[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77NJCSZDW2G43VASMP77KR1":3,"skill-same:01M77NJCSZDW2G43VASMP77KR1":186},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M77NJCSZDW2G43VASMP77KR1","ce-plan",null,"Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.","ucirello\u002Fcompound-engineering-plugin","ucirello","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F138827?v=4","01M77NFWYZ15SBS6EHVHBDDNA6","U Cirello","01M77NFWZJS5P3EKSVVKR8K5G9",0,"MIT","https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ce-plan\ndescription: \"Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.\"\nargument-hint: \"[optional: feature description, requirements doc path, plan path to deepen, or any task to plan] [output:html]\"\n---\n\n## Native execution boundaries\n\nThis skill explicitly requests the research\u002Freview subagents described below.\nUnder a user-or-loaded-skill delegation rule this suffices; do not ask again.\nRespect unconditional higher-priority bans and actual tool denials. Model choice\nis separate: use `opencode.models` for discovery, preserve configured choices and\ntiers, but omit optional model overrides when the host requires an explicit user\nmodel request and none exists. Suitable inherited-model research may proceed\nwith any unmet model requirement disclosed. Same-model reviewers do not establish\ncross-model independence; required unavailable passes mean incomplete coverage.\nVerify effective nesting capacity separately and classify actual dispatch errors\nas denial, missing tool, model-argument rejection or depth\u002Fcapacity exhaustion.\nDo not evade restrictions through another harness or shell. Use allowed inline\nor parent-coordinator fallback only when that pass permits it. These rules also\ngovern all referenced research, deepening, review and elevation instructions.\nFor every JJ command set cwd to the absolute target workspace root. Scope\nrepository `gh` commands there with `GIT_DIR=$(jj git root)`. Keep temporary\nfiles below local `.tmp\u002F`; never use direct Git execution.\n\n# Create Technical Plan\n\n**Outcome:** a plan for carrying out and checking the agreed work while preserving its outcome and constraints. Resolve technical choices from evidence; leave adequate instructions unchanged. `ce-brainstorm` defines **WHAT**, `ce-plan` plans **HOW**, and `ce-work` executes. A prior brainstorm is optional.\n\n**An explicit invocation always produces a plan.** Never classify a direct invocation as \"not a planning task\" and route out. It may select any output contract below, and the smallest valid plan is a few sentences in chat.\n\n**Research, decide, and write the plan — never implement.** Do not write production code, run tests, or learn from execution-time results. Directional pseudo-code and grammar sketches may communicate design; changing code to see what happens belongs in `ce-work`.\n\n## Mandatory Completion Contract\n\nA run is complete when its output contract's done condition is met. Every normal interactive branch that produces a plan artifact or checkpoint is incomplete until the user has been asked what to do next. A request that already authorizes the next action is that answer. For a Durable software implementation-plan run that continues past the resume check, that means the Phase 5.4 menu has been presented and the selected action has actually fired. For Direct, the change stated and the handoff offered; for a Chat brief, the brief and its one-line save-or-`ce-work` offer in chat. Neither presents the Phase 5.4 menu. Non-software plans and approach-level plans end with the handoff their reference workflow defines. A run that only answers a question may end after the answer unless its reference requires a save or share step.\n\nWriting the file, checking confidence, and running or explicitly skipping `ce-doc-review` are intermediate milestones. In pipeline mode, the run is complete only when the plan, the confidence check, and the non-interactive document-review state have been returned to the caller, which decides what happens next.\n\n## Interaction Method\n\nAsk one question at a time through the host's blocking question tool already in the current tool list. Match by capability; never probe a user-facing tool to discover it. If none is listed or a real question call errors, render numbered choices in chat; never silently skip a required question. If no feature description was supplied, ask what to plan and wait.\n\nWhen a question is a yes\u002Fno or a batch confirm, word it so that agreeing accepts the recommendation. Numbered choices stay numbered choices.\n\n## Output Contract\n\nDecide which output contract applies at the start of scoping (Phase 0.6), before choosing depth and before the scoping synthesis. It applies only when no resume route (Phase 0.1) fired and the source check (Phase 0.2) found no upstream artifact. Ground it with bounded inline reads of what the request names, without dispatching a subagent. Select one:\n\n- **Direct** — the work can be stated, done, and verified in one pass with no decision the user would weigh. State the change in a few sentences and offer the handoff to `ce-work` or the user; execution starts only with implementation authority, as `references\u002Foutput-contracts.md` defines.\n- **Chat brief** — bounded work with at most one decision the user would weigh and no risk surface. Deliver it in chat and stop.\n- **Durable** — everything else. Continue the workflow below.