[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M786TQ9NJ17PDQVPJNJNXMB4":3,"skill-same:01M786TQ9NJ17PDQVPJNJNXMB4":48},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M786TQ9NJ17PDQVPJNJNXMB4","sp-prd-build",null,"Use when `sp-prd-scan` has produced a complete reconstruction package and the final PRD suite must be compiled from it.","chenziyang110\u002Flaunchdeck","chenziyang110","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43693913?v=4","01M7863EBWK1D0P6A29YGEMAS4","Robin11","01M7863ECM1VB6RXDMHTW90D2T",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-prd-build\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"sp-prd-build\"\ndescription: \"Use when `sp-prd-scan` has produced a complete reconstruction package and the final PRD suite must be compiled from it.\"\ncompatibility: \"Requires spec-kit project structure with .specify\u002F directory\"\nmetadata:\n  author: \"github-spec-kit\"\n  source: \"templates\u002Fcommands\u002Fprd-build.md\"\n---\n## Invocation Syntax\n\n- In this integration, invoke workflow skills with `$sp-plan`-style syntax.\n- References such as `\u002Fsp.plan`, `\u002Fsp.tasks`, or `next_command: \u002Fsp.plan` are canonical workflow-state identifiers and handoff values.\n- Preserve those canonical state tokens exactly in artifacts and workflow state; do not rewrite them to this integration's invocation syntax.\n\n\n\n## Blocked Exit Contract\n\nIf blocked after safe recovery, read and follow\n`.specify\u002Ftemplates\u002Fworkflow-blocker-template.md` and its JSON schema. Never\nreturn only an error or “ask a human”; preserve state and keep agent-capable\nrepair agent-owned. Set `human_action_required: true` only for authority,\ncredentials, protected systems, human decisions\u002Freviews, or physical access.\nTailor steps, expected results, failure paths, evidence, and resume action to\nCI, visual review, or product decisions. Never claim completion.\n\nFor a feature runtime blocker, do not invent `resume_argv` or overwrite an\nexisting blocker. The CLI returns a read-only `show_argv` and structured\n`resolution_action`; `next_argv` stays empty while evidence is missing. After\nthe criteria are proven, attach sanitized evidence using the action's declared\ninput and execute its base argv. It restores the same owner and keeps the full\nblocker audit.\n\n# `\u002Fsp.prd-build` Reconstruction Build\n\n## Workflow Contract Summary\n\nThis summary is routing metadata only. The full workflow contract is the frontmatter plus the sections below.\n\n- Use `sp-prd-build` after `sp-prd-scan` has produced a validated reconstruction package.\n- Primary truth source: the scan package under `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002F`, not a fresh repository crawl.\n- Primary terminal state: completed master pack and exports, or explicit refusal back to `sp-prd-scan`.\n\n## Project Learning\n\nThe CLI is the only agent-facing Learning read surface:\n\n1. Run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify learning start --command '\u003Cclassic-command-name>' --format json` before deeper non-trivial work.\n2. Select summaries by applicability and triggers; use `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify learning list --command '\u003Cclassic-command-name>' --format json` only to filter or page.\n3. Execute one matching card's `show_argv`. Do not parse Learning storage.\n\nAfter minimal live inspection identifies a reused operation or changed entry point, rerun targeted recall with current code, tests, and task\u002Fcontract evidence, for example `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify learning list --command '\u003Cclassic-command-name>' --context 'operation_owner=\u003Cowner>' --context 'consumer_owner=\u003Cconsumer>' --context 'outcome=\u003Cresult-family>' --format json`. Do not derive these facets from archived specifications. An exact operation-owner match may surface a cross-command candidate even when the new consumer differs; treat it as a candidate, expand one `show_argv`, verify it against live evidence, and do not auto-apply it.\n\nWhen the entrypoint outcome audit is triggered, persist the live facets as `learning_context`, the contextual invocation as `learning_search_refs`, and returned refs as `learning_candidate_refs`. Record exactly one `applied`, `not_applicable`, or `deferred` item in `learning_dispositions` for every candidate. Do not silently ignore a candidate: applied Learning traces to requirement\u002Fconsequence refs, not-applicable needs current evidence, and deferred needs an explicit deferral ref.\n\n`start`, `list`, and `show` are read-only. Current repository evidence,\n`.specify\u002Fmemory\u002Fconstitution.md`, and explicit user direction override stale or\ncandidate Learning.\n\nAt closeout, corrections, retries, route changes, recovery, false leads, hidden\ndependencies, validation\u002Ftooling\u002Fstate\u002Fcognition gaps, constraints, and near\nmisses are capture signals. Prefer `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify learning capture-auto`\nfrom owning state; manual capture includes summary, problem, action, triggers,\nsuccess criteria, avoid items, exceptions, and evidence.