{ "schemaVersion": "1.0", "item": { "slug": "agentic-coding", "name": "Agentic Coding", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/agentic-coding", "canonicalUrl": "https://clawhub.ai/ivangdavila/agentic-coding", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agentic-coding", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentic-coding", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "handoff.md", "memory-template.md", "prompt-contracts.md", "protocol.md", "setup.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. 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. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "slug": "agentic-coding", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T15:11:38.922Z", "expiresAt": "2026-05-06T15:11:38.922Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentic-coding", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentic-coding", "contentDisposition": "attachment; filename=\"agentic-coding-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "agentic-coding" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/agentic-coding" }, "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/agentic-coding", "agentPageUrl": "https://openagent3.xyz/skills/agentic-coding/agent", "manifestUrl": "https://openagent3.xyz/skills/agentic-coding/agent.json", "briefUrl": "https://openagent3.xyz/skills/agentic-coding/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. 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. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Setup", "body": "If ~/agentic-coding/ does not exist or is empty, read setup.md, ask a concise kickoff question, and keep any persistence explicitly opt-in." }, { "title": "Positioning", "body": "This skill is intentionally different from agentic-engineering and vibe-coding:\n\nagentic-engineering focuses on multi-agent operating patterns and team throughput.\nvibe-coding focuses on prompt-led exploration and fast idea shipping.\nagentic-coding focuses on contract-first implementation, proof of fix, and reviewer-ready handoff." }, { "title": "When to Use", "body": "User needs merge-ready code from an AI agent with explicit quality gates. Use for production features, risky refactors, bug fixes with reproducible failures, and Xcode-centered work such as Swift feature delivery, iOS/macOS regressions, and release-branch hotfixes." }, { "title": "Architecture", "body": "Memory lives in ~/agentic-coding/. See memory-template.md for setup.\n\n~/agentic-coding/\n|- memory.md # Persistent preferences and operating mode\n|- contracts.md # Accepted task contracts and non-goals\n|- evidence.md # Test evidence and verification snapshots\n`- handoffs.md # Delivery notes and rollback hints" }, { "title": "Quick Reference", "body": "Load these files on demand to keep context focused and execution fast.\n\nTopicFileSetup processsetup.mdMemory templatememory-template.mdPACT loopprotocol.mdContract promptsprompt-contracts.mdMerge handoff checklisthandoff.md" }, { "title": "1. Lock a Contract Before Writing Code", "body": "Start every task with a compact contract:\n\nObjective: exact outcome in one sentence\nAcceptance: checks that prove success\nNon-goals: what must stay untouched\nConstraints: stack, style, limits, deadlines\n\nNo contract, no code." }, { "title": "2. Run the PACT Loop", "body": "Use the same execution loop every time:\n\nProblem framing: restate objective and assumptions\nAcceptance design: define checks before edits\nChange set: produce the smallest useful diff\nTrace and test: show evidence and residual risk\n\nThis skill is execution discipline, not brainstorming.\nFor Xcode workflows, tie acceptance to a concrete target, simulator/device, and test command before editing." }, { "title": "3. Keep Diffs Surgical", "body": "One user objective maps to one focused change set:\n\nPrefer file-local edits over broad rewrites\nSeparate behavior change from style cleanup\nAvoid hidden side effects outside declared scope\n\nIf scope grows, split into a second contract." }, { "title": "4. Prove Failure Then Prove Fix", "body": "For bugs and regressions:\n\nCapture the failing condition first (test, log, or reproduction)\nApply minimal fix\nRe-run the same check to prove resolution\n\nNever claim fixed without before and after evidence." }, { "title": "5. Deliver Handoff-Grade Output", "body": "End each cycle with a delivery packet:\n\nWhat changed and why\nFiles touched and blast radius\nValidation run and results\nKnown risks and rollback path\n\nIf handoff is unclear, the task is not finished." }, { "title": "6. Escalate With a Structured Fallback", "body": "When blocked after two failed attempts:\n\nStop editing\nState what was tried\nPropose two grounded alternatives\nRequest a decision with tradeoffs\n\nDo not keep guessing in loops." }, { "title": "Common Traps", "body": "Starting implementation without acceptance checks -> endless iteration and unclear done state.\nAsking the agent for full rewrites -> noisy diffs and avoidable regressions.\nMixing feature work with architecture overhaul -> weak reviewability and hard rollback.\nReporting success without reproducible evidence -> false confidence in production.\nTreating AI output as final draft -> quality debt moved to code review." }, { "title": "Security & Privacy", "body": "Data that leaves your machine:\n\nNone from this skill itself\n\nData that stays local:\n\nContracts, evidence notes, and handoff summaries in ~/agentic-coding/\n\nThis skill does NOT:\n\nTrigger undeclared network requests\nAccess files outside its own memory path\nWrite to global or platform memory stores\nAuto-approve risky code without explicit evidence" }, { "title": "Scope", "body": "This skill ONLY:\n\nImproves execution quality of AI-assisted coding\nEnforces contract driven implementation and verification\nProduces clear handoff packets for reviewers\n\nThis skill NEVER:\n\nReplaces security review for high risk domains\nEncourages blind trust in generated code\nOverrides project specific contribution rules" }, { "title": "Related Skills", "body": "Install with clawhub install if user confirms:\n\nagentic-engineering - Multi-agent collaboration and operating patterns.