[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78F6RJQZHT21QM0MAB92YR5":3,"skill-same:01M78F6RJQZHT21QM0MAB92YR5":140},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M78F6RJQZHT21QM0MAB92YR5","plan-to-pr",null,"Coordinates source-grounded implementation through a validated plan packet, planned task tickets, fixed model routing, verified commits, independent Luna review, and publication gates. Triggers: \"Plan-to-PR\", \"plan to PR\", \"implement this with one task per commit\", \"run the Plan-to-PR workflow\", \"validate Plan-to-PR\", \"publish the PR\".","jl-cmd-projects\u002Fclaude-dev-env","jl-cmd-projects","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F338158757?v=4","01M78F4M55P4QY5YPN27XBQA9N","01M78F4M65AGEYC88NV6PW4715",7,"MIT","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: plan-to-pr\ndescription: >-\n  Coordinates source-grounded implementation through a validated plan packet,\n  planned task tickets, fixed model routing, verified commits, independent Luna\n  review, and publication gates. Triggers: \"Plan-to-PR\", \"plan to PR\",\n  \"implement this with one task per commit\", \"run the Plan-to-PR workflow\",\n  \"validate Plan-to-PR\", \"publish the PR\".\n---\n\n# Plan-to-PR\n\n## Purpose and boundary\n\nUse this skill for source-grounded implementation with one deliverable, one\nallowed file set, one acceptance check, and one commit per task. The planning\nphase creates and validates a tool-neutral `docs\u002Fplans\u002F\u003Cslug>\u002F` packet\nbefore any `TaskCreate` or `TodoWrite` seeding.\n\nThe skill coordinates planning, task records, model routing, commit order,\nreview, verification, and publication. It does not replace the orchestrator or\nadvisor capabilities used by later phases.\n\n## Native planning phase\n\nRun this phase before task seeding and before implementation:\n\n1. The Luna max planner reads the request, repository guidance, relevant\n   source, tests, and documentation, then selects a unique lowercase slug.\n2. The planner consults a Sol xhigh advisor heavily at scope, dependency,\n   task-boundary, acceptance, and risk decisions. The advisor supports planning\n   decisions and packet review.\n3. The planner writes the packet files and validates them against\n   [`reference\u002Fpacket-contract.md`](reference\u002Fpacket-contract.md) and\n   [`reference\u002Fpacket-schema.json`](reference\u002Fpacket-schema.json).\n4. The planner repairs packet findings and repeats deterministic validation\n   until the packet passes. A failed validation blocks task seeding.\n5. Only a passing packet with `status: approved` may seed host tasks. Record the\n   packet path and validation result in the task ledger.\n\nThe packet is the sole planning handoff. It contains its own scope, evidence,\ntask boundaries, acceptance checks, risks, and implementation order. Do not\nseed tasks from conversational notes or an incomplete packet.\n\n## Capability boundary\n\nThis skill owns the native planning packet, task records, routing, review,\nverification, and publication decisions. Later execution uses the companion\norchestrator and advisor capabilities.\n\n## Refusal cases\n\nRefuse the first matching case and stop:\n\n- The request has no source-grounded plan packet.\n- The packet is missing, invalid, outside `docs\u002Fplans\u002F\u003Cslug>\u002F`, or not approved.\n- A requested change spans files outside the packet's allowed file set.\n- A task contains more than one deliverable, acceptance check, or commit.\n- A required task tool, verifier, model tier, advisor, review path, or gate is unavailable.\n- The user asks to bypass verification, review under the [review guide](..\u002Freviews\u002FSKILL.md#review-workflow), final validation, or a publication gate.\n\nReturn exactly: `Plan-to-PR blocked: \u003Cmissing input or capability>.`\n\n## Runtime and task seeding\n\nThe packet and task-run validators use Python 3 standard library only. From this\nskill directory, create a packet skeleton with:\n\n`python scripts\u002Fcreate_packet.py --repo-root \u003Crepository> --slug \u003Cslug> --base-ref \u003Cbase-ref>`\n\nAfter the planner fills the packet, validate it with:\n\n`python scripts\u002Fvalidate_packet.py \u003Crepository>\u002Fdocs\u002Fplans\u002F\u003Cslug>`\n\nRun `python scripts\u002Fvalidate_protocol.py \u003Crecord.json>` for each task record;\nexit `0` means valid and exit `2` means invalid.\n\nAfter packet approval, seed one host task for every packet task with\n`TaskCreate`, `TodoWrite`, or its equivalent. Each task records exactly one\ndeliverable, one allowed file set, one acceptance check, and one commit. Mark a\ntask complete only with verifier output and its commit identity. Use the fixed\ncontracts in `reference\u002Ftask-ticket.md`, `reference\u002Fmodel-routing.md`,\n`reference\u002Ftask-seeds.md`, `reference\u002Ffinal-validation-tasks.md`, and\n`reference\u002Fself-audit-tasks.md`. The fixed fields live in those references.