[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75H0M0VRCS7G3RFHT8JVGSF":3,"skill-same:01M75H0M0VRCS7G3RFHT8JVGSF":54},{"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":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M75H0M0VRCS7G3RFHT8JVGSF","forge-init",null,"Initialize feature-forge configuration in the current project. Use when user runs forge-init or asks to set up forge for the first time. Creates forge.config.json with defaults. Do NOT trigger for general project initialization or setup tasks outside the forge pipeline.","garygentry\u002Ffeature-forge","garygentry","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12444042?v=4","01M75GWTRXHQMKFWDVG9N8ENNS","01M75GWTSZ5NV3MYKFWVCZJKW4",0,"MIT","https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Fadapters\u002Fcodex\u002Fskills\u002Fforge-init\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\n# GENERATED — DO NOT EDIT. Source: skills\u002Fforge-init\u002FSKILL.md. Regenerate: python3 scripts\u002Fbuild-adapters.py\nname: forge-init\ndescription: Initialize feature-forge configuration in the current project. Use when user runs forge-init or asks to set up forge for the first time. Creates forge.config.json with defaults. Do NOT trigger for general project initialization or setup tasks outside the forge pipeline.\n---\n\n# Initialize Feature Forge\n\nRun the initialization script to create `forge.config.json` with default settings:\n\n```bash\nR=\"$(bash -c '[ -z \"${FEATURE_FORGE_ROOT:-}\" ] || [ -x \"$FEATURE_FORGE_ROOT\u002Fscripts\u002Fforge-root.sh\" ] || { echo \"feature-forge: FEATURE_FORGE_ROOT=$FEATURE_FORGE_ROOT has no scripts\u002Fforge-root.sh\" >&2; exit 2; }; for d in \"${FEATURE_FORGE_ROOT:-}\" \"${CLAUDE_PLUGIN_ROOT:-}\" \"$HOME\"\u002F.claude\u002Fskills\u002Ffeature-forge \"$HOME\"\u002F.claude\u002Fplugins\u002Fcache\u002F*\u002Ffeature-forge\u002F* \"$HOME\"\u002F.claude\u002Fplugins\u002F*\u002Ffeature-forge \"$HOME\"\u002F.agents\u002Fskills\u002Ffeature-forge .\u002F.agents\u002Fskills\u002Ffeature-forge; do [ -x \"$d\u002Fscripts\u002Fforge-root.sh\" ] && exec \"$d\u002Fscripts\u002Fforge-root.sh\"; done')\"\n[ -n \"$R\" ] || { echo \"feature-forge: cannot locate plugin root\" >&2; exit 1; }\nbash \"$R\u002Fscripts\u002Fforge-init.sh\"\n```\n\nAfter initialization, the config file will contain defaults for:\n- `specsDir`: `.\u002Fspecs`\n- `docsDir`: `.\u002Fdocs\u002Farchitecture`\n- `backlogDir`: `null` (backlog lives alongside specs)\n- `gitCommitAfterStage`: `true`\n- `commitPrefix`: `forge`\n- `stack`: `null` (detected during `forge-2-tech`)\n- `typeCheckCommand`: `null` (set during `forge-2-tech`)\n- `testCommand`: `null` (set during `forge-2-tech`)\n- `smokeCommand`: `null` (optional end-to-end smoke that boots the wired app and drives one request; set it to enable impl-verify's runnability check `CHECK-I21` — distinct from `testCommand`)\n- `autoInvokeNextStage`: `true` (the navigator auto-starts the next stage after you confirm; set `false` to only print the command)\n- `contextWindowTokens`: `null` (the navigator infers the context window; set to your model's window, e.g. `1000000` for a 1M-context model, for accurate context-usage advice)\n- `contextWarnThreshold`: `0.7` (fraction of the window past which the navigator suggests a clean session)\n- `autoVerify`: `false` (set `true` to run `forge-verify` automatically after each authoring stage completes — in-stage, in the same session, before the exit block; it costs an extra clean-room verify per stage, so it trades a little time\u002Ftokens for catching errors early)\n- `autoVerifyStages`: `{}` (per-stage overrides for `autoVerify`)\n- `autoFix`: `false` (set `true` to chain `forge-fix` after an auto-verify finds issues)\n\nIf `forge.config.json` already exists, the script will not overwrite it.\n\n## Offer auto-verify\n\nThe template writes `autoVerify: false`. After the config is created (and only when the script\nactually created it — skip this if it reported the file already exists), offer to turn\nauto-verify on, then write the choice back into `forge.config.json`.