\n\n- `fast`: skip unless the task escalates.\n- `accept`, `analyze`, `ask`, `auto`, `constitution`, `explain`,\n  `implement-teams`, `taskstoissues`, and `team`: consume-only; do not violate\n  their write boundaries to capture.\n- Other non-trivial workflows: consume before deeper work; capture reusable\n  signals at closeout or record a no-learning decision.\n\nThe `policy` returned by the CLI is authoritative when prompt wording drifts.\n\n## Objective\n\n[AGENT] Compile the reconstruction package into a delivery-grade PRD suite and prove reverse coverage validation.\n\n`sp-prd-build` must not become a second repository scan. It must not silently fill critical evidence gaps. When the scan package is incomplete, stop and route back to `sp-prd-scan`.\nFinal outputs must preserve `Evidence`, `Inference`, and `Unknown` labels rather than flattening them during synthesis.\nBefore writing exports, the build step must collect and validate the scan evidence bundle: scan packets, worker results, and the machine-readable reconstruction contracts produced by `sp-prd-scan`. That intake includes results returned by mandatory subagents before any export synthesis begins.\n\n## Context\n\nRequired build inputs:\n\n- The scan workspace under `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002F`\n- Core scan artifacts:\n  - `workflow-state.md`\n  - `prd-scan.md`\n  - `coverage-ledger.json`\n  - `capability-ledger.json`\n  - `artifact-contracts.json`\n  - `reconstruction-checklist.json`\n- Machine-readable reconstruction contracts:\n  - `entrypoint-ledger.json`\n  - `config-contracts.json`\n  - `protocol-contracts.json`\n  - `state-machines.json`\n  - `error-semantics.json`\n  - `verification-surfaces.json`\n- Scan packets under `scan-packets\u002F\u003Clane-id>.md`\n- Project classification from the scan package: `ui`, `service`, or `mixed`\n\n## Mandatory Subagent Execution\n\nAll substantive tasks in ordinary `sp-*` workflows default to and must use subagents.\n\nThe leader orchestrates: route, split tasks, prepare task contracts, dispatch subagents, wait for structured handoffs, integrate results, verify, and update state.\n\nBefore dispatch, every subagent lane needs a task contract with objective, authoritative inputs, allowed scope, forbidden actions, acceptance checks, verification evidence, and structured handoff format.\n\nUse `execution_model: subagent-mandatory`.\nUse `dispatch_shape: one-subagent | parallel-subagents`.\nUse `execution_surface: native-subagents`.\n\nBuild-support lanes operate on the run bundle, not the live repository.\n\n## Required Inputs\n\nBefore writing final exports, read:\n\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fworkflow-state.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fprd-scan.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fcoverage-ledger.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fcapability-ledger.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fartifact-contracts.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Freconstruction-checklist.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fentrypoint-ledger.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fconfig-contracts.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fprotocol-contracts.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fstate-machines.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Ferror-semantics.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fverification-surfaces.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fscan-packets\u002F\u003Clane-id>.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fworker-results\u002F**`\n\n## PRD Run State Protocol\n\n- `workflow-state.md` under `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002F` is the resumable state surface for `sp-prd-scan` and `sp-prd-build`.\n- [AGENT] Create or resume `workflow-state.md` before substantial build work.\n- If `workflow-state.md` exists with `active_command: sp-prd-build` and a non-terminal build state, resume from it instead of rebuilding intent from chat memory.\n- Track at least:\n  - `active_command: sp-prd-build`\n  - `status: validating | executing-packets | synthesizing | reverse-validating | blocked | complete`\n  - `scan_status`\n  - `build_status: pending | executing | blocked | complete`\n  - `classification`\n  - `current_packet`\n  - `accepted_packet_results`\n  - `rejected_packet_results`\n  - `failed_readiness_checks`\n  - `failed_reverse_coverage_checks`\n  - `next_action`\n  - `next_command`\n  - `handoff_reason`\n  - `open_gaps`\n\n## Process\n\n1. Validate that the `sp-prd-scan` package is complete enough to build.\n2. Perform packet evidence intake across scan packets, ledgers, JSON contracts, and worker results returned by mandatory subagent lanes.\n3. Compile `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fmaster\u002Fmaster-pack.md` from scan outputs only.