{
  "schemaVersion": "1.0",
  "item": {
    "slug": "context-driven-development",
    "name": "Context Driven Development",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/wpank/context-driven-development",
    "canonicalUrl": "https://clawhub.ai/wpank/context-driven-development",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/context-driven-development",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=context-driven-development",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "templates/product.md",
      "templates/workflow.md",
      "templates/tech-stack.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "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."
        },
        {
          "label": "Upgrade existing",
          "body": "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."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/context-driven-development"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/context-driven-development",
    "agentPageUrl": "https://openagent3.xyz/skills/context-driven-development/agent",
    "manifestUrl": "https://openagent3.xyz/skills/context-driven-development/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/context-driven-development/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "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."
      },
      {
        "label": "Upgrade existing",
        "body": "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."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Context-Driven Development",
        "body": "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."
      },
      {
        "title": "OpenClaw / Moltbot / Clawbot",
        "body": "npx clawhub@latest install context-driven-development"
      },
      {
        "title": "WHAT This Skill Does",
        "body": "Creates and maintains a set of context documents that:\n\nDefine what you're building and why (product.md)\nSpecify technology choices and constraints (tech-stack.md)\nEstablish how the team works (workflow.md)\nTrack what's happening (tracks.md)"
      },
      {
        "title": "WHEN to Use",
        "body": "Use for:\n\nSetting up new projects with AI-assisted development\nOnboarding team members to existing codebases\nEnsuring consistent AI behavior across sessions\nDocumenting decisions that affect code generation\nManaging projects with multiple contributors or AI assistants\n\nSkip for:\n\nSolo experiments or throwaway prototypes\nSingle-file scripts\nProjects without AI assistance\n\nKeywords: context, project setup, documentation, AI alignment, team workflow, product vision, tech stack"
      },
      {
        "title": "Core Philosophy",
        "body": "Context precedes code.\nLiving documentation.\nSingle source of truth.\nAI alignment.\n\nContext precedes code — Define what you're building and how before implementation\nLiving documentation — Context artifacts evolve with the project\nSingle source of truth — One canonical location for each type of information\nAI alignment — Consistent context produces consistent AI behavior"
      },
      {
        "title": "The Workflow",
        "body": "Context → Spec & Plan → Implement\n\nContext Phase: Establish or verify project context artifacts exist and are current\nSpecification Phase: Define requirements and acceptance criteria for work units\nPlanning Phase: Break specifications into phased, actionable tasks\nImplementation Phase: Execute tasks following established workflow patterns"
      },
      {
        "title": "product.md — WHAT and WHY",
        "body": "Purpose: Captures product vision, goals, target users, and business context.\n\nContents:\n\nProduct name and one-line description\nProblem statement and solution approach\nTarget user personas\nCore features and capabilities\nSuccess metrics and KPIs\nProduct roadmap (high-level)\n\nUpdate when:\n\nProduct vision or goals change\nNew major features are planned\nTarget audience shifts"
      },
      {
        "title": "tech-stack.md — WITH WHAT",
        "body": "Purpose: Documents technology choices, dependencies, and architectural decisions.\n\nContents:\n\nPrimary languages and frameworks\nKey dependencies with versions\nInfrastructure and deployment targets\nDevelopment tools and environment\nTesting frameworks\nCode quality tools\n\nUpdate when:\n\nAdding new dependencies\nUpgrading major versions\nChanging infrastructure\nAdopting new tools or patterns"
      },
      {
        "title": "workflow.md — HOW to Work",
        "body": "Purpose: Establishes development practices, quality gates, and team workflows.\n\nContents:\n\nDevelopment methodology (TDD, trunk-based, etc.)\nGit workflow and commit conventions\nCode review requirements\nTesting requirements and coverage targets\nQuality assurance gates\nDeployment procedures\n\nUpdate when:\n\nTeam practices evolve\nQuality standards change\nNew workflow patterns are adopted"
      },
      {
        "title": "tracks.md — WHAT'S HAPPENING",
        "body": "Purpose: Registry of all work units with status and metadata.\n\nContents:\n\nActive tracks with current status\nCompleted tracks with completion dates\nTrack metadata (type, priority, assignee)\nLinks to individual track specs\n\nUpdate when:\n\nNew work starts\nWork status changes\nWork completes"
      },
      {
        "title": "Directory Structure",
        "body": "context/\n├── product.md            # Product vision and goals\n├── tech-stack.md         # Technology choices\n├── workflow.md           # Development practices\n├── tracks.md             # Work unit registry\n└── styleguides/          # Language-specific conventions\n    ├── python.md\n    ├── typescript.md\n    └── ..."