\n\n## Model contract\n\nThe planner and final validator use Luna max with Sol xhigh advisory heavily\nat decisive points. The orchestrator uses the max route and delegates every work\ntask. Every implementation,\nreview, and repair worker uses fast, low-effort Luna. Unavailable models or routing tools\nfail closed; never promote workers,\ndemote planners or validators, or substitute a role route.\n\nThe planner owns the approved packet. The orchestrator owns task assignment,\nledger state, and result reconciliation. Workers change only their ticket's\nfiles and run its acceptance check. The final validator checks the complete\nhistory and publication gates.\n\n## One-task and one-commit protocol\n\nFor each seeded task:\n\n1. The orchestrator issues the standalone task ticket.\n2. One worker implements one deliverable within the ticket's allowed files.\n3. The worker runs the one acceptance check and reports exact output and blockers.\n4. Review and verify the task diff, baseline, named checks, and ticket-to-diff\n   scope under the [review guide](..\u002Freviews\u002FSKILL.md#review-workflow).\n5. The orchestrator creates exactly one commit and records its hash.\n\nNo task borrows files, acceptance checks, or commit history from another task.\nUnrelated changes remain untouched and uncommitted.\n\n## Review and repair\n\nBefore every commit, record fresh verification and review under the [review guide](..\u002Freviews\u002FSKILL.md#review-workflow).\nAfter the commit, a separate fast low-effort Luna review worker runs native\nfindings-only correctness review at `\u002Fe-code-review low`. The review returns\nfindings only and has no repair flag.\n\nA separate fast low-effort Luna repair worker applies only confirmed findings.\nRecord resolved model, effort, command, findings, repair status, and surface\nhash. Rerun the task acceptance check and fresh exact-surface verification, amend the task commit,\nand repeat native review until clean. The max review is the correctness\ngate after cleanup.\n\n## Final validation and publication\n\nThe Luna max final validator maps every commit to one packet task and checks\ncumulative behavior, the allowed-file ledger, acceptance checks, verification\noutput, and post-commit review records. Any\nunmapped commit, missing record, failed gate, or unresolved finding blocks\npublication.\n\nRun the workflow self-audit and retain its evidence. Publish only when final validation\nand self-audit pass. After the branch is finalized and pushed, run Luna max `\u002Fe-simplify`\nfor cleanup-only fixes, then Luna low `\u002Fe-code-review max loop` with a separate\nLuna low repair worker. commit, and push every validated repair;\nfinish only when the max review is clean.\n\n## Companion references\n\n- [`reference\u002Fpacket-contract.md`](reference\u002Fpacket-contract.md) — native planning packet contract.\n- [`reference\u002Fpacket-schema.json`](reference\u002Fpacket-schema.json) — machine-readable packet schema.\n- [`scripts\u002Fcreate_packet.py`](scripts\u002Fcreate_packet.py) — deterministic packet skeleton creator.\n- [`scripts\u002Fvalidate_packet.py`](scripts\u002Fvalidate_packet.py) — deterministic packet validator.\n- [`reference\u002Fmodel-routing.md`](reference\u002Fmodel-routing.md) — fixed model and gate matrix.\n- [`reference\u002Ftask-ticket.md`](reference\u002Ftask-ticket.md) — task, commit, and review record contract.\n- [`reference\u002Freview-loop.md`](reference\u002Freview-loop.md) — review and repair loop.\n- [`reference\u002Fprocess-inventory.md`](reference\u002Fprocess-inventory.md) — evidence homes.\n- [`reference\u002Frun-record.schema.json`](reference\u002Frun-record.schema.json) — machine-checkable task-run record.\n\nRun `scripts\u002Fvalidate_run.py` with the task records and commit set during final\nvalidation. Add `--worktree PATH` when the commit set belongs to another tree.\n","# Plan-to-PR\n\n## Purpose and boundary\n\nUse this skill for source-grounded implementation with one deliverable, one\nallowed file set, one acceptance check, and one commit per task. The planning\nphase creates and validates a tool-neutral `docs\u002Fplans\u002F\u003Cslug>\u002F` packet\nbefore any `TaskCreate` or `TodoWrite` seeding.\n\nThe skill coordinates planning, task records, model routing, commit order,\nreview, verification, and publication. It does not replace the orchestrator or\nadvisor capabilities used by later phases.\n\n## Native planning phase\n\nRun this phase before task seeding and before implementation:\n\n1. The Luna max planner reads the request, repository guidance, relevant\n   source, tests, and documentation, then selects a unique lowercase slug.\n2. The planner consults a Sol xhigh advisor heavily at scope, dependency,\n   task-boundary, acceptance, and risk decisions. The advisor supports planning\n   decisions and packet review.