\n4. Render `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002FREADME.md`, `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fprd.md`, and the supporting exports.\n5. Respect classification-aware export semantics: `ui`, `service`, and `mixed` runs must keep the final package grounded in the scan classification even when the fixed export set is used.\n6. Run reverse coverage validation across capabilities, artifacts, field-level contracts, and `Evidence` \u002F `Inference` \u002F `Unknown` labels.\n7. Refuse completion and route back to `sp-prd-scan` when critical gaps remain.\n\n## Validate Scan Inputs Before Execution\n\n- Refuse build execution if required scan artifacts are missing or malformed.\n- Treat the scan workspace under `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002F` as the only authoritative fact source for `sp-prd-build`.\n- Do not reread the repository to fill gaps.\n\n## Compile And Validate PrdBuildPacket Inputs\n\n- [AGENT] Compile a validated `PrdBuildPacket` before dispatch or `subagent-blocked` status.\n- A valid `PrdBuildPacket` must include:\n  - `lane_id`\n  - `mode: bundle_only`\n  - `packet_scope`\n  - `required_scan_inputs`\n  - `required_contract_files`\n  - `required_worker_results`\n  - `expected_exports`\n  - `traceability_targets`\n  - `forbidden_actions`\n  - `minimum_verification`\n  - `result_handoff_path`\n- Hard rule: do not dispatch from raw scan prose alone.\n\n## Readiness Refusal Rules\n\n`sp-prd-build` must refuse completion when:\n\n- required scan artifacts are missing or malformed\n- worker results are absent or structurally shallow\n- critical reconstruction claims cannot be traced back to scan-package evidence\n- export landing for critical artifacts is missing\n- unresolved critical unknowns remain in the bundle\n- the build would need new repository facts to complete honestly\n\nWhen refusal happens, report the smallest safe repair and route back to `sp-prd-scan`.\n\n## Execution Dispatch\n\n- [AGENT] Before build-support packet dispatch begins, assess workload shape and the current agent capability snapshot, then apply the shared policy contract: `choose_subagent_dispatch(command_name=\"prd-build\", snapshot, workload_shape)`.\n- Persist the decision fields exactly: `execution_model: subagent-mandatory`, `dispatch_shape: one-subagent | parallel-subagents`, `execution_surface: native-subagents`.\n- Decision order is fixed:\n  - One safe validated intake or validation lane -> `one-subagent` on `native-subagents` when available.\n  - Two or more isolated bundle-processing lanes -> `parallel-subagents` on `native-subagents` when available.\n  - Any need for new repository facts, missing build packet, or unavailable delegation -> `subagent-blocked` with a recorded reason.\n\n## Build Packet Dispatch\n\n- `subagent-blocked` stops substantive build work. Record the blocker and stop for escalation or recovery. Do not continue by turning `sp-prd-build` into a second repository scan.\n- Required join points:\n  - before writing `master\u002Fmaster-pack.md`\n  - before writing or finalizing `exports\u002F**`\n  - before reverse coverage \u002F traceability validation\n- Idle subagent output is not an accepted result.\n- The leader must wait for every dispatched build-support lane and integrate the returned evidence before writing exports or declaring the build complete.\n\n## Build Worker Result Contract\n\nEvery build-support lane result must include:\n\n- `lane_id`\n- `reported_status`\n- `bundle_inputs_read`\n- `traceability_findings`\n- `export_landing_findings`\n- `confidence`\n- `unknowns`\n- `recommended_repairs`\n- `minimum_verification`\n- `result_handoff_path`\n\nReject any build-lane output that lacks concrete bundle inputs, omits critical unknowns, or relies on live repository rereads instead of bundle inputs.\n\n## Output Contract\n\nThe build phase writes:\n\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fworkflow-state.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fmaster\u002Fmaster-pack.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002FREADME.md` - package navigation entry for the PRD suite\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fprd.md` - primary reader-facing PRD\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Freconstruction-appendix.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fdata-model.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fintegration-contracts.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fruntime-behaviors.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fconfig-contracts.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fprotocol-contracts.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fstate-machines.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Ferror-semantics.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fverification-surface.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Freconstruction-risks.md`\n\nClassification-aware export rule:\n\n- `ui` runs must keep UI-facing behaviors explicit in the exported package.