{ "schemaVersion": "1.0", "item": { "slug": "solo-plan", "name": "Plan", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/fortunto2/solo-plan", "canonicalUrl": "https://clawhub.ai/fortunto2/solo-plan", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/solo-plan", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=solo-plan", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.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", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.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/solo-plan" }, "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/solo-plan", "agentPageUrl": "https://openagent3.xyz/skills/solo-plan/agent", "manifestUrl": "https://openagent3.xyz/skills/solo-plan/agent.json", "briefUrl": "https://openagent3.xyz/skills/solo-plan/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": "/plan", "body": "This skill is self-contained — follow the steps below instead of delegating to external planning skills (superpowers, etc.).\n\nResearch the codebase and create a spec + phased implementation plan. Zero interactive questions — explores the code instead." }, { "title": "When to use", "body": "Creates a track for any feature, bug fix, or refactor with a concrete, file-level implementation plan. Works with or without /setup." }, { "title": "MCP Tools (use if available)", "body": "session_search(query) — find similar past work in Claude Code chat history\nproject_code_search(query, project) — find reusable code across projects\ncodegraph_query(query) — check dependencies of affected files\ncodegraph_explain(project) — architecture overview: stack, languages, directory layers, key patterns, top dependencies, hub files\nkb_search(query) — search knowledge base for relevant methodology\n\nIf MCP tools are not available, fall back to Glob + Grep + Read." }, { "title": "Steps", "body": "Parse task description from $ARGUMENTS.\n\nIf empty, ask via AskUserQuestion: \"What feature, bug, or refactor do you want to plan?\"\nThis is the ONE question maximum.\n\n\n\nDetect context — determine where plan files should be stored:\nProject context (normal project with code):\n\nDetected by: package.json, pyproject.toml, Cargo.toml, *.xcodeproj, or build.gradle.kts exists in working directory\nPlan path: docs/plan/{trackId}/\n\nKnowledge base context (documentation-centric project):\n\nDetected by: NO package manifest found, BUT directories like docs/, notes/, or structured numbered directories exist\nPlan path: docs/plan/{shortname}/\nNote: the shortname is derived from the task (kebab-case, no date suffix for the directory)\n\nSet $PLAN_ROOT based on detected context. All subsequent file paths use $PLAN_ROOT.\n\n\nLoad project context (parallel reads):\n\nCLAUDE.md — architecture, constraints, Do/Don't\ndocs/prd.md — what the product does (if exists)\ndocs/workflow.md — TDD policy, commit strategy (if exists)\npackage.json or pyproject.toml — stack, versions, deps\n\n\n\nAuto-classify track type from keywords in task description:\n\nContains \"fix\", \"bug\", \"broken\", \"error\", \"crash\" → bug\nContains \"refactor\", \"cleanup\", \"reorganize\", \"migrate\" → refactor\nContains \"update\", \"upgrade\", \"bump\" → chore\nDefault → feature\n\n\n\nResearch phase — explore the codebase to understand what needs to change:\na. Get architecture overview (if MCP available — do this FIRST):\ncodegraph_explain(project=\"{project name from CLAUDE.md or directory name}\")\n\nGives you: stack, languages, directory layers, key patterns, top dependencies, hub files.