\n3. The planner writes the packet files and validates them against\n   [`reference\u002Fpacket-contract.md`](reference\u002Fpacket-contract.md) and\n   [`reference\u002Fpacket-schema.json`](reference\u002Fpacket-schema.json).\n4. The planner repairs packet findings and repeats deterministic validation\n   until the packet passes. A failed validation blocks task seeding.\n5. Only a passing packet with `status: approved` may seed host tasks. Record the\n   packet path and validation result in the task ledger.\n\nThe packet is the sole planning handoff. It contains its own scope, evidence,\ntask boundaries, acceptance checks, risks, and implementation order. Do not\nseed tasks from conversational notes or an incomplete packet.\n\n## Capability boundary\n\nThis skill owns the native planning packet, task records, routing, review,\nverification, and publication decisions. Later execution uses the companion\norchestrator and advisor capabilities.\n\n## Refusal cases\n\nRefuse the first matching case and stop:\n\n- The request has no source-grounded plan packet.\n- The packet is missing, invalid, outside `docs\u002Fplans\u002F\u003Cslug>\u002F`, or not approved.\n- A requested change spans files outside the packet's allowed file set.\n- A task contains more than one deliverable, acceptance check, or commit.\n- A required task tool, verifier, model tier, advisor, review path, or gate is unavailable.\n- The user asks to bypass verification, review under the [review guide](..\u002Freviews\u002FSKILL.md#review-workflow), final validation, or a publication gate.\n\nReturn exactly: `Plan-to-PR blocked: \u003Cmissing input or capability>.`\n\n## Runtime and task seeding\n\nThe packet and task-run validators use Python 3 standard library only. From this\nskill directory, create a packet skeleton with:\n\n`python scripts\u002Fcreate_packet.py --repo-root \u003Crepository> --slug \u003Cslug> --base-ref \u003Cbase-ref>`\n\nAfter the planner fills the packet, validate it with:\n\n`python scripts\u002Fvalidate_packet.py \u003Crepository>\u002Fdocs\u002Fplans\u002F\u003Cslug>`\n\nRun `python scripts\u002Fvalidate_protocol.py \u003Crecord.json>` for each task record;\nexit `0` means valid and exit `2` means invalid.\n\nAfter packet approval, seed one host task for every packet task with\n`TaskCreate`, `TodoWrite`, or its equivalent. Each task records exactly one\ndeliverable, one allowed file set, one acceptance check, and one commit. Mark a\ntask complete only with verifier output and its commit identity. Use the fixed\ncontracts in `reference\u002Ftask-ticket.md`, `reference\u002Fmodel-routing.md`,\n`reference\u002Ftask-seeds.md`, `reference\u002Ffinal-validation-tasks.md`, and\n`reference\u002Fself-audit-tasks.md`. The fixed fields live in those references.\n\n## Model contract\n\nThe planner and final validator use Luna max with Sol xhigh advisory heavily\nat decisive points. The orchestrator uses the max route and delegates every work\ntask. Every implementation,\nreview, and repair worker uses fast, low-effort Luna. Unavailable models or routing tools\nfail closed; never promote workers,\ndemote planners or validators, or substitute a role route.\n\nThe planner owns the approved packet. The orchestrator owns task assignment,\nledger state, and result reconciliation. Workers change only their ticket's\nfiles and run its acceptance check. The final validator checks the complete\nhistory and publication gates.\n\n## One-task and one-commit protocol\n\nFor each seeded task:\n\n1. The orchestrator issues the standalone task ticket.\n2. One worker implements one deliverable within the ticket's allowed files.\n3. The worker runs the one acceptance check and reports exact output and blockers.\n4. Review and verify the task diff, baseline, named checks, and ticket-to-diff\n   scope under the [review guide](..\u002Freviews\u002FSKILL.md#review-workflow).\n5. The orchestrator creates exactly one commit and records its hash.\n\nNo task borrows files, acceptance checks, or commit history from another task.\nUnrelated changes remain untouched and uncommitted.\n\n## Review and repair\n\nBefore every commit, record fresh verification and review under the [review guide](..\u002Freviews\u002FSKILL.md#review-workflow).\nAfter the commit, a separate fast low-effort Luna review worker runs native\nfindings-only correctness review at `\u002Fe-code-review low`. The review returns\nfindings only and has no repair flag.\n\nA separate fast low-effort Luna repair worker applies only confirmed findings.\nRecord resolved model, effort, command, findings, repair status, and surface\nhash. Rerun the task acceptance check and fresh exact-surface verification, amend the task commit,\nand repeat native review until clean. The max review is the correctness\ngate after cleanup.