\n- `service` runs must keep service, API, CLI, and runtime contract behaviors explicit in the exported package.\n- `mixed` runs must preserve both UI and service surfaces rather than collapsing to one side.\n\n## Quality Gates\n\n- No New Facts Gate: final exports must be grounded in the scan package rather than new repository rereads.\n- Artifact Landing Gate: critical artifacts from `artifact-contracts.json` must land in the master pack and appropriate exports.\n- Field-Level Coverage Gate: field, schema, mapping, and transition details must not be flattened into prose-only summaries.\n- Inference Ceiling Gate: inference can summarize evidence, but it cannot replace missing critical facts.\n- Evidence Label Gate: outputs and build validation must preserve `Evidence`, `Inference`, and `Unknown` handling.\n- Classification Export Gate: `ui`, `service`, and `mixed` classification semantics must survive into the final export package.\n- Critical Unknown Refusal Gate: unresolved critical unknowns in the validated scan evidence bundle block final export completion.\n- Traceability Gate: every reconstruction claim in the master pack and exports must trace back to scan-package evidence.\n- Reconstruction Readiness Gate: the compiled archive must preserve enough L4-level detail to recreate critical behavior.\n- Navigation Entry Gate: the compiled archive must include a package navigation entry so the supporting exports are usable as a coherent PRD suite.\n\n## Traceability Validation\n\n- Every reconstruction claim in the master pack and exports must trace back to scan-package evidence.\n- Reject any build-lane output that relies on live repository rereads instead of bundle inputs.\n\n## Report Completion\n\n- Before reporting success, confirm that `workflow-state.md` records the final build status, accepted packet results, rejected packet results, readiness failures, reverse-coverage outcomes, and the final handoff decision.\n- Successful completion must name the bundle inputs read, the accepted packet results that informed `master\u002Fmaster-pack.md` and `exports\u002F**`, and any remaining non-critical unknowns.\n- Blocked completion must name the failed readiness or traceability check, the affected packet or export target, and the smallest safe repair to resume through `sp-prd-scan` or the current build run.\n\n## Guardrails\n\n- `sp-prd-build` must not become a second repository scan.\n- `sp-prd-build` must not silently fill critical evidence gaps.\n- `sp-prd-build` must not strip `Evidence`, `Inference`, or `Unknown` labels from consequential claims.\n- If the scan package is incomplete, route back to `sp-prd-scan` instead of guessing.\n\n## Codex Subagent Capability Discovery\n\n- Execution model: preserve the workflow's existing `subagent-mandatory`, `subagents-first`, `adaptive`, or `subagent-assisted` policy.\n- Dispatch shape: preserve the workflow's existing dispatch shape; use `subagent-blocked` only after the discovery step below fails or is unsafe.\n- Execution surface: prefer `native-subagents` when the current runtime supports it; use `none` only after recording the unavailable or unsafe surface.\n- Native subagent capability discovery: Before recording `subagent-blocked`, confirm the current runtime exposes `spawn_agent`, `wait_agent`, and `close_agent`; if they are not visible, use the active tool discovery mechanism for multi-agent or subagent tools first.\n- Do not record `subagent-blocked` until this capability discovery step is complete and the exact unavailable or unsafe surface is recorded.\n- Native subagent dispatch: Dispatch bounded subagents through `spawn_agent`.\n- Join behavior: Rejoin with `wait_agent`, integrate, then `close_agent`.\n- Preserve this workflow's existing packet, handoff, artifact, and result schema; this section only governs capability discovery before dispatch or blocked-state recording.\n","## Invocation Syntax\n\n- In this integration, invoke workflow skills with `$sp-plan`-style syntax.\n- References such as `\u002Fsp.plan`, `\u002Fsp.tasks`, or `next_command: \u002Fsp.plan` are canonical workflow-state identifiers and handoff values.\n- Preserve those canonical state tokens exactly in artifacts and workflow state; do not rewrite them to this integration's invocation syntax.\n\n\n\n## Blocked Exit Contract\n\nIf blocked after safe recovery, read and follow\n`.specify\u002Ftemplates\u002Fworkflow-blocker-template.md` and its JSON schema. Never\nreturn only an error or “ask a human”; preserve state and keep agent-capable\nrepair agent-owned. Set `human_action_required: true` only for authority,\ncredentials, protected systems, human decisions\u002Freviews, or physical access.\nTailor steps, expected results, failure paths, evidence, and resume action to\nCI, visual review, or product decisions. Never claim completion.