\nb. Find relevant files — Glob + Grep for patterns related to the task:\n\nSearch for keywords from the task description\nLook at directory structure to understand architecture\nIdentify files that will need modification\n\nc. Precedent retrieval (context graph pattern — search past solutions BEFORE planning):\n\nSearch past sessions (if MCP available):\nsession_search(query=\"{task description keywords}\")\n\nLook for: how similar tasks were solved, what went wrong, what patterns worked.\nSearch KB for relevant methodology:\nkb_search(query=\"{task type}: {keywords}\")\n\nCheck for: harness patterns, architectural constraints, quality scores.\n\nd. Search code across projects (if MCP available):\nproject_code_search(query=\"{relevant pattern}\")\n\ne. Check dependencies of affected files (if MCP available):\ncodegraph_query(query=\"MATCH (f:File {path: '{file}'})-[:IMPORTS]->(dep) RETURN dep.path\")\n\nf. Read existing tests in the affected area — understand testing patterns used.\ng. Read CLAUDE.md architecture constraints — understand boundaries and conventions.\n\nCheck for harness section: module boundaries, data validation rules, lint configs.\nRead docs/ARCHITECTURE.md and docs/QUALITY_SCORE.md if they exist.\n\nh. Detect deploy infrastructure — search for deploy scripts/configs to include deploy phase in plan:\nfind . -maxdepth 3 \\( -name 'deploy.sh' -o -name 'Dockerfile' -o -name 'docker-compose.yml' -o -name 'fly.toml' -o -name 'wrangler.toml' \\) -type f 2>/dev/null\n\nIf found, read them to understand deploy targets. Include a deploy phase in the plan with concrete commands.\n\n\nGenerate track ID:\n\nExtract a short name (2-3 words, kebab-case) from task description.\nFormat: {shortname}_{YYYYMMDD} (e.g., user-auth_20260209).\n\n\n\nCreate track directory:\nmkdir -p $PLAN_ROOT\n\n\nProject context: docs/plan/{trackId}/\nKB context: docs/plan/{shortname}/\n\n\n\nGenerate $PLAN_ROOT/spec.md:\nBased on research findings, NOT generic questions.\n# Specification: {Title}\n\n**Track ID:** {trackId}\n**Type:** {Feature|Bug|Refactor|Chore}\n**Created:** {YYYY-MM-DD}\n**Status:** Draft\n\n## Summary\n{1-2 paragraph description based on research}\n\n## Acceptance Criteria\n- [ ] {concrete, testable criterion}\n- [ ] {concrete, testable criterion}\n{3-8 criteria based on research findings}\n\n## Dependencies\n- {external deps, packages, other tracks}\n\n## Out of Scope\n- {what this track does NOT cover}\n\n## Technical Notes\n- {architecture decisions from research}\n- {relevant patterns found in codebase}\n- {reusable code from other projects}\n\n\n\nGenerate $PLAN_ROOT/plan.md:\nConcrete, file-level plan from research. Keep it tight: 2-4 phases, 5-15 tasks total.\nCritical format rules (parsed by /build):\n\nPhase headers: ## Phase N: Name\nTasks: - [ ] Task N.Y: Description (with period or detailed text)\nSubtasks: indented - [ ] Subtask description\nAll tasks use [ ] (unchecked), [~] (in progress), [x] (done)\n\n# Implementation Plan: {Title}\n\n**Track ID:** {trackId}\n**Spec:** [spec.md](./spec.md)\n**Created:** {YYYY-MM-DD}\n**Status:** [ ] Not Started\n\n## Overview\n{1-2 sentences on approach}\n\n## Phase 1: {Name}\n{brief description of phase goal}\n\n### Tasks\n- [ ] Task 1.1: {description with concrete file paths}\n- [ ] Task 1.2: {description}\n\n### Verification\n- [ ] {what to check after this phase}\n\n## Phase 2: {Name}\n### Tasks\n- [ ] Task 2.1: {description}\n- [ ] Task 2.2: {description}\n\n### Verification\n- [ ] {verification steps}\n\n{2-4 phases total}\n\n## Phase {N-1}: Deploy (if deploy infrastructure exists)\n_Include this phase ONLY if the project has deploy scripts/configs (deploy.sh, Dockerfile, docker-compose.yml, fly.toml, wrangler.toml, vercel.json). Skip if no deploy infra found._\n\n### Tasks\n- [ ] Task {N-1}.1: {concrete deploy step — e.g. \"Run python/deploy.sh to push Docker image to VPS\", \"wrangler deploy\", etc.