[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6D9BGSDC8H77JFN92Z494K3":3,"skill-same:01M6D9BGSDC8H77JFN92Z494K3":70},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6D9BGSDC8H77JFN92Z494K3","ship-end",null,"Wrap up the current session — update docs, commit, and push","GeorgeQLe\u002Fagentic-skills","GeorgeQLe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F21134126?v=4","01M6D2JP418S0VGJGF8M93EC3H","George Le","01M6D2JPBAKYD82TA5FS6HKQ3D",1,"MIT","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fexec-loop\u002Fclaude\u002Fship-end\u002Farchive\u002Fv0.11\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"ship end","end","ship","v0","social","conversation","wrap","update docs","up","session","docs","wrap up","save","push","shipping","update","deploy","commit","2026-11-10 10:12:30",false,"---\nname: ship-end\ndescription: Wrap up the current session — update docs, commit, and push\ntype: shipping\nversion: v0.11\nrequired_conventions: [social-ledger]\nargument-hint: \"[--no-deploy] [--save-conversation] [--save-all-conversations]\"\n---\n\n# Ship End\n\nWrap up the current session: mark progress, commit, and push. If `$ARGUMENTS` contains `--save-conversation`, save the current conversation to `conversations\u002F`. If `$ARGUMENTS` contains `--save-all-conversations`, export all past conversations to `conversations\u002F`.\n\n## Process\n\n1. **Check for changes:**\n   - Run `git status` and `git diff` to see all changes.\n   - If the working tree is clean and no unpushed commits: report \"nothing to ship\" and stop.\n\n2. **Update task tracking:**\n   - Update `tasks\u002Ftodo.md` — mark completed items as done, note any outstanding items or blockers.\n   - Update milestone progress in `tasks\u002Froadmap.md` if criteria were met.\n   - Check `tasks\u002Fmanual-todo.md` (if it exists) — note the status of manual tasks (how many checked vs unchecked). Do NOT modify checked items.\n   - Check `tasks\u002Frecord-todo.md` and `tasks\u002Frecurring-todo.md` if they exist — note unchecked advisory counts only. Do NOT treat them as blockers unless an item has been promoted into `tasks\u002Ftodo.md`.\n   - Update `tasks\u002Fhistory.md` — append a brief record of what was accomplished this session (phase\u002Fstep completed, key changes). Create it if it doesn't exist.\n   - If `tasks\u002Ftodo.md`, `tasks\u002Froadmap.md`, `tasks\u002Fmanual-todo.md`, `tasks\u002Frecord-todo.md`, or `tasks\u002Frecurring-todo.md` changed and `scripts\u002Faudit-task-docs.mjs` exists, run `node scripts\u002Faudit-task-docs.mjs` and fix any failures before final next-work routing.\n\n3. **Deploy (skip if `--no-deploy`):**\n   After shipping, deploy only when the project has an explicit manual deploy contract.\n   - **Check for deploy contract.** Look for `deploy.md` or `tasks\u002Fdeploy.md`.\n   - If neither file exists, skip deploy and report `Deploy skipped: no explicit manual deploy contract (deploy.md or tasks\u002Fdeploy.md)`.\n   - If a deploy contract exists, continue.\n   - **Invoke `\u002Fdeploy`** (release-ops pack) targeting the default environment (staging).\n   - Pass the deploy contract context to `\u002Fdeploy`.\n   - Skip ledger recording and staleness reporting — those are for standalone `\u002Fdeploy` invocations only.\n   - If `\u002Fdeploy` (release-ops pack) reports failure, report the error. Do not retry.\n\n4. **Save conversation (skip if `--save-conversation` and `--save-all-conversations` both absent):**\n   - Run `scripts\u002Fsave-conversation.sh` to export the current Claude Code conversation as a markdown file in `conversations\u002F`. If the script is not found or fails (e.g., not running in Claude Code, no local conversation history), warn and continue — do not block shipping. Include the generated file in the shipping boundary.\n   - If `$ARGUMENTS` contains `--save-all-conversations`, run `scripts\u002Fsave-conversation.sh --all` instead.\n\n5. **Ship the session changes:**\n   - Use the `\u002Fcommit-and-push-by-feature` workflow: group changes into logical feature\u002Ffunction buckets, use conventional commit messages, land the resulting commits on `main` or `master`, and push them there when the workflow succeeds.