\n\nFor a feature runtime blocker, do not invent `resume_argv` or overwrite an\nexisting blocker. The CLI returns a read-only `show_argv` and structured\n`resolution_action`; `next_argv` stays empty while evidence is missing. After\nthe criteria are proven, attach sanitized evidence using the action's declared\ninput and execute its base argv. It restores the same owner and keeps the full\nblocker audit.\n\n# `\u002Fsp.prd-build` Reconstruction Build\n\n## Workflow Contract Summary\n\nThis summary is routing metadata only. The full workflow contract is the frontmatter plus the sections below.\n\n- Use `sp-prd-build` after `sp-prd-scan` has produced a validated reconstruction package.\n- Primary truth source: the scan package under `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002F`, not a fresh repository crawl.\n- Primary terminal state: completed master pack and exports, or explicit refusal back to `sp-prd-scan`.\n\n## Project Learning\n\nThe CLI is the only agent-facing Learning read surface:\n\n1. Run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify learning start --command '\u003Cclassic-command-name>' --format json` before deeper non-trivial work.\n2. Select summaries by applicability and triggers; use `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify learning list --command '\u003Cclassic-command-name>' --format json` only to filter or page.\n3. Execute one matching card's `show_argv`. Do not parse Learning storage.\n\nAfter minimal live inspection identifies a reused operation or changed entry point, rerun targeted recall with current code, tests, and task\u002Fcontract evidence, for example `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify learning list --command '\u003Cclassic-command-name>' --context 'operation_owner=\u003Cowner>' --context 'consumer_owner=\u003Cconsumer>' --context 'outcome=\u003Cresult-family>' --format json`. Do not derive these facets from archived specifications. An exact operation-owner match may surface a cross-command candidate even when the new consumer differs; treat it as a candidate, expand one `show_argv`, verify it against live evidence, and do not auto-apply it.\n\nWhen the entrypoint outcome audit is triggered, persist the live facets as `learning_context`, the contextual invocation as `learning_search_refs`, and returned refs as `learning_candidate_refs`. Record exactly one `applied`, `not_applicable`, or `deferred` item in `learning_dispositions` for every candidate. Do not silently ignore a candidate: applied Learning traces to requirement\u002Fconsequence refs, not-applicable needs current evidence, and deferred needs an explicit deferral ref.\n\n`start`, `list`, and `show` are read-only. Current repository evidence,\n`.specify\u002Fmemory\u002Fconstitution.md`, and explicit user direction override stale or\ncandidate Learning.\n\nAt closeout, corrections, retries, route changes, recovery, false leads, hidden\ndependencies, validation\u002Ftooling\u002Fstate\u002Fcognition gaps, constraints, and near\nmisses are capture signals. Prefer `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify learning capture-auto`\nfrom owning state; manual capture includes summary, problem, action, triggers,\nsuccess criteria, avoid items, exceptions, and evidence.\n\n- `fast`: skip unless the task escalates.\n- `accept`, `analyze`, `ask`, `auto`, `constitution`, `explain`,\n  `implement-teams`, `taskstoissues`, and `team`: consume-only; do not violate\n  their write boundaries to capture.\n- Other non-trivial workflows: consume before deeper work; capture reusable\n  signals at closeout or record a no-learning decision.\n\nThe `policy` returned by the CLI is authoritative when prompt wording drifts.\n\n## Objective\n\n[AGENT] Compile the reconstruction package into a delivery-grade PRD suite and prove reverse coverage validation.\n\n`sp-prd-build` must not become a second repository scan. It must not silently fill critical evidence gaps. When the scan package is incomplete, stop and route back to `sp-prd-scan`.\nFinal outputs must preserve `Evidence`, `Inference`, and `Unknown` labels rather than flattening them during synthesis.\nBefore writing exports, the build step must collect and validate the scan evidence bundle: scan packets, worker results, and the machine-readable reconstruction contracts produced by `sp-prd-scan`. That intake includes results returned by mandatory subagents before any export synthesis begins.\n\n## Context\n\nRequired build inputs:\n\n- The scan workspace under `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002F`\n- Core scan artifacts:\n  - `workflow-state.md`\n  - `prd-scan.md`\n  - `coverage-ledger.json`\n  - `capability-ledger.json`\n  - `artifact-contracts.json`\n  - `reconstruction-checklist.json`\n- Machine-readable reconstruction contracts:\n  - `entrypoint-ledger.json`\n  - `config-contracts.json`\n  - `protocol-contracts.json`\n  - `state-machines.json`\n  - `error-semantics.json`\n  - `verification-surfaces.json`\n- Scan packets under `scan-packets\u002F\u003Clane-id>.md`\n- Project classification from the scan package: `ui`, `service`, or `mixed`\n\n## Mandatory Subagent Execution\n\nAll substantive tasks in ordinary `sp-*` workflows default to and must use subagents.