}\n- [ ] Task {N-1}.2: Verify deployment — health check, logs, HTTP status\n\n### Verification\n- [ ] Service is live and healthy\n- [ ] No runtime errors in production logs\n\n## Phase {N}: Docs & Cleanup\n### Tasks\n- [ ] Task {N}.1: Update CLAUDE.md with any new commands, architecture changes, or key files\n- [ ] Task {N}.2: Update README.md if public API or setup steps changed\n- [ ] Task {N}.3: Remove dead code — unused imports, orphaned files, stale exports\n\n### Verification\n- [ ] CLAUDE.md reflects current project state\n- [ ] Linter clean, tests pass\n\n## Final Verification\n- [ ] All acceptance criteria from spec met\n- [ ] Tests pass\n- [ ] Linter clean\n- [ ] Build succeeds\n- [ ] Documentation up to date\n\n---\n_Generated by /plan. Tasks marked [~] in progress and [x] complete by /build._\n\nPlan quality rules:\n\nEvery task mentions specific file paths (from research).\nTasks are atomic — one commit each.\nPhases are independently verifiable.\nTotal: 5-15 tasks (not 70).\nLast phase is always \"Docs & Cleanup\".\nHarness-aware: if the task introduces new patterns, include a task to update lint rules or CLAUDE.md constraints. If it touches module boundaries, include verification of dependency direction. Think: \"what harness change prevents future agents from breaking this?\"\n\n\n\nCreate progress task list for pipeline visibility:\nAfter writing plan.md, create TaskCreate entries so progress is trackable:\n\nOne task per phase: \"Phase 1: {name}\" with task list as description.\nThis gives the user and pipeline real-time visibility into what's planned.\n/build will update these tasks as it works through them.\n\nIf superpowers:writing-plans skill is available, follow its granularity format: bite-sized tasks (2-5 minutes each), complete code in task descriptions, exact file paths, verification steps per task. This enhances the built-in format above.\n\n\nShow plan for approval via AskUserQuestion:\nPresent the spec summary + plan overview. Options:\n\n\"Approve and start\" — ready for /build\n\"Edit plan\" — user wants to modify before implementing\n\"Cancel\" — discard the track\n\nIf \"Edit plan\": tell user to edit $PLAN_ROOT/plan.md manually, then run /build." }, { "title": "Output", "body": "Track created: {trackId}\n\n Type: {Feature|Bug|Refactor|Chore}\n Phases: {N}\n Tasks: {N}\n Spec: $PLAN_ROOT/spec.md\n Plan: $PLAN_ROOT/plan.md\n\nResearch findings:\n - {key finding 1}\n - {key finding 2}\n - {reusable code found, if any}\n\nNext: /build {trackId}" }, { "title": "Rationalizations Catalog", "body": "These thoughts mean STOP — you're skipping research:\n\nThoughtReality\"I know this codebase\"You know what you've seen. Search for what you haven't.\"The plan is obvious\"Obvious plans miss edge cases. Research first.\"Let me just start coding\"10 minutes of research prevents 2 hours of rework.\"This is a small feature\"Small features touch many files. Map the blast radius.\"I'll figure it out as I go\"That's not a plan. Write the file paths first.\"70 tasks should cover it\"5-15 tasks. If you need more, split into tracks." }, { "title": "Compatibility Notes", "body": "Plan format must match what /build parses: ## Phase N:, - [ ] Task N.Y:.\n/build reads docs/workflow.md for TDD policy and commit strategy (if exists).\nIf docs/workflow.md missing, /build uses sensible defaults (moderate TDD, conventional commits)." }, { "title": "Plan has too many tasks", "body": "Cause: Feature scope too broad or tasks not atomic enough.\nFix: Target 5-15 tasks across 2-4 phases. Split large features into multiple tracks." }, { "title": "Context detection wrong (project vs KB)", "body": "Cause: Directory has both code manifests and KB-style directories.