\n\n`references\u002Foutput-contracts.md` defines Direct and Chat brief; read it when either is selected. When the tier is still uncertain after those reads, take the heavier one. If a read surfaces a decision the user would weigh, a risk surface, or multi-pass verification, move to the heavier tier before emitting anything. Durable regardless of size: a run with no synchronous user to act on chat this turn (pipeline, headless, goal- or scheduler-driven), a request whose wording asks for a plan, a plan file, or an output format, a request that continues an existing plan's item, and a risk surface — authentication, payments, migrations, external contracts.\n\n## Workflow\n\nPhases run in order unless a reference routes out or short-circuits. Read a phase's required reference in full when you enter that phase; a read made before that phase does not satisfy it, and a reference named for the final steps is read again at its step even when already in context. If a required reference cannot be read, stop before the action it governs and report the blocker and recovery path; never reconstruct the missing rules from memory. In pipeline mode, every required-reference failure returns `status: blocked`, `phase`, `blocker`, and `recovery_path`; include `artifact_path` and preserve the artifact when one exists. Report blocked even when an artifact exists.\n\n### Phase 0: Output, Resume, and Scope\n\n1. **Output first.** Read `references\u002Foutput-mode.md` before interpreting any phase. It defines token parsing, output and confirmation precedence, renderer selection, artifact location, and when a repository may be resolved.\n2. **Resume, deepen, approach, and domain.** Read `references\u002Fresume.md` before acting. It defines resuming an existing plan, enriching a requirements-only plan, deepening, approach-level planning, and the software\u002Fnon-software split. Follow any terminal route it selects; otherwise continue.\n3. **Source and scope.** Read `references\u002Fintake.md` before Phase 0.2 and follow it through Phase 0.7. It defines finding and preserving the upstream artifact, routing out to bootstrap work, blocking questions, depth, named resources, and the scoping synthesis; the Output Contract decision above happens inside it. Do not pass a decision point that has not resolved.\n\n### Phases 1-4: Research and Compose\n\n4. Read `references\u002Fresearch.md` before gathering context.\n5. Read `references\u002Fstructure.md` before resolving questions or structuring the plan.\n6. Compose from `references\u002Fplan-sections.md` plus the format-rendering reference selected by `output-mode.md`.\n\n### Phase 5: Review, Write, Deepen, and Hand Off\n\n7. Read `references\u002Ffinal-review.md` before the pre-write review; it defines Phase 5.1 through 5.3.2. On an interactive run from a brainstorm, the user sees the Phase 5.1.5 scoping synthesis in chat before the write: a confirmation to wait on, or its one-line auto-proceed announcement.\n8. **Model elevation.** Immediately before authoring, read `references\u002Freasoning-elevation.md`, resolve the choice at this boundary, and follow it. Do not author until activation resolution has completed and any selected dispatch or transparent fallback has settled.\n9. In pipeline mode, evidence that invalidates a decision settled earlier in the session stops the write. Return the exact token `settled-decision-invalidated`, the decision, and the reason; do not resolve it silently.\n10. Write the plan before presenting options, then complete the confidence path `final-review.md` defines.\n\n**STOP. Read `references\u002Fplan-handoff.md` immediately before Phase 5.3.8 and 5.4** (document review and the handoff menu). Document review is mandatory for a Durable plan and the default is non-interactive (`mode:non-interactive`). In interactive software runs, ask exactly: \"Plan ready at `\u003Cabsolute path to plan>`. What would you like to do next?\" Present its menu and wait. If the selection arrives after a user turn, reload `references\u002Fplan-handoff.md` before acting. Rendering the menu, receiving a selection, or announcing a route is not completion; execute the selected action.\n","## Native execution boundaries\n\nThis skill explicitly requests the research\u002Freview subagents described below.\nUnder a user-or-loaded-skill delegation rule this suffices; do not ask again.\nRespect unconditional higher-priority bans and actual tool denials. Model choice\nis separate: use `opencode.models` for discovery, preserve configured choices and\ntiers, but omit optional model overrides when the host requires an explicit user\nmodel request and none exists. Suitable inherited-model research may proceed\nwith any unmet model requirement disclosed. Same-model reviewers do not establish\ncross-model independence; required unavailable passes mean incomplete coverage.\nVerify effective nesting capacity separately and classify actual dispatch errors\nas denial, missing tool, model-argument rejection or depth\u002Fcapacity exhaustion.\nDo not evade restrictions through another harness or shell. Use allowed inline\nor parent-coordinator fallback only when that pass permits it. These rules also\ngovern all referenced research, deepening, review and elevation instructions.\nFor every JJ command set cwd to the absolute target workspace root. Scope\nrepository `gh` commands there with `GIT_DIR=$(jj git root)`. Keep temporary\nfiles below local `.tmp\u002F`; never use direct Git execution.\n\n# Create Technical Plan\n\n**Outcome:** a plan for carrying out and checking the agreed work while preserving its outcome and constraints. Resolve technical choices from evidence; leave adequate instructions unchanged. `ce-brainstorm` defines **WHAT**, `ce-plan` plans **HOW**, and `ce-work` executes. A prior brainstorm is optional.