      },
      {
        "title": "Setup: New Project (Greenfield)",
        "body": "For new projects, create all artifacts from scratch:\n\nCreate context/product.md:\n\nDefine the problem you're solving\nDescribe target users\nList core features for v1\nDefine success metrics\n\n\n\nCreate context/tech-stack.md:\n\nChoose languages and frameworks\nDocument key dependencies with versions\nSpecify infrastructure targets\nList development tools\n\n\n\nCreate context/workflow.md:\n\nDefine branching strategy\nSet commit conventions\nEstablish testing requirements\nDocument deployment process\n\n\n\nCreate context/tracks.md:\n\nStart with empty registry\nAdd work units as they're created"
      },
      {
        "title": "Setup: Existing Project (Brownfield)",
        "body": "For existing codebases, extract context from what exists:\n\nAnalyze the codebase:\n\nRead package.json, requirements.txt, go.mod, etc.\nLook at existing README and docs\nCheck git history for patterns\n\n\n\nCreate context/tech-stack.md:\n\nDocument discovered dependencies\nNote infrastructure from configs (Docker, CI, etc.)\n\n\n\nCreate context/product.md:\n\nInfer product purpose from code\nDocument current feature set\nNote any README content\n\n\n\nCreate context/workflow.md:\n\nDocument existing practices\nNote any established patterns"
      },
      {
        "title": "Keep Artifacts Synchronized",
        "body": "Changes in one artifact should reflect in related documents:\n\nNew feature in product.md → Update tech-stack.md if new dependencies needed\nCompleted track → Update product.md to reflect new capabilities\nWorkflow change → Update all affected track plans"
      },
      {
        "title": "Update tech-stack.md When Adding Dependencies",
        "body": "Before adding any new dependency:\n\nCheck if existing dependencies solve the need\nDocument the rationale for new dependencies\nAdd version constraints\nNote any configuration requirements"
      },
      {
        "title": "Verify Context Before Implementation",
        "body": "Before starting any work:\n\nRead all context artifacts\nFlag any outdated information\nPropose updates before proceeding\nConfirm context accuracy"
      },
      {
        "title": "Validation Checklist",
        "body": "Before starting implementation, validate:\n\nProduct Context:\n\nproduct.md reflects current vision\n Target users are accurately described\n Feature list is up to date\n\nTechnical Context:\n\ntech-stack.md lists all current dependencies\n Version numbers are accurate\n Infrastructure targets are correct\n\nWorkflow Context:\n\nworkflow.md describes current practices\n Quality gates are defined\n Commit conventions are documented"
      },
      {
        "title": "Anti-Patterns",
        "body": "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"
      },
      {
        "title": "Starting a New Session",
        "body": "Read context/product.md to orient yourself\nCheck context/tracks.md for active work\nRead relevant track specs for current task\nVerify context artifacts are current"
      },
      {
        "title": "Ending a Session",
        "body": "Update track status with current progress\nNote any blockers or decisions made\nCommit in-progress work with clear status\nUpdate tracks.md if status changed"
      },
      {
        "title": "Benefits",
        "body": "Team Alignment:\n\nNew team members onboard faster with explicit context\nConsistent terminology across the team\nShared understanding of product goals\n\nAI Consistency:\n\nAI assistants produce aligned outputs across sessions\nReduced need to re-explain context\nPredictable behavior based on documented standards\n\nInstitutional Memory:\n\nDecisions and rationale are preserved\nContext survives team changes\nHistorical context informs future decisions"
      },
      {
        "title": "NEVER Do",
        "body": "NEVER start implementation without reading context — context precedes code\nNEVER add dependencies without updating tech-stack.md — keep the source of truth current\nNEVER let context documents get stale — update them as part of completing work\nNEVER scatter context across ad-hoc documents — use the defined structure\nNEVER assume AI remembers previous sessions — context must be in artifacts\nNEVER skip context for \"quick\" changes — small changes compound into drift"