\n\nThe leader orchestrates: route, split tasks, prepare task contracts, dispatch subagents, wait for structured handoffs, integrate results, verify, and update state.\n\nBefore dispatch, every subagent lane needs a task contract with objective, authoritative inputs, allowed scope, forbidden actions, acceptance checks, verification evidence, and structured handoff format.\n\nUse `execution_model: subagent-mandatory`.\nUse `dispatch_shape: one-subagent | parallel-subagents`.\nUse `execution_surface: native-subagents`.\n\nBuild-support lanes operate on the run bundle, not the live repository.\n\n## Required Inputs\n\nBefore writing final exports, read:\n\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fworkflow-state.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fprd-scan.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fcoverage-ledger.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fcapability-ledger.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fartifact-contracts.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Freconstruction-checklist.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fentrypoint-ledger.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fconfig-contracts.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fprotocol-contracts.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fstate-machines.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Ferror-semantics.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fverification-surfaces.json`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fscan-packets\u002F\u003Clane-id>.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fworker-results\u002F**`\n\n## PRD Run State Protocol\n\n- `workflow-state.md` under `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002F` is the resumable state surface for `sp-prd-scan` and `sp-prd-build`.\n- [AGENT] Create or resume `workflow-state.md` before substantial build work.\n- If `workflow-state.md` exists with `active_command: sp-prd-build` and a non-terminal build state, resume from it instead of rebuilding intent from chat memory.\n- Track at least:\n  - `active_command: sp-prd-build`\n  - `status: validating | executing-packets | synthesizing | reverse-validating | blocked | complete`\n  - `scan_status`\n  - `build_status: pending | executing | blocked | complete`\n  - `classification`\n  - `current_packet`\n  - `accepted_packet_results`\n  - `rejected_packet_results`\n  - `failed_readiness_checks`\n  - `failed_reverse_coverage_checks`\n  - `next_action`\n  - `next_command`\n  - `handoff_reason`\n  - `open_gaps`\n\n## Process\n\n1. Validate that the `sp-prd-scan` package is complete enough to build.\n2. Perform packet evidence intake across scan packets, ledgers, JSON contracts, and worker results returned by mandatory subagent lanes.\n3. Compile `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fmaster\u002Fmaster-pack.md` from scan outputs only.\n4. Render `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002FREADME.md`, `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fprd.md`, and the supporting exports.\n5. Respect classification-aware export semantics: `ui`, `service`, and `mixed` runs must keep the final package grounded in the scan classification even when the fixed export set is used.\n6. Run reverse coverage validation across capabilities, artifacts, field-level contracts, and `Evidence` \u002F `Inference` \u002F `Unknown` labels.\n7. Refuse completion and route back to `sp-prd-scan` when critical gaps remain.\n\n## Validate Scan Inputs Before Execution\n\n- Refuse build execution if required scan artifacts are missing or malformed.\n- Treat the scan workspace under `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002F` as the only authoritative fact source for `sp-prd-build`.\n- Do not reread the repository to fill gaps.\n\n## Compile And Validate PrdBuildPacket Inputs\n\n- [AGENT] Compile a validated `PrdBuildPacket` before dispatch or `subagent-blocked` status.\n- A valid `PrdBuildPacket` must include:\n  - `lane_id`\n  - `mode: bundle_only`\n  - `packet_scope`\n  - `required_scan_inputs`\n  - `required_contract_files`\n  - `required_worker_results`\n  - `expected_exports`\n  - `traceability_targets`\n  - `forbidden_actions`\n  - `minimum_verification`\n  - `result_handoff_path`\n- Hard rule: do not dispatch from raw scan prose alone.\n\n## Readiness Refusal Rules\n\n`sp-prd-build` must refuse completion when:\n\n- required scan artifacts are missing or malformed\n- worker results are absent or structurally shallow\n- critical reconstruction claims cannot be traced back to scan-package evidence\n- export landing for critical artifacts is missing\n- unresolved critical unknowns remain in the bundle\n- the build would need new repository facts to complete honestly\n\nWhen refusal happens, report the smallest safe repair and route back to `sp-prd-scan`.