\n\n**An explicit invocation always produces a plan.** Never classify a direct invocation as \"not a planning task\" and route out. It may select any output contract below, and the smallest valid plan is a few sentences in chat.\n\n**Research, decide, and write the plan — never implement.** Do not write production code, run tests, or learn from execution-time results. Directional pseudo-code and grammar sketches may communicate design; changing code to see what happens belongs in `ce-work`.\n\n## Mandatory Completion Contract\n\nA run is complete when its output contract's done condition is met. Every normal interactive branch that produces a plan artifact or checkpoint is incomplete until the user has been asked what to do next. A request that already authorizes the next action is that answer. For a Durable software implementation-plan run that continues past the resume check, that means the Phase 5.4 menu has been presented and the selected action has actually fired. For Direct, the change stated and the handoff offered; for a Chat brief, the brief and its one-line save-or-`ce-work` offer in chat. Neither presents the Phase 5.4 menu. Non-software plans and approach-level plans end with the handoff their reference workflow defines. A run that only answers a question may end after the answer unless its reference requires a save or share step.\n\nWriting the file, checking confidence, and running or explicitly skipping `ce-doc-review` are intermediate milestones. In pipeline mode, the run is complete only when the plan, the confidence check, and the non-interactive document-review state have been returned to the caller, which decides what happens next.\n\n## Interaction Method\n\nAsk one question at a time through the host's blocking question tool already in the current tool list. Match by capability; never probe a user-facing tool to discover it. If none is listed or a real question call errors, render numbered choices in chat; never silently skip a required question. If no feature description was supplied, ask what to plan and wait.\n\nWhen a question is a yes\u002Fno or a batch confirm, word it so that agreeing accepts the recommendation. Numbered choices stay numbered choices.\n\n## Output Contract\n\nDecide which output contract applies at the start of scoping (Phase 0.6), before choosing depth and before the scoping synthesis. It applies only when no resume route (Phase 0.1) fired and the source check (Phase 0.2) found no upstream artifact. Ground it with bounded inline reads of what the request names, without dispatching a subagent. Select one:\n\n- **Direct** — the work can be stated, done, and verified in one pass with no decision the user would weigh. State the change in a few sentences and offer the handoff to `ce-work` or the user; execution starts only with implementation authority, as `references\u002Foutput-contracts.md` defines.\n- **Chat brief** — bounded work with at most one decision the user would weigh and no risk surface. Deliver it in chat and stop.\n- **Durable** — everything else. Continue the workflow below.\n\n`references\u002Foutput-contracts.md` defines Direct and Chat brief; read it when either is selected. When the tier is still uncertain after those reads, take the heavier one. If a read surfaces a decision the user would weigh, a risk surface, or multi-pass verification, move to the heavier tier before emitting anything. Durable regardless of size: a run with no synchronous user to act on chat this turn (pipeline, headless, goal- or scheduler-driven), a request whose wording asks for a plan, a plan file, or an output format, a request that continues an existing plan's item, and a risk surface — authentication, payments, migrations, external contracts.\n\n## Workflow\n\nPhases run in order unless a reference routes out or short-circuits. Read a phase's required reference in full when you enter that phase; a read made before that phase does not satisfy it, and a reference named for the final steps is read again at its step even when already in context. If a required reference cannot be read, stop before the action it governs and report the blocker and recovery path; never reconstruct the missing rules from memory. In pipeline mode, every required-reference failure returns `status: blocked`, `phase`, `blocker`, and `recovery_path`; include `artifact_path` and preserve the artifact when one exists. Report blocked even when an artifact exists.\n\n### Phase 0: Output, Resume, and Scope\n\n1. **Output first.** Read `references\u002Foutput-mode.md` before interpreting any phase. It defines token parsing, output and confirmation precedence, renderer selection, artifact location, and when a repository may be resolved.\n2. **Resume, deepen, approach, and domain.** Read `references\u002Fresume.md` before acting. It defines resuming an existing plan, enriching a requirements-only plan, deepening, approach-level planning, and the software\u002Fnon-software split. Follow any terminal route it selects; otherwise continue.\n3. **Source and scope.** Read `references\u002Fintake.md` before Phase 0.2 and follow it through Phase 0.7. It defines finding and preserving the upstream artifact, routing out to bootstrap work, blocking questions, depth, named resources, and the scoping synthesis; the Output Contract decision above happens inside it. Do not pass a decision point that has not resolved.\n\n### Phases 1-4: Research and Compose\n\n4. Read `references\u002Fresearch.md` before gathering context.