\nFix: Project context takes priority if package.json/pyproject.toml exists." }, { "title": "Research phase finds no relevant code", "body": "Cause: New project with minimal codebase or MCP tools unavailable.\nFix: Skill falls back to Glob + Grep. For new projects, the plan will rely more on CLAUDE.md architecture and stack conventions." } ], "body": "/plan\n\nThis skill is self-contained — follow the steps below instead of delegating to external planning skills (superpowers, etc.).\n\nResearch the codebase and create a spec + phased implementation plan. Zero interactive questions — explores the code instead.\n\nWhen to use\n\nCreates a track for any feature, bug fix, or refactor with a concrete, file-level implementation plan. Works with or without /setup.\n\nMCP Tools (use if available)\nsession_search(query) — find similar past work in Claude Code chat history\nproject_code_search(query, project) — find reusable code across projects\ncodegraph_query(query) — check dependencies of affected files\ncodegraph_explain(project) — architecture overview: stack, languages, directory layers, key patterns, top dependencies, hub files\nkb_search(query) — search knowledge base for relevant methodology\n\nIf MCP tools are not available, fall back to Glob + Grep + Read.\n\nSteps\n\nParse task description from $ARGUMENTS.\n\nIf empty, ask via AskUserQuestion: \"What feature, bug, or refactor do you want to plan?\"\nThis is the ONE question maximum.\n\nDetect context — determine where plan files should be stored:\n\nProject context (normal project with code):\n\nDetected by: package.json, pyproject.toml, Cargo.toml, *.xcodeproj, or build.gradle.kts exists in working directory\nPlan path: docs/plan/{trackId}/\n\nKnowledge base context (documentation-centric project):\n\nDetected by: NO package manifest found, BUT directories like docs/, notes/, or structured numbered directories exist\nPlan path: docs/plan/{shortname}/\nNote: the shortname is derived from the task (kebab-case, no date suffix for the directory)\n\nSet $PLAN_ROOT based on detected context. All subsequent file paths use $PLAN_ROOT.\n\nLoad project context (parallel reads):\n\nCLAUDE.md — architecture, constraints, Do/Don't\ndocs/prd.md — what the product does (if exists)\ndocs/workflow.md — TDD policy, commit strategy (if exists)\npackage.json or pyproject.toml — stack, versions, deps\n\nAuto-classify track type from keywords in task description:\n\nContains \"fix\", \"bug\", \"broken\", \"error\", \"crash\" → bug\nContains \"refactor\", \"cleanup\", \"reorganize\", \"migrate\" → refactor\nContains \"update\", \"upgrade\", \"bump\" → chore\nDefault → feature\n\nResearch phase — explore the codebase to understand what needs to change:\n\na. Get architecture overview (if MCP available — do this FIRST):\n\ncodegraph_explain(project=\"{project name from CLAUDE.md or directory name}\")\n\n\nGives you: stack, languages, directory layers, key patterns, top dependencies, hub files.\n\nb. Find relevant files — Glob + Grep for patterns related to the task:\n\nSearch for keywords from the task description\nLook at directory structure to understand architecture\nIdentify files that will need modification\n\nc. Precedent retrieval (context graph pattern — search past solutions BEFORE planning):\n\nSearch past sessions (if MCP available):\nsession_search(query=\"{task description keywords}\")\n\nLook for: how similar tasks were solved, what went wrong, what patterns worked.\nSearch KB for relevant methodology:\nkb_search(query=\"{task type}: {keywords}\")\n\nCheck for: harness patterns, architectural constraints, quality scores.\n\nd. Search code across projects (if MCP available):\n\nproject_code_search(query=\"{relevant pattern}\")\n\n\ne. Check dependencies of affected files (if MCP available):\n\ncodegraph_query(query=\"MATCH (f:File {path: '{file}'})-[:IMPORTS]->(dep) RETURN dep.path\")\n\n\nf. Read existing tests in the affected area — understand testing patterns used.