\n   - **Pack install artifact boundary:** Treat `.agents\u002Fproject.json` as the committed project designation. When pack configuration changed, include `.agents\u002Fproject.json` in the shipping boundary. Treat `.claude\u002Fskills\u002F**` and `.codex\u002Fskills\u002F**` as generated local skill roots recreated by `scripts\u002Fpack.sh refresh`; generated skill roots must not be staged or committed. If those roots are untracked, leave them uncommitted and report them as generated local artifacts. If any path under those roots is already tracked or modified as a tracked file, stop unless the current task explicitly includes repository hygiene to untrack or ignore generated skill roots.\n\n6. **Report session summary:**\n   - What was accomplished\n   - Deploy status (if deployed)\n   - Test status — explicitly state whether any failing tests are expected (red phase: tests written before implementation) or unexpected (regressions\u002Fbugs that need fixing)\n   - What's outstanding\n   - Branch and commit list\n   - Confirm working tree is clean\n\n7. **BIP post suggestions** (advisory; never blocks wrap-up — run after the summary, even if shipping reported nothing):\n   - Read `.agents\u002Fproject.json`.\n   - If `alignment.build_in_public === true`, skip only the enablement question, then run the enabled BIP post-suggestion path below. Do not report only that the BIP gate was skipped.\n   - Else if `alignment.bip_prompt_dismissed === true`, skip both enablement and post suggestions.\n   - Otherwise ask the user once, concisely — explain that Build-In-Public mode generates source-safe social posts from your alignment pages and shipped work, and ask whether to enable it for this project.\n   - On **yes**: run `scripts\u002Fpack.sh set-bip on` (or `npx skillpacks set-bip on`) **and** `scripts\u002Fpack.sh set-bip-prompt dismiss` (or the `npx` equivalent). Then run the enabled BIP post-suggestion path for this shipped session.\n   - On **no**: run `scripts\u002Fpack.sh set-bip-prompt dismiss` (or the `npx` equivalent). Do not ask again.\n   - Enabled BIP post-suggestion path: inspect the shipped boundary from the session summary, changed files, commits, task\u002Fhistory notes, and any alignment pages. Read `.agents\u002Fproject.json.alignment.bip_platforms` only as optional priority\u002Franking metadata. Do not ask a project-platform setup question and do not use saved platforms as a filter. Load the shared social routers and every bundled text\u002Fcommunity and video channel convention.\n   - Infer `bip_phase` as exactly one of `research`, `prototyping`, or `implementation` from the shipped boundary. Following `docs\u002Fsocial-ledger-convention.md` plus every bundled channel convention, draft an exhaustive phase-aware batch of source-safe Build-In-Public post candidates for every bundled channel, or state that there is no safe public angle for this wrap-up. Mark top-ranked options clearly and keep rejected\u002Fnot-now options visible when useful for dedupe or future context. For each candidate, include target channel, optional priority rank from saved `alignment.bip_platforms`, `bip_phase`, angle, source basis, loaded convention path, risk level, claim-safety notes, publish precheck, and draft post text or a concise video\u002Fcommunity-post outline.\n   - **Write the batch to the single HTML BIP page, not inline.** Treat the successful ship as the equivalent of alignment-page confirmation and write the exhaustive per-channel batch to `alignment\u002Fbip-ship-end.html`, following the shared post-confirmation BIP page shape: set `data-alignment-page-kind=\"bip\"`, `data-bip-generation=\"post-confirmation\"`, `data-bip-source-skill=\"ship-end\"`, and `data-alignment-status=\"confirmed\"` on `\u003Chtml>`; cover every bundled text\u002Fcommunity and video channel; include the recommendation-notes, source-basis, claim-safety-notes, risk-level, publish-precheck, and loaded-convention-path fields with the recommended\u002Fnot-now\u002Frejected statuses; add the responsive viewport meta and the Brief Me TTS include before `\u003C\u002Fbody>`; and use no embeds or active approval gates. If `alignment\u002Fbip-ship-end.html` already exists, archive it first to `docs\u002Fhistory\u002Farchive\u002FYYYY-MM-DD\u002FHHMMSS\u002Falignment\u002Fbip-ship-end.html`. Include the page in `alignment\u002Findex.html` (with today's date), run the TTS inject step, and attempt to open it after wrap-up. Print a one-line terminal pointer to the file instead of dumping candidates inline. Do not publish externally or write social-ledger records without later explicit approval.