\n\n## Execution Dispatch\n\n- [AGENT] Before build-support packet dispatch begins, assess workload shape and the current agent capability snapshot, then apply the shared policy contract: `choose_subagent_dispatch(command_name=\"prd-build\", snapshot, workload_shape)`.\n- Persist the decision fields exactly: `execution_model: subagent-mandatory`, `dispatch_shape: one-subagent | parallel-subagents`, `execution_surface: native-subagents`.\n- Decision order is fixed:\n  - One safe validated intake or validation lane -> `one-subagent` on `native-subagents` when available.\n  - Two or more isolated bundle-processing lanes -> `parallel-subagents` on `native-subagents` when available.\n  - Any need for new repository facts, missing build packet, or unavailable delegation -> `subagent-blocked` with a recorded reason.\n\n## Build Packet Dispatch\n\n- `subagent-blocked` stops substantive build work. Record the blocker and stop for escalation or recovery. Do not continue by turning `sp-prd-build` into a second repository scan.\n- Required join points:\n  - before writing `master\u002Fmaster-pack.md`\n  - before writing or finalizing `exports\u002F**`\n  - before reverse coverage \u002F traceability validation\n- Idle subagent output is not an accepted result.\n- The leader must wait for every dispatched build-support lane and integrate the returned evidence before writing exports or declaring the build complete.\n\n## Build Worker Result Contract\n\nEvery build-support lane result must include:\n\n- `lane_id`\n- `reported_status`\n- `bundle_inputs_read`\n- `traceability_findings`\n- `export_landing_findings`\n- `confidence`\n- `unknowns`\n- `recommended_repairs`\n- `minimum_verification`\n- `result_handoff_path`\n\nReject any build-lane output that lacks concrete bundle inputs, omits critical unknowns, or relies on live repository rereads instead of bundle inputs.\n\n## Output Contract\n\nThe build phase writes:\n\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fworkflow-state.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fmaster\u002Fmaster-pack.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002FREADME.md` - package navigation entry for the PRD suite\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fprd.md` - primary reader-facing PRD\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Freconstruction-appendix.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fdata-model.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fintegration-contracts.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fruntime-behaviors.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fconfig-contracts.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fprotocol-contracts.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fstate-machines.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Ferror-semantics.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Fverification-surface.md`\n- `.specify\u002Fprd-runs\u002F\u003Crun-id>\u002Fexports\u002Freconstruction-risks.md`\n\nClassification-aware export rule:\n\n- `ui` runs must keep UI-facing behaviors explicit in the exported package.\n- `service` runs must keep service, API, CLI, and runtime contract behaviors explicit in the exported package.\n- `mixed` runs must preserve both UI and service surfaces rather than collapsing to one side.\n\n## Quality Gates\n\n- No New Facts Gate: final exports must be grounded in the scan package rather than new repository rereads.\n- Artifact Landing Gate: critical artifacts from `artifact-contracts.json` must land in the master pack and appropriate exports.\n- Field-Level Coverage Gate: field, schema, mapping, and transition details must not be flattened into prose-only summaries.\n- Inference Ceiling Gate: inference can summarize evidence, but it cannot replace missing critical facts.\n- Evidence Label Gate: outputs and build validation must preserve `Evidence`, `Inference`, and `Unknown` handling.\n- Classification Export Gate: `ui`, `service`, and `mixed` classification semantics must survive into the final export package.\n- Critical Unknown Refusal Gate: unresolved critical unknowns in the validated scan evidence bundle block final export completion.\n- Traceability Gate: every reconstruction claim in the master pack and exports must trace back to scan-package evidence.\n- Reconstruction Readiness Gate: the compiled archive must preserve enough L4-level detail to recreate critical behavior.\n- Navigation Entry Gate: the compiled archive must include a package navigation entry so the supporting exports are usable as a coherent PRD suite.\n\n## Traceability Validation\n\n- Every reconstruction claim in the master pack and exports must trace back to scan-package evidence.\n- Reject any build-lane output that relies on live repository rereads instead of bundle inputs.\n\n## Report Completion\n\n- Before reporting success, confirm that `workflow-state.md` records the final build status, accepted packet results, rejected packet results, readiness failures, reverse-coverage outcomes, and the final handoff decision.