\n\ng. Read CLAUDE.md architecture constraints — understand boundaries and conventions.\n\nCheck for harness section: module boundaries, data validation rules, lint configs.\nRead docs/ARCHITECTURE.md and docs/QUALITY_SCORE.md if they exist.\n\nh. Detect deploy infrastructure — search for deploy scripts/configs to include deploy phase in plan:\n\nfind . -maxdepth 3 \\( -name 'deploy.sh' -o -name 'Dockerfile' -o -name 'docker-compose.yml' -o -name 'fly.toml' -o -name 'wrangler.toml' \\) -type f 2>/dev/null\n\n\nIf found, read them to understand deploy targets. Include a deploy phase in the plan with concrete commands.\n\nGenerate track ID:\n\nExtract a short name (2-3 words, kebab-case) from task description.\nFormat: {shortname}_{YYYYMMDD} (e.g., user-auth_20260209).\n\nCreate track directory:\n\nmkdir -p $PLAN_ROOT\n\nProject context: docs/plan/{trackId}/\nKB context: docs/plan/{shortname}/\n\nGenerate $PLAN_ROOT/spec.md: Based on research findings, NOT generic questions.\n\n# Specification: {Title}\n\n**Track ID:** {trackId}\n**Type:** {Feature|Bug|Refactor|Chore}\n**Created:** {YYYY-MM-DD}\n**Status:** Draft\n\n## Summary\n{1-2 paragraph description based on research}\n\n## Acceptance Criteria\n- [ ] {concrete, testable criterion}\n- [ ] {concrete, testable criterion}\n{3-8 criteria based on research findings}\n\n## Dependencies\n- {external deps, packages, other tracks}\n\n## Out of Scope\n- {what this track does NOT cover}\n\n## Technical Notes\n- {architecture decisions from research}\n- {relevant patterns found in codebase}\n- {reusable code from other projects}\n\n\nGenerate $PLAN_ROOT/plan.md: Concrete, file-level plan from research. Keep it tight: 2-4 phases, 5-15 tasks total.\n\nCritical format rules (parsed by /build):\n\nPhase headers: ## Phase N: Name\nTasks: - [ ] Task N.Y: Description (with period or detailed text)\nSubtasks: indented - [ ] Subtask description\nAll tasks use [ ] (unchecked), [~] (in progress), [x] (done)\n# Implementation Plan: {Title}\n\n**Track ID:** {trackId}\n**Spec:** [spec.md](./spec.md)\n**Created:** {YYYY-MM-DD}\n**Status:** [ ] Not Started\n\n## Overview\n{1-2 sentences on approach}\n\n## Phase 1: {Name}\n{brief description of phase goal}\n\n### Tasks\n- [ ] Task 1.1: {description with concrete file paths}\n- [ ] Task 1.2: {description}\n\n### Verification\n- [ ] {what to check after this phase}\n\n## Phase 2: {Name}\n### Tasks\n- [ ] Task 2.1: {description}\n- [ ] Task 2.2: {description}\n\n### Verification\n- [ ] {verification steps}\n\n{2-4 phases total}\n\n## Phase {N-1}: Deploy (if deploy infrastructure exists)\n_Include this phase ONLY if the project has deploy scripts/configs (deploy.sh, Dockerfile, docker-compose.yml, fly.toml, wrangler.toml, vercel.json). Skip if no deploy infra found._\n\n### Tasks\n- [ ] Task {N-1}.1: {concrete deploy step — e.g. \"Run python/deploy.sh to push Docker image to VPS\", \"wrangler deploy\", etc.}\n- [ ] Task {N-1}.2: Verify deployment — health check, logs, HTTP status\n\n### Verification\n- [ ] Service is live and healthy\n- [ ] No runtime errors in production logs\n\n## Phase {N}: Docs & Cleanup\n### Tasks\n- [ ] Task {N}.1: Update CLAUDE.md with any new commands, architecture changes, or key files\n- [ ] Task {N}.2: Update README.md if public API or setup steps changed\n- [ ] Task {N}.3: Remove dead code — unused imports, orphaned files, stale exports\n\n### Verification\n- [ ] CLAUDE.md reflects current project state\n- [ ] Linter clean, tests pass\n\n## Final Verification\n- [ ] All acceptance criteria from spec met\n- [ ] Tests pass\n- [ ] Linter clean\n- [ ] Build succeeds\n- [ ] Documentation up to date\n\n---\n_Generated by /plan. Tasks marked [~] in progress and [x] complete by /build._\n\n\nPlan quality rules:\n\nEvery task mentions specific file paths (from research).