\n\n## Output\n\n```\n## Session Summary\n- **Accomplished**: [what was done]\n- **Deploy**: [status]\n- **Tests**: [pass\u002Ffail — expected or unexpected]\n- **Manual tasks**: [X\u002FY complete, or \"none\"]\n- **Advisory tasks**: [record\u002Frecurring counts, or \"none\"]\n- **Outstanding**: [remaining work]\n- **Branch**: [branch name]\n- **Commits**: [list]\n- **Working tree**: clean\n- **Next work:** [specific task, blocker, verification gap, or \"none\"]\n- **Recommended next command:** [one command or route]\n```\n\n## Next-Step Routing\n\nBefore closing out the session, identify the next concrete work item from project state, then recommend the executor and invocation.\n\nOutput exactly two lines beyond the normal session summary:\n\n- **Next work:** \u003Cspecific task name, manual blocker, verification gap, or \"none\">\n- **Recommended next command:** \u003Cone command or route>\n\nRules:\n\n- Make the next work item primary. Derive it from `tasks\u002Ftodo.md`, `tasks\u002Fmanual-todo.md`, deploy status, validation gaps, smoke-test gaps, outstanding session work, or the absence of any remaining work. Do not use agent mode itself as the next work item.\n- Treat `tasks\u002Ftodo.md` as the only executable current-task surface. Historical roadmap entries and unchecked advisory\u002Fmanual\u002Frecord\u002Frecurring items are reconciliation candidates, not next executable work, unless the current active todo section explicitly promotes them.\n- Use `.\u002Fscripts\u002Fagent-mode.sh` only to choose command text. If it is missing, unset, or non-zero, infer routing from the current invocation and task type instead of asking the user to select a mode by default.\n- Prefer an owning workflow\u002Fdomain route over execution-loop defaults. If the next work item names a research, alignment, design, UI, UX, prototype-test, or copy-audit artifact or review page, recommend the specific owning skill, required user review, or compiled-YAML step directly. Use `\u002Fexec` only when no narrower installed skill, artifact contract, or review route owns the next action.\n- Inference defaults:\n  - Hybrid execution handoff → check `.agents\u002Fproject.json.enabled_packs` for `agent-bridge` — if `agent-bridge` is not enabled, recommend `npx skillpacks install agent-bridge` from the project shell first; if `agent-bridge` is enabled, recommend `\u002Fdelegate $exec`.\n  - Claude-only or orchestration-heavy work → after applying owning-route precedence above, recommend `\u002Fexec`.\n  - Codex-only execution → after applying owning-route precedence above, recommend `$exec`.\n  - External human-only manual work (browser\u002Fauth\u002FDNS\u002Fservice dashboard work with no reliable authenticated CLI\u002FAPI path, paid account setup, real-device checks, or production smoke-test work needing human sign-off) → check `.agents\u002Fproject.json.enabled_packs` for `guided-walkthrough` — if `guided-walkthrough` is not enabled, recommend `npx skillpacks install guided-walkthrough` from the project shell first; if `guided-walkthrough` is enabled, recommend `\u002Fguide` — or a Claude-guided manual step rather than `\u002Fexec`.\n  - Agent-executable work misfiled in `tasks\u002Fmanual-todo.md`, task-doc bookkeeping, stale `tasks\u002Fmanual-todo.md` cleanup, or reconciliation against repo\u002Fhistory reality → check `.agents\u002Fproject.json.enabled_packs` for `docs-health` — if `docs-health` is not enabled, recommend `npx skillpacks install docs-health` from the project shell first; if `docs-health` is enabled, recommend `\u002Freconcile-dev-docs fix tasks` — promotion to `tasks\u002Ftodo.md`, or a direct dev-doc audit, not `\u002Fguide`.\n- Only present multiple commands when the ambiguity materially changes execution safety or there are equally valid next work items. Otherwise choose the best route and mention degraded mode lookup inline.\n\n## Constraints\n\n- When recommending a skill from another pack, verify the pack is installed via `.agents\u002Fproject.json` `enabled_packs`. If not installed, include `npx skillpacks install \u003Cpack-name>` from the project shell as the prerequisite.\n- **Fix unrelated issues:** If any step surfaces errors, warnings, or lint issues — even ones unrelated to the current work — investigate and fix them before continuing. Commit these fixes separately with a descriptive message.