      }
    ],
    "body": "Context-Driven Development\n\nTreat 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.\n\nInstallation\nOpenClaw / Moltbot / Clawbot\nnpx clawhub@latest install context-driven-development\n\nWHAT This Skill Does\n\nCreates and maintains a set of context documents that:\n\nDefine what you're building and why (product.md)\nSpecify technology choices and constraints (tech-stack.md)\nEstablish how the team works (workflow.md)\nTrack what's happening (tracks.md)\nWHEN to Use\n\nUse for:\n\nSetting up new projects with AI-assisted development\nOnboarding team members to existing codebases\nEnsuring consistent AI behavior across sessions\nDocumenting decisions that affect code generation\nManaging projects with multiple contributors or AI assistants\n\nSkip for:\n\nSolo experiments or throwaway prototypes\nSingle-file scripts\nProjects without AI assistance\n\nKeywords: context, project setup, documentation, AI alignment, team workflow, product vision, tech stack\n\nCore Philosophy\nContext precedes code.\nLiving documentation.\nSingle source of truth.\nAI alignment.\n\nContext precedes code — Define what you're building and how before implementation\nLiving documentation — Context artifacts evolve with the project\nSingle source of truth — One canonical location for each type of information\nAI alignment — Consistent context produces consistent AI behavior\nThe Workflow\nContext → Spec & Plan → Implement\n\nContext Phase: Establish or verify project context artifacts exist and are current\nSpecification Phase: Define requirements and acceptance criteria for work units\nPlanning Phase: Break specifications into phased, actionable tasks\nImplementation Phase: Execute tasks following established workflow patterns\nThe Context Documents\nproduct.md — WHAT and WHY\n\nPurpose: Captures product vision, goals, target users, and business context.\n\nContents:\n\nProduct name and one-line description\nProblem statement and solution approach\nTarget user personas\nCore features and capabilities\nSuccess metrics and KPIs\nProduct roadmap (high-level)\n\nUpdate when:\n\nProduct vision or goals change\nNew major features are planned\nTarget audience shifts\ntech-stack.md — WITH WHAT\n\nPurpose: Documents technology choices, dependencies, and architectural decisions.\n\nContents:\n\nPrimary languages and frameworks\nKey dependencies with versions\nInfrastructure and deployment targets\nDevelopment tools and environment\nTesting frameworks\nCode quality tools\n\nUpdate when:\n\nAdding new dependencies\nUpgrading major versions\nChanging infrastructure\nAdopting new tools or patterns\nworkflow.md — HOW to Work\n\nPurpose: Establishes development practices, quality gates, and team workflows.\n\nContents:\n\nDevelopment methodology (TDD, trunk-based, etc.)\nGit workflow and commit conventions\nCode review requirements\nTesting requirements and coverage targets\nQuality assurance gates\nDeployment procedures\n\nUpdate when:\n\nTeam practices evolve\nQuality standards change\nNew workflow patterns are adopted\ntracks.md — WHAT'S HAPPENING\n\nPurpose: Registry of all work units with status and metadata.\n\nContents:\n\nActive tracks with current status\nCompleted tracks with completion dates\nTrack metadata (type, priority, assignee)\nLinks to individual track specs\n\nUpdate when:\n\nNew work starts\nWork status changes\nWork completes\nDirectory Structure\ncontext/\n├── product.md            # Product vision and goals\n├── tech-stack.md         # Technology choices\n├── workflow.md           # Development practices\n├── tracks.md             # Work unit registry\n└── styleguides/          # Language-specific conventions\n    ├── python.md\n    ├── typescript.md\n    └── ...\n\nSetup: New Project (Greenfield)\n\nFor new projects, create all artifacts from scratch:\n\nCreate context/product.md:\n\nDefine the problem you're solving\nDescribe target users\nList core features for v1\nDefine success metrics\n\nCreate context/tech-stack.md:\n\nChoose languages and frameworks\nDocument key dependencies with versions\nSpecify infrastructure targets\nList development tools\n\nCreate context/workflow.md:\n\nDefine branching strategy\nSet commit conventions\nEstablish testing requirements\nDocument deployment process\n\nCreate context/tracks.md:\n\nStart with empty registry\nAdd work units as they're created\nSetup: Existing Project (Brownfield)\n\nFor existing codebases, extract context from what exists:\n\nAnalyze the codebase:\n\nRead package.json, requirements.txt, go.mod, etc.