\nTasks are atomic — one commit each.\nPhases are independently verifiable.\nTotal: 5-15 tasks (not 70).\nLast phase is always \"Docs & Cleanup\".\nHarness-aware: if the task introduces new patterns, include a task to update lint rules or CLAUDE.md constraints. If it touches module boundaries, include verification of dependency direction. Think: \"what harness change prevents future agents from breaking this?\"\n\nCreate progress task list for pipeline visibility:\n\nAfter writing plan.md, create TaskCreate entries so progress is trackable:\n\nOne task per phase: \"Phase 1: {name}\" with task list as description.\nThis gives the user and pipeline real-time visibility into what's planned.\n/build will update these tasks as it works through them.\n\nIf superpowers:writing-plans skill is available, follow its granularity format: bite-sized tasks (2-5 minutes each), complete code in task descriptions, exact file paths, verification steps per task. This enhances the built-in format above.\n\nShow plan for approval via AskUserQuestion: Present the spec summary + plan overview. Options:\n\n\"Approve and start\" — ready for /build\n\"Edit plan\" — user wants to modify before implementing\n\"Cancel\" — discard the track\n\nIf \"Edit plan\": tell user to edit $PLAN_ROOT/plan.md manually, then run /build.\n\nOutput\nTrack created: {trackId}\n\n Type: {Feature|Bug|Refactor|Chore}\n Phases: {N}\n Tasks: {N}\n Spec: $PLAN_ROOT/spec.md\n Plan: $PLAN_ROOT/plan.md\n\nResearch findings:\n - {key finding 1}\n - {key finding 2}\n - {reusable code found, if any}\n\nNext: /build {trackId}\n\nRationalizations Catalog\n\nThese thoughts mean STOP — you're skipping research:\n\nThought\tReality\n\"I know this codebase\"\tYou know what you've seen. Search for what you haven't.\n\"The plan is obvious\"\tObvious plans miss edge cases. Research first.\n\"Let me just start coding\"\t10 minutes of research prevents 2 hours of rework.\n\"This is a small feature\"\tSmall features touch many files. Map the blast radius.\n\"I'll figure it out as I go\"\tThat's not a plan. Write the file paths first.\n\"70 tasks should cover it\"\t5-15 tasks. If you need more, split into tracks.\nCompatibility Notes\nPlan format must match what /build parses: ## Phase N:, - [ ] Task N.Y:.\n/build reads docs/workflow.md for TDD policy and commit strategy (if exists).\nIf docs/workflow.md missing, /build uses sensible defaults (moderate TDD, conventional commits).\nCommon Issues\nPlan has too many tasks\n\nCause: Feature scope too broad or tasks not atomic enough. Fix: Target 5-15 tasks across 2-4 phases. Split large features into multiple tracks.\n\nContext detection wrong (project vs KB)\n\nCause: Directory has both code manifests and KB-style directories. Fix: Project context takes priority if package.json/pyproject.toml exists.\n\nResearch phase finds no relevant code\n\nCause: New project with minimal codebase or MCP tools unavailable. Fix: Skill falls back to Glob + Grep. For new projects, the plan will rely more on CLAUDE.md architecture and stack conventions." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/fortunto2/solo-plan", "publisherUrl": "https://clawhub.ai/fortunto2/solo-plan", "owner": "fortunto2", "version": "2.2.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/solo-plan", "downloadUrl": "https://openagent3.xyz/downloads/solo-plan", "agentUrl": "https://openagent3.xyz/skills/solo-plan/agent", "manifestUrl": "https://openagent3.xyz/skills/solo-plan/agent.json", "briefUrl": "https://openagent3.xyz/skills/solo-plan/agent.md" } }