\n- Do NOT modify CLAUDE.md. CLAUDE.md is for project conventions and config only — not progress tracking.\n- Progress and active work go in `tasks\u002Ftodo.md`. Completed work history goes in `tasks\u002Fhistory.md`.\n- Do not execute or block wrap-up on `tasks\u002Frecord-todo.md` or `tasks\u002Frecurring-todo.md` items unless they were explicitly promoted into `tasks\u002Ftodo.md`.\n- When task docs changed, do not finish with a next-work recommendation until `node scripts\u002Faudit-task-docs.mjs` passes, if that script exists.\n- Do not switch branches or create new branches unless the current state requires it.\n- Do not amend or rewrite history.\n- Do not commit secrets.\n- Do not push session-wrap-up commits to an existing feature branch. Use `\u002Fcommit-and-push-by-feature` to move the work onto `main` or `master` and push it there, or stop and report a blocker if that cannot be done safely.\n- If pre-commit hooks fail, fix and retry.\n- Never use GitHub Actions for deployment. Only use manual deploy scripts, Makefiles, or CLI commands.\n- Never deploy to production without explicit user confirmation.\n\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n","# Ship End\n\nWrap up the current session: mark progress, commit, and push. If `$ARGUMENTS` contains `--save-conversation`, save the current conversation to `conversations\u002F`. If `$ARGUMENTS` contains `--save-all-conversations`, export all past conversations to `conversations\u002F`.\n\n## Process\n\n1. **Check for changes:**\n   - Run `git status` and `git diff` to see all changes.\n   - If the working tree is clean and no unpushed commits: report \"nothing to ship\" and stop.\n\n2. **Update task tracking:**\n   - Update `tasks\u002Ftodo.md` — mark completed items as done, note any outstanding items or blockers.\n   - Update milestone progress in `tasks\u002Froadmap.md` if criteria were met.\n   - Check `tasks\u002Fmanual-todo.md` (if it exists) — note the status of manual tasks (how many checked vs unchecked). Do NOT modify checked items.\n   - Check `tasks\u002Frecord-todo.md` and `tasks\u002Frecurring-todo.md` if they exist — note unchecked advisory counts only. Do NOT treat them as blockers unless an item has been promoted into `tasks\u002Ftodo.md`.\n   - Update `tasks\u002Fhistory.md` — append a brief record of what was accomplished this session (phase\u002Fstep completed, key changes). Create it if it doesn't exist.\n   - If `tasks\u002Ftodo.md`, `tasks\u002Froadmap.md`, `tasks\u002Fmanual-todo.md`, `tasks\u002Frecord-todo.md`, or `tasks\u002Frecurring-todo.md` changed and `scripts\u002Faudit-task-docs.mjs` exists, run `node scripts\u002Faudit-task-docs.mjs` and fix any failures before final next-work routing.\n\n3. **Deploy (skip if `--no-deploy`):**\n   After shipping, deploy only when the project has an explicit manual deploy contract.\n   - **Check for deploy contract.** Look for `deploy.md` or `tasks\u002Fdeploy.md`.\n   - If neither file exists, skip deploy and report `Deploy skipped: no explicit manual deploy contract (deploy.md or tasks\u002Fdeploy.md)`.\n   - If a deploy contract exists, continue.\n   - **Invoke `\u002Fdeploy`** (release-ops pack) targeting the default environment (staging).\n   - Pass the deploy contract context to `\u002Fdeploy`.\n   - Skip ledger recording and staleness reporting — those are for standalone `\u002Fdeploy` invocations only.\n   - If `\u002Fdeploy` (release-ops pack) reports failure, report the error. Do not retry.\n\n4. **Save conversation (skip if `--save-conversation` and `--save-all-conversations` both absent):**\n   - Run `scripts\u002Fsave-conversation.sh` to export the current Claude Code conversation as a markdown file in `conversations\u002F`. If the script is not found or fails (e.g., not running in Claude Code, no local conversation history), warn and continue — do not block shipping. Include the generated file in the shipping boundary.\n   - If `$ARGUMENTS` contains `--save-all-conversations`, run `scripts\u002Fsave-conversation.sh --all` instead.\n\n5. **Ship the session changes:**\n   - Use the `\u002Fcommit-and-push-by-feature` workflow: group changes into logical feature\u002Ffunction buckets, use conventional commit messages, land the resulting commits on `main` or `master`, and push them there when the workflow succeeds.