\nLook at existing README and docs\nCheck git history for patterns\n\nCreate context/tech-stack.md:\n\nDocument discovered dependencies\nNote infrastructure from configs (Docker, CI, etc.)\n\nCreate context/product.md:\n\nInfer product purpose from code\nDocument current feature set\nNote any README content\n\nCreate context/workflow.md:\n\nDocument existing practices\nNote any established patterns\nMaintenance Principles\nKeep Artifacts Synchronized\n\nChanges in one artifact should reflect in related documents:\n\nNew feature in product.md → Update tech-stack.md if new dependencies needed\nCompleted track → Update product.md to reflect new capabilities\nWorkflow change → Update all affected track plans\nUpdate tech-stack.md When Adding Dependencies\n\nBefore adding any new dependency:\n\nCheck if existing dependencies solve the need\nDocument the rationale for new dependencies\nAdd version constraints\nNote any configuration requirements\nVerify Context Before Implementation\n\nBefore starting any work:\n\nRead all context artifacts\nFlag any outdated information\nPropose updates before proceeding\nConfirm context accuracy\nValidation Checklist\n\nBefore starting implementation, validate:\n\nProduct Context:\n\n product.md reflects current vision\n Target users are accurately described\n Feature list is up to date\n\nTechnical Context:\n\n tech-stack.md lists all current dependencies\n Version numbers are accurate\n Infrastructure targets are correct\n\nWorkflow Context:\n\n workflow.md describes current practices\n Quality gates are defined\n Commit conventions are documented\nAnti-Patterns\nAnti-Pattern\tProblem\tFix\nStale Context\tDocuments become outdated and misleading\tUpdate context as part of each track's completion\nContext Sprawl\tInformation scattered across multiple locations\tUse defined artifact structure; resist new document types\nImplicit Context\tRelying on knowledge not captured in artifacts\tIf referenced repeatedly, add to appropriate artifact\nOver-Specification\tContext so detailed it's impossible to maintain\tKeep focused on decisions affecting AI behavior and team alignment\nSession Continuity\nStarting a New Session\nRead context/product.md to orient yourself\nCheck context/tracks.md for active work\nRead relevant track specs for current task\nVerify context artifacts are current\nEnding a Session\nUpdate track status with current progress\nNote any blockers or decisions made\nCommit in-progress work with clear status\nUpdate tracks.md if status changed\nBenefits\n\nTeam Alignment:\n\nNew team members onboard faster with explicit context\nConsistent terminology across the team\nShared understanding of product goals\n\nAI Consistency:\n\nAI assistants produce aligned outputs across sessions\nReduced need to re-explain context\nPredictable behavior based on documented standards\n\nInstitutional Memory:\n\nDecisions and rationale are preserved\nContext survives team changes\nHistorical context informs future decisions\nNEVER Do\nNEVER start implementation without reading context — context precedes code\nNEVER add dependencies without updating tech-stack.md — keep the source of truth current\nNEVER let context documents get stale — update them as part of completing work\nNEVER scatter context across ad-hoc documents — use the defined structure\nNEVER assume AI remembers previous sessions — context must be in artifacts\nNEVER skip context for \"quick\" changes — small changes compound into drift"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wpank/context-driven-development",
    "publisherUrl": "https://clawhub.ai/wpank/context-driven-development",
    "owner": "wpank",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/context-driven-development",
    "downloadUrl": "https://openagent3.xyz/downloads/context-driven-development",
    "agentUrl": "https://openagent3.xyz/skills/context-driven-development/agent",
    "manifestUrl": "https://openagent3.xyz/skills/context-driven-development/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/context-driven-development/agent.md"
  }
}