\n\n## Final validation and publication\n\nThe Luna max final validator maps every commit to one packet task and checks\ncumulative behavior, the allowed-file ledger, acceptance checks, verification\noutput, and post-commit review records. Any\nunmapped commit, missing record, failed gate, or unresolved finding blocks\npublication.\n\nRun the workflow self-audit and retain its evidence. Publish only when final validation\nand self-audit pass. After the branch is finalized and pushed, run Luna max `\u002Fe-simplify`\nfor cleanup-only fixes, then Luna low `\u002Fe-code-review max loop` with a separate\nLuna low repair worker. commit, and push every validated repair;\nfinish only when the max review is clean.\n\n## Companion references\n\n- [`reference\u002Fpacket-contract.md`](reference\u002Fpacket-contract.md) — native planning packet contract.\n- [`reference\u002Fpacket-schema.json`](reference\u002Fpacket-schema.json) — machine-readable packet schema.\n- [`scripts\u002Fcreate_packet.py`](scripts\u002Fcreate_packet.py) — deterministic packet skeleton creator.\n- [`scripts\u002Fvalidate_packet.py`](scripts\u002Fvalidate_packet.py) — deterministic packet validator.\n- [`reference\u002Fmodel-routing.md`](reference\u002Fmodel-routing.md) — fixed model and gate matrix.\n- [`reference\u002Ftask-ticket.md`](reference\u002Ftask-ticket.md) — task, commit, and review record contract.\n- [`reference\u002Freview-loop.md`](reference\u002Freview-loop.md) — review and repair loop.\n- [`reference\u002Fprocess-inventory.md`](reference\u002Fprocess-inventory.md) — evidence homes.\n- [`reference\u002Frun-record.schema.json`](reference\u002Frun-record.schema.json) — machine-checkable task-run record.\n\nRun `scripts\u002Fvalidate_run.py` with the task records and commit set during final\nvalidation. Add `--worktree PATH` when the commit set belongs to another tree.\n",{"name":5,"description":7},"main","974284b42eeb4609e94d4ebc1f6e36df400d54ca","packages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr",1,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects","2026-11-15 05:02:47",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add jl-cmd-projects\u002Fclaude-dev-env --skill plan-to-pr",{"tool":36,"command":37},"bunx","bunx skills add jl-cmd-projects\u002Fclaude-dev-env --skill plan-to-pr",{"tool":39,"command":40},"pnpm","pnpm dlx skills add jl-cmd-projects\u002Fclaude-dev-env --skill plan-to-pr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002FSKILL.md",true,[44,50,54,58,62,66,70,74,78,82,86,92,96,100,104,108,112,116,120,124,128,132,136],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"reference\u002Ffinal-validation-tasks.md","REFERENCE","参考文档",1014,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Ffinal-validation-tasks.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"reference\u002Fmodel-routing.md",2474,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Fmodel-routing.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"reference\u002Fpacket-contract.md",2373,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Fpacket-contract.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"reference\u002Fpacket-schema.json",2812,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Fpacket-schema.json",{"path":63,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":64,"sourceHtmlUrl":65},"reference\u002Fprocess-inventory.md",2468,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Fprocess-inventory.md",{"path":67,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":68,"sourceHtmlUrl":69},"reference\u002Freview-loop.md",1585,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Freview-loop.md",{"path":71,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":72,"sourceHtmlUrl":73},"reference\u002Frun-record.schema.json",2797,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Frun-record.schema.json",{"path":75,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":76,"sourceHtmlUrl":77},"reference\u002Fself-audit-tasks.md",1044,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Fself-audit-tasks.md",{"path":79,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":80,"sourceHtmlUrl":81},"reference\u002Ftask-seeds.md",818,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Ftask-seeds.md",{"path":83,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":84,"sourceHtmlUrl":85},"reference\u002Ftask-ticket.md",2312,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Freference\u002Ftask-ticket.