\n   - **Pack install artifact boundary:** Treat `.agents\u002Fproject.json` as the committed project designation. When pack configuration changed, include `.agents\u002Fproject.json` in the shipping boundary. Treat `.claude\u002Fskills\u002F**` and `.codex\u002Fskills\u002F**` as generated local skill roots recreated by `scripts\u002Fpack.sh refresh`; generated skill roots must not be staged or committed. If those roots are untracked, leave them uncommitted and report them as generated local artifacts. If any path under those roots is already tracked or modified as a tracked file, stop unless the current task explicitly includes repository hygiene to untrack or ignore generated skill roots.\n\n6. **Report session summary:**\n   - What was accomplished\n   - Deploy status (if deployed)\n   - Test status — explicitly state whether any failing tests are expected (red phase: tests written before implementation) or unexpected (regressions\u002Fbugs that need fixing)\n   - What's outstanding\n   - Branch and commit list\n   - Confirm working tree is clean\n\n7. **BIP post suggestions** (advisory; never blocks wrap-up — run after the summary, even if shipping reported nothing):\n   - Read `.agents\u002Fproject.json`.\n   - If `alignment.build_in_public === true`, skip only the enablement question, then run the enabled BIP post-suggestion path below. Do not report only that the BIP gate was skipped.\n   - Else if `alignment.bip_prompt_dismissed === true`, skip both enablement and post suggestions.\n   - Otherwise ask the user once, concisely — explain that Build-In-Public mode generates source-safe social posts from your alignment pages and shipped work, and ask whether to enable it for this project.\n   - On **yes**: run `scripts\u002Fpack.sh set-bip on` (or `npx skillpacks set-bip on`) **and** `scripts\u002Fpack.sh set-bip-prompt dismiss` (or the `npx` equivalent). Then run the enabled BIP post-suggestion path for this shipped session.\n   - On **no**: run `scripts\u002Fpack.sh set-bip-prompt dismiss` (or the `npx` equivalent). Do not ask again.\n   - Enabled BIP post-suggestion path: inspect the shipped boundary from the session summary, changed files, commits, task\u002Fhistory notes, and any alignment pages. Read `.agents\u002Fproject.json.alignment.bip_platforms` only as optional priority\u002Franking metadata. Do not ask a project-platform setup question and do not use saved platforms as a filter. Load the shared social routers and every bundled text\u002Fcommunity and video channel convention.\n   - Infer `bip_phase` as exactly one of `research`, `prototyping`, or `implementation` from the shipped boundary. Following `docs\u002Fsocial-ledger-convention.md` plus every bundled channel convention, draft an exhaustive phase-aware batch of source-safe Build-In-Public post candidates for every bundled channel, or state that there is no safe public angle for this wrap-up. Mark top-ranked options clearly and keep rejected\u002Fnot-now options visible when useful for dedupe or future context. For each candidate, include target channel, optional priority rank from saved `alignment.bip_platforms`, `bip_phase`, angle, source basis, loaded convention path, risk level, claim-safety notes, publish precheck, and draft post text or a concise video\u002Fcommunity-post outline.\n   - **Write the batch to the single HTML BIP page, not inline.** Treat the successful ship as the equivalent of alignment-page confirmation and write the exhaustive per-channel batch to `alignment\u002Fbip-ship-end.html`, following the shared post-confirmation BIP page shape: set `data-alignment-page-kind=\"bip\"`, `data-bip-generation=\"post-confirmation\"`, `data-bip-source-skill=\"ship-end\"`, and `data-alignment-status=\"confirmed\"` on `\u003Chtml>`; cover every bundled text\u002Fcommunity and video channel; include the recommendation-notes, source-basis, claim-safety-notes, risk-level, publish-precheck, and loaded-convention-path fields with the recommended\u002Fnot-now\u002Frejected statuses; add the responsive viewport meta and the Brief Me TTS include before `\u003C\u002Fbody>`; and use no embeds or active approval gates. If `alignment\u002Fbip-ship-end.html` already exists, archive it first to `docs\u002Fhistory\u002Farchive\u002FYYYY-MM-DD\u002FHHMMSS\u002Falignment\u002Fbip-ship-end.html`. Include the page in `alignment\u002Findex.html` (with today's date), run the TTS inject step, and attempt to open it after wrap-up. Print a one-line terminal pointer to the file instead of dumping candidates inline. Do not publish externally or write social-ledger records without later explicit approval.