md, tech-stack.md, workflow.md) to enable consistent AI interactions and team alignment. Essential for projects using AI-assisted development.
Treat project context as a managed artifact alongside code. Use structured context documents (product.md, tech-stack.md, workflow.md) to enable consistent AI interactions and team alignment. Essential for projects using AI-assisted development.
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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Treat project context as a first-class artifact managed alongside code. Instead of relying on ad-hoc prompts or scattered documentation, establish a persistent, structured foundation that informs all AI interactions.
npx clawhub@latest install context-driven-development
Creates and maintains a set of context documents that: Define what you're building and why (product.md) Specify technology choices and constraints (tech-stack.md) Establish how the team works (workflow.md) Track what's happening (tracks.md)
Use for: Setting up new projects with AI-assisted development Onboarding team members to existing codebases Ensuring consistent AI behavior across sessions Documenting decisions that affect code generation Managing projects with multiple contributors or AI assistants Skip for: Solo experiments or throwaway prototypes Single-file scripts Projects without AI assistance Keywords: context, project setup, documentation, AI alignment, team workflow, product vision, tech stack
Context precedes code. Living documentation. Single source of truth. AI alignment. Context precedes code โ Define what you're building and how before implementation Living documentation โ Context artifacts evolve with the project Single source of truth โ One canonical location for each type of information AI alignment โ Consistent context produces consistent AI behavior
Context โ Spec & Plan โ Implement Context Phase: Establish or verify project context artifacts exist and are current Specification Phase: Define requirements and acceptance criteria for work units Planning Phase: Break specifications into phased, actionable tasks Implementation Phase: Execute tasks following established workflow patterns
Purpose: Captures product vision, goals, target users, and business context. Contents: Product name and one-line description Problem statement and solution approach Target user personas Core features and capabilities Success metrics and KPIs Product roadmap (high-level) Update when: Product vision or goals change New major features are planned Target audience shifts
Purpose: Documents technology choices, dependencies, and architectural decisions. Contents: Primary languages and frameworks Key dependencies with versions Infrastructure and deployment targets Development tools and environment Testing frameworks Code quality tools Update when: Adding new dependencies Upgrading major versions Changing infrastructure Adopting new tools or patterns
Purpose: Establishes development practices, quality gates, and team workflows. Contents: Development methodology (TDD, trunk-based, etc.) Git workflow and commit conventions Code review requirements Testing requirements and coverage targets Quality assurance gates Deployment procedures Update when: Team practices evolve Quality standards change New workflow patterns are adopted
Purpose: Registry of all work units with status and metadata. Contents: Active tracks with current status Completed tracks with completion dates Track metadata (type, priority, assignee) Links to individual track specs Update when: New work starts Work status changes Work completes
context/ โโโ product.md # Product vision and goals โโโ tech-stack.md # Technology choices โโโ workflow.md # Development practices โโโ tracks.md # Work unit registry โโโ styleguides/ # Language-specific conventions โโโ python.md โโโ typescript.md โโโ ...
For new projects, create all artifacts from scratch: Create context/product.md: Define the problem you're solving Describe target users List core features for v1 Define success metrics Create context/tech-stack.md: Choose languages and frameworks Document key dependencies with versions Specify infrastructure targets List development tools Create context/workflow.md: Define branching strategy Set commit conventions Establish testing requirements Document deployment process Create context/tracks.md: Start with empty registry Add work units as they're created
For existing codebases, extract context from what exists: Analyze the codebase: Read package.json, requirements.txt, go.mod, etc. Look at existing README and docs Check git history for patterns Create context/tech-stack.md: Document discovered dependencies Note infrastructure from configs (Docker, CI, etc.) Create context/product.md: Infer product purpose from code Document current feature set Note any README content Create context/workflow.md: Document existing practices Note any established patterns
Changes in one artifact should reflect in related documents: New feature in product.md โ Update tech-stack.md if new dependencies needed Completed track โ Update product.md to reflect new capabilities Workflow change โ Update all affected track plans
Before adding any new dependency: Check if existing dependencies solve the need Document the rationale for new dependencies Add version constraints Note any configuration requirements
Before starting any work: Read all context artifacts Flag any outdated information Propose updates before proceeding Confirm context accuracy
Before starting implementation, validate: Product Context: product.md reflects current vision Target users are accurately described Feature list is up to date Technical Context: tech-stack.md lists all current dependencies Version numbers are accurate Infrastructure targets are correct Workflow Context: workflow.md describes current practices Quality gates are defined Commit conventions are documented
Anti-PatternProblemFixStale ContextDocuments become outdated and misleadingUpdate context as part of each track's completionContext SprawlInformation scattered across multiple locationsUse defined artifact structure; resist new document typesImplicit ContextRelying on knowledge not captured in artifactsIf referenced repeatedly, add to appropriate artifactOver-SpecificationContext so detailed it's impossible to maintainKeep focused on decisions affecting AI behavior and team alignment
Read context/product.md to orient yourself Check context/tracks.md for active work Read relevant track specs for current task Verify context artifacts are current
Update track status with current progress Note any blockers or decisions made Commit in-progress work with clear status Update tracks.md if status changed
Team Alignment: New team members onboard faster with explicit context Consistent terminology across the team Shared understanding of product goals AI Consistency: AI assistants produce aligned outputs across sessions Reduced need to re-explain context Predictable behavior based on documented standards Institutional Memory: Decisions and rationale are preserved Context survives team changes Historical context informs future decisions
NEVER start implementation without reading context โ context precedes code NEVER add dependencies without updating tech-stack.md โ keep the source of truth current NEVER let context documents get stale โ update them as part of completing work NEVER scatter context across ad-hoc documents โ use the defined structure NEVER assume AI remembers previous sessions โ context must be in artifacts NEVER skip context for "quick" changes โ small changes compound into drift
Workflow acceleration for inboxes, docs, calendars, planning, and execution loops.
Largest current source with strong distribution and engagement signals.