\ncoding - General coding support across stacks and tasks.\ncode - Broad code authoring and editing assistance.\ncopilot - Companion style IDE assistance patterns.\ndelegate - Structured task delegation to autonomous agents." }, { "title": "Feedback", "body": "If useful: clawhub star agentic-coding\nStay updated: clawhub sync" } ], "body": "Setup\n\nIf ~/agentic-coding/ does not exist or is empty, read setup.md, ask a concise kickoff question, and keep any persistence explicitly opt-in.\n\nPositioning\n\nThis skill is intentionally different from agentic-engineering and vibe-coding:\n\nagentic-engineering focuses on multi-agent operating patterns and team throughput.\nvibe-coding focuses on prompt-led exploration and fast idea shipping.\nagentic-coding focuses on contract-first implementation, proof of fix, and reviewer-ready handoff.\nWhen to Use\n\nUser needs merge-ready code from an AI agent with explicit quality gates. Use for production features, risky refactors, bug fixes with reproducible failures, and Xcode-centered work such as Swift feature delivery, iOS/macOS regressions, and release-branch hotfixes.\n\nArchitecture\n\nMemory lives in ~/agentic-coding/. See memory-template.md for setup.\n\n~/agentic-coding/\n|- memory.md # Persistent preferences and operating mode\n|- contracts.md # Accepted task contracts and non-goals\n|- evidence.md # Test evidence and verification snapshots\n`- handoffs.md # Delivery notes and rollback hints\n\nQuick Reference\n\nLoad these files on demand to keep context focused and execution fast.\n\nTopic\tFile\nSetup process\tsetup.md\nMemory template\tmemory-template.md\nPACT loop\tprotocol.md\nContract prompts\tprompt-contracts.md\nMerge handoff checklist\thandoff.md\nCore Rules\n1. Lock a Contract Before Writing Code\n\nStart every task with a compact contract:\n\nObjective: exact outcome in one sentence\nAcceptance: checks that prove success\nNon-goals: what must stay untouched\nConstraints: stack, style, limits, deadlines\n\nNo contract, no code.\n\n2. Run the PACT Loop\n\nUse the same execution loop every time:\n\nProblem framing: restate objective and assumptions\nAcceptance design: define checks before edits\nChange set: produce the smallest useful diff\nTrace and test: show evidence and residual risk\n\nThis skill is execution discipline, not brainstorming. For Xcode workflows, tie acceptance to a concrete target, simulator/device, and test command before editing.\n\n3. Keep Diffs Surgical\n\nOne user objective maps to one focused change set:\n\nPrefer file-local edits over broad rewrites\nSeparate behavior change from style cleanup\nAvoid hidden side effects outside declared scope\n\nIf scope grows, split into a second contract.\n\n4. Prove Failure Then Prove Fix\n\nFor bugs and regressions:\n\nCapture the failing condition first (test, log, or reproduction)\nApply minimal fix\nRe-run the same check to prove resolution\n\nNever claim fixed without before and after evidence.\n\n5. Deliver Handoff-Grade Output\n\nEnd each cycle with a delivery packet:\n\nWhat changed and why\nFiles touched and blast radius\nValidation run and results\nKnown risks and rollback path\n\nIf handoff is unclear, the task is not finished.\n\n6. Escalate With a Structured Fallback\n\nWhen blocked after two failed attempts:\n\nStop editing\nState what was tried\nPropose two grounded alternatives\nRequest a decision with tradeoffs\n\nDo not keep guessing in loops.\n\nCommon Traps\nStarting implementation without acceptance checks -> endless iteration and unclear done state.\nAsking the agent for full rewrites -> noisy diffs and avoidable regressions.\nMixing feature work with architecture overhaul -> weak reviewability and hard rollback.\nReporting success without reproducible evidence -> false confidence in production.\nTreating AI output as final draft -> quality debt moved to code review.\nSecurity & Privacy\n\nData that leaves your machine:\n\nNone from this skill itself\n\nData that stays local:\n\nContracts, evidence notes, and handoff summaries in ~/agentic-coding/\n\nThis skill does NOT:\n\nTrigger undeclared network requests\nAccess files outside its own memory path\nWrite to global or platform memory stores\nAuto-approve risky code without explicit evidence\nScope\n\nThis skill ONLY:\n\nImproves execution quality of AI-assisted coding\nEnforces contract driven implementation and verification\nProduces clear handoff packets for reviewers\n\nThis skill NEVER:\n\nReplaces security review for high risk domains\nEncourages blind trust in generated code\nOverrides project specific contribution rules\nRelated Skills\n\nInstall with clawhub install if user confirms:\n\nagentic-engineering - Multi-agent collaboration and operating patterns.\ncoding - General coding support across stacks and tasks.\ncode - Broad code authoring and editing assistance.\ncopilot - Companion style IDE assistance patterns.\ndelegate - Structured task delegation to autonomous agents.\nFeedback\nIf useful: clawhub star agentic-coding\nStay updated: clawhub sync" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/agentic-coding", "publisherUrl": "https://clawhub.ai/ivangdavila/agentic-coding", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agentic-coding", "downloadUrl": "https://openagent3.xyz/downloads/agentic-coding", "agentUrl": "https://openagent3.xyz/skills/agentic-coding/agent", "manifestUrl": "https://openagent3.xyz/skills/agentic-coding/agent.json", "briefUrl": "https://openagent3.xyz/skills/agentic-coding/agent.md" } }