\n\n## Output\n\n```\n## Session Summary\n- **Accomplished**: [what was done]\n- **Deploy**: [status]\n- **Tests**: [pass\u002Ffail — expected or unexpected]\n- **Manual tasks**: [X\u002FY complete, or \"none\"]\n- **Advisory tasks**: [record\u002Frecurring counts, or \"none\"]\n- **Outstanding**: [remaining work]\n- **Branch**: [branch name]\n- **Commits**: [list]\n- **Working tree**: clean\n- **Next work:** [specific task, blocker, verification gap, or \"none\"]\n- **Recommended next command:** [one command or route]\n```\n\n## Next-Step Routing\n\nBefore closing out the session, identify the next concrete work item from project state, then recommend the executor and invocation.\n\nOutput exactly two lines beyond the normal session summary:\n\n- **Next work:** \u003Cspecific task name, manual blocker, verification gap, or \"none\">\n- **Recommended next command:** \u003Cone command or route>\n\nRules:\n\n- Make the next work item primary. Derive it from `tasks\u002Ftodo.md`, `tasks\u002Fmanual-todo.md`, deploy status, validation gaps, smoke-test gaps, outstanding session work, or the absence of any remaining work. Do not use agent mode itself as the next work item.\n- Treat `tasks\u002Ftodo.md` as the only executable current-task surface. Historical roadmap entries and unchecked advisory\u002Fmanual\u002Frecord\u002Frecurring items are reconciliation candidates, not next executable work, unless the current active todo section explicitly promotes them.\n- Use `.\u002Fscripts\u002Fagent-mode.sh` only to choose command text. If it is missing, unset, or non-zero, infer routing from the current invocation and task type instead of asking the user to select a mode by default.\n- Prefer an owning workflow\u002Fdomain route over execution-loop defaults. If the next work item names a research, alignment, design, UI, UX, prototype-test, or copy-audit artifact or review page, recommend the specific owning skill, required user review, or compiled-YAML step directly. Use `\u002Fexec` only when no narrower installed skill, artifact contract, or review route owns the next action.\n- Inference defaults:\n  - Hybrid execution handoff → check `.agents\u002Fproject.json.enabled_packs` for `agent-bridge` — if `agent-bridge` is not enabled, recommend `npx skillpacks install agent-bridge` from the project shell first; if `agent-bridge` is enabled, recommend `\u002Fdelegate $exec`.\n  - Claude-only or orchestration-heavy work → after applying owning-route precedence above, recommend `\u002Fexec`.\n  - Codex-only execution → after applying owning-route precedence above, recommend `$exec`.\n  - External human-only manual work (browser\u002Fauth\u002FDNS\u002Fservice dashboard work with no reliable authenticated CLI\u002FAPI path, paid account setup, real-device checks, or production smoke-test work needing human sign-off) → check `.agents\u002Fproject.json.enabled_packs` for `guided-walkthrough` — if `guided-walkthrough` is not enabled, recommend `npx skillpacks install guided-walkthrough` from the project shell first; if `guided-walkthrough` is enabled, recommend `\u002Fguide` — or a Claude-guided manual step rather than `\u002Fexec`.\n  - Agent-executable work misfiled in `tasks\u002Fmanual-todo.md`, task-doc bookkeeping, stale `tasks\u002Fmanual-todo.md` cleanup, or reconciliation against repo\u002Fhistory reality → check `.agents\u002Fproject.json.enabled_packs` for `docs-health` — if `docs-health` is not enabled, recommend `npx skillpacks install docs-health` from the project shell first; if `docs-health` is enabled, recommend `\u002Freconcile-dev-docs fix tasks` — promotion to `tasks\u002Ftodo.md`, or a direct dev-doc audit, not `\u002Fguide`.\n- Only present multiple commands when the ambiguity materially changes execution safety or there are equally valid next work items. Otherwise choose the best route and mention degraded mode lookup inline.\n\n## Constraints\n\n- When recommending a skill from another pack, verify the pack is installed via `.agents\u002Fproject.json` `enabled_packs`. If not installed, include `npx skillpacks install \u003Cpack-name>` from the project shell as the prerequisite.