\n- Successful completion must name the bundle inputs read, the accepted packet results that informed `master\u002Fmaster-pack.md` and `exports\u002F**`, and any remaining non-critical unknowns.\n- Blocked completion must name the failed readiness or traceability check, the affected packet or export target, and the smallest safe repair to resume through `sp-prd-scan` or the current build run.\n\n## Guardrails\n\n- `sp-prd-build` must not become a second repository scan.\n- `sp-prd-build` must not silently fill critical evidence gaps.\n- `sp-prd-build` must not strip `Evidence`, `Inference`, or `Unknown` labels from consequential claims.\n- If the scan package is incomplete, route back to `sp-prd-scan` instead of guessing.\n\n## Codex Subagent Capability Discovery\n\n- Execution model: preserve the workflow's existing `subagent-mandatory`, `subagents-first`, `adaptive`, or `subagent-assisted` policy.\n- Dispatch shape: preserve the workflow's existing dispatch shape; use `subagent-blocked` only after the discovery step below fails or is unsafe.\n- Execution surface: prefer `native-subagents` when the current runtime supports it; use `none` only after recording the unavailable or unsafe surface.\n- Native subagent capability discovery: Before recording `subagent-blocked`, confirm the current runtime exposes `spawn_agent`, `wait_agent`, and `close_agent`; if they are not visible, use the active tool discovery mechanism for multi-agent or subagent tools first.\n- Do not record `subagent-blocked` until this capability discovery step is complete and the exact unavailable or unsafe surface is recorded.\n- Native subagent dispatch: Dispatch bounded subagents through `spawn_agent`.\n- Join behavior: Rejoin with `wait_agent`, integrate, then `close_agent`.\n- Preserve this workflow's existing packet, handoff, artifact, and result schema; this section only governs capability discovery before dispatch or blocked-state recording.\n",{"name":5,"metadata":24,"description":7,"compatibility":27},{"author":25,"source":26},"github-spec-kit","templates\u002Fcommands\u002Fprd-build.md","Requires spec-kit project structure with .specify\u002F directory","main","021f5cbe02157229460a577e9a585f2da6d78cb0",".codex\u002Fskills\u002Fsp-prd-build","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck","https:\u002F\u002Fgithub.com\u002Fchenziyang110","2026-08-07 18:10:54",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add chenziyang110\u002Flaunchdeck --skill sp-prd-build",{"tool":40,"command":41},"bunx","bunx skills add chenziyang110\u002Flaunchdeck --skill sp-prd-build",{"tool":43,"command":44},"pnpm","pnpm dlx skills add chenziyang110\u002Flaunchdeck --skill sp-prd-build","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-prd-build\u002FSKILL.md",true,[],[49,56,62,68,75,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7875F3HQ1GF5F6BR36KY3JE","launchdeck-agent","Codex host adapter contract fixture for Launchdeck.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fagent-hosts\u002Fcodex\u002Fskill\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7875DV2DQR33K1NFJHKAMZP","Claude host adapter contract fixture for Launchdeck.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fagent-hosts\u002Fclaude\u002Fskill\u002FSKILL.md",[],[],{"skillNo":63,"name":51,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M78759JQ7A6FQ8KDQTNYS3X9","Use this skill aggressively for local project lifecycle operations even when the user does not mention Launchdeck: start this project, run the dev server, dev, build, test, restart service, stop service, show logs, inspect ports, port is occupied, clean cache; and when the user explicitly asks to configure this local project for Launchdeck or create or generate a project-adapted `.launchdeck.yml`, including 为这个项目生成 Launchdeck 配置. Do not use for ordinary code edits, docs-only work, general explanations, API design discussion, or production deployment unless the user also asks to operate or configure a local project or service.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Fagent\u002Finstaller-payload\u002Fskill\u002Flaunchdeck-agent\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M78753ZJQ7G2CZT1W1G8WRJV","zig-testing","Use ONLY when user explicitly requests Zig test code, built-in test runner configuration,\ntest failure diagnosis, or coverage for Zig projects.\n\nTriggers: \"write test zig\", \"zig test\", \"testing.allocator\", \"zig coverage\",\n\"comptime test\", \"zig expectError\", \"zig snapshot test\", \"zig fuzz\".\n\nDo NOT activate for: general Zig coding without test context, build.zig configuration\nfor non-test targets, Zig compiler errors, or Zig build system setup.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fzig-testing\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M78750JXY4Z5D5W1EX3PQ31Z","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7874X2T83EQQFRCEY5SJJVC","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fverification-before-completion\u002FSKILL.md",[],[]]