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fconfig\u002F__init__.py","SCRIPT","脚本",61,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Fconfig\u002F__init__.py",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fconfig\u002Fconstants.py",5906,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Fconfig\u002Fconstants.py",{"path":97,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Fcreate_packet.py",6008,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Fcreate_packet.py",{"path":101,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fload_skill_constants.py",1672,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Fload_skill_constants.py",{"path":105,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Ftest_create_packet.py",3419,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Ftest_create_packet.py",{"path":109,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Ftest_validate_packet.py",10903,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Ftest_validate_packet.py",{"path":113,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":114,"sourceHtmlUrl":115},"scripts\u002Ftest_validate_protocol.py",7026,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Ftest_validate_protocol.py",{"path":117,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":118,"sourceHtmlUrl":119},"scripts\u002Ftest_validate_run.py",5880,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Ftest_validate_run.py",{"path":121,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":122,"sourceHtmlUrl":123},"scripts\u002Fvalidate_packet.py",25414,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Fvalidate_packet.py",{"path":125,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":126,"sourceHtmlUrl":127},"scripts\u002Fvalidate_protocol.py",24342,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Fvalidate_protocol.py",{"path":129,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":130,"sourceHtmlUrl":131},"scripts\u002Fvalidate_run.py",7386,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Fscripts\u002Fvalidate_run.py",{"path":133,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":134,"sourceHtmlUrl":135},"test_skill_contract.py",8158,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Ftest_skill_contract.py",{"path":137,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":138,"sourceHtmlUrl":139},"test_task_ticket_contract.py",5124,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fplan-to-pr\u002Ftest_task_ticket_contract.py",[141,148,155,162,169,176],{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":18},"01M78FER7S09AE87MMJFT1E87E","update","Fast-forwards a local repository's main branch to a remote's main after confirming the repo path and source remote through AskUserQuestion. Use when the user says '\u002Fupdate', 'update main', 'fast-forward main', 'sync main from origin', 'pull latest main into \u003Cpath>', or 'bring main up to date'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fupdate\u002FSKILL.md",[],[],{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":18},"01M78FENWZS01MB4PMGX6801X6","source-command-sr-loop","Converging cleanup loop: repeat \u002Fsimplify until clean, then repeat \u002Fcode-review --fix until clean","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsource-command-sr-loop\u002FSKILL.md",[],[],{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":18},"01M78FEGZ7JDWEG3RM78M9Y8F8","skill-builder","Skill lifecycle: classify, scaffold, write via the skill-writer-agent, self-audit, compose sub-skills, polish description triggers, enforce deterministic scripts. Triggers: build a skill, new skill workflow, improve this skill, optimize skill description, skill development lifecycle, skill modularity, skill composition, description trigger catalog, deterministic skill scripts.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fskill-builder\u002FSKILL.md",[],[],{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":18},"01M78FEDEYHJYKTER9S566DMEZ","session-tidy","Audit, clean, and consolidate session logs in the Obsidian vault. Fixes format drift, resolves orphaned next-steps, updates stale statuses, and generates project rollup summaries. Use when session logs feel cluttered or before starting a new project milestone. Triggers on '\u002Fsession-tidy', 'tidy sessions', 'clean up session logs', 'session audit'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-tidy\u002FSKILL.md",[],[],{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":18},"01M78FE8QR789SKBF3A78N2T13","session-log","Logs a session report as an HTML page, tracks vault context, extracts decisions, and outputs a \u002Frename command. Use for \u002Fsession-log, 'journal this session', 'log this work', 'session report', 'summarize\u002Flog\u002Frecord this session', 'save session', 'capture session', or 'document what we did'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-log\u002FSKILL.md",[],[],{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":18},"01M78FE4JDJHKTJPWRWNQEX2HT","run-claude-dev-env","Build, install, run, and test the claude-dev-env installer. Use when asked to run claude-dev-env, install the Claude Code config into ~\u002F.claude, drive the installer, smoke-test it against a sandbox, or run its test suite.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Frun-claude-dev-env\u002FSKILL.md",[],[]]