\n5. Read `references\u002Fstructure.md` before resolving questions or structuring the plan.\n6. Compose from `references\u002Fplan-sections.md` plus the format-rendering reference selected by `output-mode.md`.\n\n### Phase 5: Review, Write, Deepen, and Hand Off\n\n7. Read `references\u002Ffinal-review.md` before the pre-write review; it defines Phase 5.1 through 5.3.2. On an interactive run from a brainstorm, the user sees the Phase 5.1.5 scoping synthesis in chat before the write: a confirmation to wait on, or its one-line auto-proceed announcement.\n8. **Model elevation.** Immediately before authoring, read `references\u002Freasoning-elevation.md`, resolve the choice at this boundary, and follow it. Do not author until activation resolution has completed and any selected dispatch or transparent fallback has settled.\n9. In pipeline mode, evidence that invalidates a decision settled earlier in the session stops the write. Return the exact token `settled-decision-invalidated`, the decision, and the reason; do not resolve it silently.\n10. Write the plan before presenting options, then complete the confidence path `final-review.md` defines.\n\n**STOP. Read `references\u002Fplan-handoff.md` immediately before Phase 5.3.8 and 5.4** (document review and the handoff menu). Document review is mandatory for a Durable plan and the default is non-interactive (`mode:non-interactive`). In interactive software runs, ask exactly: \"Plan ready at `\u003Cabsolute path to plan>`. What would you like to do next?\" Present its menu and wait. If the selection arrives after a user turn, reload `references\u002Fplan-handoff.md` before acting. Rendering the menu, receiving a selection, or announcing a route is not completion; execute the selected action.\n",{"name":5,"description":7,"argument-hint":24},"[optional: feature description, requirements doc path, plan path to deepen, or any task to plan] [output:html]","main","03ecf78d3885acd7cbd6ff9f37928d306cc7ba0e","skills\u002Fce-plan","https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin","https:\u002F\u002Fgithub.com\u002Fucirello","Gopher. Mars aficionado.","2026-11-14 06:10:50",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add ucirello\u002Fcompound-engineering-plugin --skill ce-plan",{"tool":38,"command":39},"bunx","bunx skills add ucirello\u002Fcompound-engineering-plugin --skill ce-plan",{"tool":41,"command":42},"pnpm","pnpm dlx skills add ucirello\u002Fcompound-engineering-plugin --skill ce-plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002FSKILL.md",true,[46,52,56,60,64,68,72,76,80,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148,152,156,160,164,168,172,176,180],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fagents\u002Fagent-native-planning-strategist.md","REFERENCE","参考文档",4680,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fagent-native-planning-strategist.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fagents\u002Farchitecture-strategist.md",3253,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Farchitecture-strategist.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fagents\u002Fbest-practices-researcher.md",7634,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fbest-practices-researcher.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fagents\u002Fdata-integrity-guardian.md",3246,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fdata-integrity-guardian.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fagents\u002Fframework-docs-researcher.md",6087,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fframework-docs-researcher.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fagents\u002Fgit-history-analyzer.md",2517,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fgit-history-analyzer.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fagents\u002Flearnings-researcher.md",20213,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Flearnings-researcher.md",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fagents\u002Fpattern-recognition-specialist.md",3660,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fpattern-recognition-specialist.md",{"path":81,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fagents\u002Fperformance-oracle.md",4566,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fperformance-oracle.md",{"path":85,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fagents\u002Frepo-research-analyst.md",15489,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Frepo-research-analyst.md",{"path":89,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fagents\u002Fsecurity-sentinel.md",4048,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fsecurity-sentinel.md",{"path":93,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fagents\u002Fslack-researcher.md",10941,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fslack-researcher.md",{"path":97,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fagents\u002Fspec-flow-analyzer.md",5358,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fspec-flow-analyzer.md",{"path":101,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fagents\u002Fweb-researcher.md",9615,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fagents\u002Fweb-researcher.md",{"path":105,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fapproach-altitude.md",7575,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fapproach-altitude.md",{"path":109,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fbakeoff.md",2453,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fbakeoff.md",{"path":113,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fdeepening-workflow.md",21064,