\n- **Fix unrelated issues:** If any step surfaces errors, warnings, or lint issues — even ones unrelated to the current work — investigate and fix them before continuing. Commit these fixes separately with a descriptive message.\n- Do NOT modify CLAUDE.md. CLAUDE.md is for project conventions and config only — not progress tracking.\n- Progress and active work go in `tasks\u002Ftodo.md`. Completed work history goes in `tasks\u002Fhistory.md`.\n- Do not execute or block wrap-up on `tasks\u002Frecord-todo.md` or `tasks\u002Frecurring-todo.md` items unless they were explicitly promoted into `tasks\u002Ftodo.md`.\n- When task docs changed, do not finish with a next-work recommendation until `node scripts\u002Faudit-task-docs.mjs` passes, if that script exists.\n- Do not switch branches or create new branches unless the current state requires it.\n- Do not amend or rewrite history.\n- Do not commit secrets.\n- Do not push session-wrap-up commits to an existing feature branch. Use `\u002Fcommit-and-push-by-feature` to move the work onto `main` or `master` and push it there, or stop and report a blocker if that cannot be done safely.\n- If pre-commit hooks fail, fix and retry.\n- Never use GitHub Actions for deployment. Only use manual deploy scripts, Makefiles, or CLI commands.\n- Never deploy to production without explicit user confirmation.\n\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n",{"name":5,"type":33,"version":42,"description":7,"argument-hint":43,"required_conventions":44},"v0.11","[--no-deploy] [--save-conversation] [--save-all-conversations]",[45],"social-ledger","master","96e2912af886dd1606b1b97df707715aef062b02","packs\u002Fexec-loop\u002Fclaude\u002Fship-end\u002Farchive\u002Fv0.11",0,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills","https:\u002F\u002Fagentic-skills-blush.vercel.app","https:\u002F\u002Fgithub.com\u002FGeorgeQLe","georgeqle.com","George Le is a futurist and serial tech entrepreneur who wants to work toward a world where humanity is free from robotic tasks.","2026-11-10 04:07:24",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add GeorgeQLe\u002Fagentic-skills --skill ship-end",{"tool":62,"command":63},"bunx","bunx skills add GeorgeQLe\u002Fagentic-skills --skill ship-end",{"tool":65,"command":66},"pnpm","pnpm dlx skills add GeorgeQLe\u002Fagentic-skills --skill ship-end","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fexec-loop\u002Fclaude\u002Fship-end\u002Farchive\u002Fv0.11\u002FSKILL.md",true,[],[71,83,93,105,120,131],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":37},"01M6G0NJES15RJKZE6YZ0TSYGF","source-checkout-allowed","Valid source-checkout-only fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fsource-checkout-allowed\u002FSKILL.md",[],[78,79,80,81,22,82],"source checkout allowed","checkout","fixture","only","valid",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":37},"01M6G0NFZ3R1MNB1E3DVTM0WB7","deck-install-valid","Valid deck install fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fdeck-install\u002FSKILL.md",[],[90,91,92,82,80,22],"deck install valid","deck","install",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":37},"01M6G0ND3QZQC4MDZ9NVB97PT2","codex-pack-guard-valid","Valid Codex Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-pack-guard\u002FSKILL.md",[],[100,101,102,82,103,104,80,22],"codex pack guard valid","pack","guard","codex","availability",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":116,"publishedAt":37},"01M6G0NA9YB3NKGZKD3S96JMNB","codex-missing-skill-valid","Valid Codex missing skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-missing-skill-fallback\u002FSKILL.md",[111],{"categoryNo":112,"categoryName":113,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[117,118,82,103,22,119,80],"codex missing skill valid","missing","fallback",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":127,"publishedAt":37},"01M6G0N7PC0EKFD40ZWQAXSAQ9","codex-base-skill-fallback-valid","Valid Codex base skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-base-skill-fallback\u002FSKILL.md",[126],{"categoryNo":112,"categoryName":113,"taxonomyType":114,"taxonomyTypeDesc":115},[82,103,119,128,129,130,22,80],"base skill","codex base skill fallback valid","base",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":37},"01M6G0N4VRR2YKZQ6N3Y6S2BQA","claude-pack-guard-valid","Valid Claude Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fclaude-pack-guard\u002FSKILL.md",[],[82,102,101,138,104,22,80],"claude pack guard valid"]