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fdeepening-workflow.md",{"path":117,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Ffinal-review.md",19616,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Ffinal-review.md",{"path":121,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Fhtml-rendering.md",12786,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fhtml-rendering.md",{"path":125,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fintake.md",20419,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fintake.md",{"path":129,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Fmarkdown-rendering.md",11183,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fmarkdown-rendering.md",{"path":133,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Foutput-contracts.md",2992,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Foutput-contracts.md",{"path":137,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Foutput-mode.md",7514,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Foutput-mode.md",{"path":141,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":142,"sourceHtmlUrl":143},"references\u002Fplan-handoff.md",22930,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fplan-handoff.md",{"path":145,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":146,"sourceHtmlUrl":147},"references\u002Fplan-sections.md",30743,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fplan-sections.md",{"path":149,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":150,"sourceHtmlUrl":151},"references\u002Fpublishing.md",2834,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fpublishing.md",{"path":153,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":154,"sourceHtmlUrl":155},"references\u002Freasoning-elevation.md",6189,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Freasoning-elevation.md",{"path":157,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":158,"sourceHtmlUrl":159},"references\u002Fresearch.md",25884,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fresearch.md",{"path":161,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":162,"sourceHtmlUrl":163},"references\u002Fresume.md",9839,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fresume.md",{"path":165,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":166,"sourceHtmlUrl":167},"references\u002Fsettled-decisions.md",5193,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fsettled-decisions.md",{"path":169,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":170,"sourceHtmlUrl":171},"references\u002Fstructure.md",26579,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fstructure.md",{"path":173,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":174,"sourceHtmlUrl":175},"references\u002Fsynthesis-summary.md",28590,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Fsynthesis-summary.md",{"path":177,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":178,"sourceHtmlUrl":179},"references\u002Funiversal-planning.md",16154,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Freferences\u002Funiversal-planning.md",{"path":181,"resourceType":182,"resourceTypeDesc":183,"sizeBytes":184,"sourceHtmlUrl":185},"scripts\u002Fpacks-resolve.py","SCRIPT","脚本",32196,"https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-plan\u002Fscripts\u002Fpacks-resolve.py",[187,194,201,208,215,222],{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":19},"01M78VM0YXEHCKHF8YT1P2WFHF","ce-retro","Look back over an agent session in this repo, the current one by default or any scope the user names across harnesses, and find what in the repo's environment keeps costing agents effort or leading them into mistakes, keeping only fixes the evidence shows are worth it. Lands the approved environment fixes and hands the rest to their owners. Use for a retro, postmortem, or papercut sweep of how agents worked in this repo. Use ce-compound to keep the lesson of one solved problem, and ce-debug for a bug in product code.","https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fce-retro\u002FSKILL.md",[],[],{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":200,"publishedAt":19},"01M77NMFCKBMKN3C8EACVGP8TG","release-notes","Draft release notes from merged pull requests since the last tag. Use when preparing a release.","https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Ftests\u002Fskill-eval-cell\u002Ffixtures\u002Freview-roster-skill-prose\u002Fskills\u002Frelease-notes\u002FSKILL.md",[],[],{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":207,"publishedAt":19},"01M77NMEKMA0BXHC4230FV7S39","skill-one","Sample skill","https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fskill-one\u002FSKILL.md",[],[],{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":214,"publishedAt":19},"01M77NMCCVPH1F4P94W3CCAP5T","disabled-skill","A skill with model invocation disabled","https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fdisabled-skill\u002FSKILL.md",[],[],{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":219,"categories":220,"keywords":221,"publishedAt":19},"01M77NMACM3ACB6PX92GMHFF3P","claude-only-skill","A skill restricted to Claude Code only","https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fclaude-only-skill\u002FSKILL.md",[],[],{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":228,"publishedAt":19},"01M77NM9ACPBEWHX6Z3QT1PRMS","agent-only-skill","An agent-only skill not intended for direct user invocation","https:\u002F\u002Fgithub.com\u002Fucirello\u002Fcompound-engineering-plugin\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fagent-only-skill\u002FSKILL.md",[],[]]