\n\nIf the host's question mechanism is available, ask exactly one question:\n\n> **Enable auto-verify?** Verification runs in a clean-room subagent in-stage after each\n> authoring stage completes — in the same session, before the exit block, so any fix\n> decision keeps its context. It never needs a session clear and only returns a compact digest.\n> **Recommended: on.** (Change later by editing `autoVerify` in `forge.config.json`.)\n\nOptions: **Enable (recommended)** \u002F **Leave off**.\n\n- On **Enable**: patch `\"autoVerify\": false` → `\"autoVerify\": true` in the generated\n  `forge.config.json` in place, preserving formatting and every other key.\n- On **Leave off**: leave the config as written (`autoVerify: false`).\n\nThis is the run's **first question**, so determine your rung before asking it, per the\nInteraction Capability Ladder (`references\u002Fshared-conventions.md`) — **read** the rung from\n`doctor`'s `interaction-mode` record as that section directs; never judge it from your own tool\nsurface, which cannot see whether anyone is there to answer:\n\n```bash\nR=\"$(bash -c '[ -z \"${FEATURE_FORGE_ROOT:-}\" ] || [ -x \"$FEATURE_FORGE_ROOT\u002Fscripts\u002Fforge-root.sh\" ] || { echo \"feature-forge: FEATURE_FORGE_ROOT=$FEATURE_FORGE_ROOT has no scripts\u002Fforge-root.sh\" >&2; exit 2; }; for d in \"${FEATURE_FORGE_ROOT:-}\" \"${CLAUDE_PLUGIN_ROOT:-}\" \"$HOME\"\u002F.claude\u002Fskills\u002Ffeature-forge \"$HOME\"\u002F.claude\u002Fplugins\u002Fcache\u002F*\u002Ffeature-forge\u002F* \"$HOME\"\u002F.claude\u002Fplugins\u002F*\u002Ffeature-forge \"$HOME\"\u002F.agents\u002Fskills\u002Ffeature-forge .\u002F.agents\u002Fskills\u002Ffeature-forge; do [ -x \"$d\u002Fscripts\u002Fforge-root.sh\" ] && exec \"$d\u002Fscripts\u002Fforge-root.sh\"; done')\"\n[ -n \"$R\" ] || { echo \"feature-forge: cannot locate plugin root\" >&2; exit 1; }\npython3 \"$R\u002Fscripts\u002Fforge-session.py\" doctor --json --check interaction-mode\n```\n\nAt rung 1 or 2, ask (structured tool, or the same choice in plain prose — then wait for the\nreply). At rung 3 this question's declared default is the no-write \u002F no-proceed option — skip the\nprompt, leave `autoVerify: false`, state the rung-3 default taken, and print the one-line note\n`Set \"autoVerify\": true in forge.config.json to verify automatically after each stage.` — then\n**continue with the steps below**; declining this edit never ends the skill. The same rung governs\nevery remaining step: never emit a question a rung-3 run cannot answer.\n\n## Preflight the install\n\nOnce the config exists, check the tooling this project's pipeline will lean on:\n\n```bash\nR=\"$(bash -c '[ -z \"${FEATURE_FORGE_ROOT:-}\" ] || [ -x \"$FEATURE_FORGE_ROOT\u002Fscripts\u002Fforge-root.sh\" ] || { echo \"feature-forge: FEATURE_FORGE_ROOT=$FEATURE_FORGE_ROOT has no scripts\u002Fforge-root.sh\" >&2; exit 2; }; for d in \"${FEATURE_FORGE_ROOT:-}\" \"${CLAUDE_PLUGIN_ROOT:-}\" \"$HOME\"\u002F.claude\u002Fskills\u002Ffeature-forge \"$HOME\"\u002F.claude\u002Fplugins\u002Fcache\u002F*\u002Ffeature-forge\u002F* \"$HOME\"\u002F.claude\u002Fplugins\u002F*\u002Ffeature-forge \"$HOME\"\u002F.agents\u002Fskills\u002Ffeature-forge .\u002F.agents\u002Fskills\u002Ffeature-forge; do [ -x \"$d\u002Fscripts\u002Fforge-root.sh\" ] && exec \"$d\u002Fscripts\u002Fforge-root.sh\"; done')\"\n[ -n \"$R\" ] || { echo \"feature-forge: cannot locate plugin root\" >&2; exit 1; }\npython3 \"$R\u002Fscripts\u002Fforge-session.py\" doctor --json \\\n  --check plugin-root --check root-version-skew --check gh-available\n```\n\nFollow `references\u002Fpreflight-and-self-heal.md` with that result: all `ok`\u002F`na` → say nothing and\nmove on. Otherwise cluster and report. **No check here is a stop for `forge-init`** — report and\ncontinue; a `warn` here never aborts initialization (the procedure returns statuses; the caller\nowns its own gate). `gh-available` matters because the tooling-feedback step below tells agents\nto file issues with `gh issue create`; when `gh` is missing or unauthenticated, say so once — its\nremedies are `global-install`\u002F`network`, so they are **advise-only** and nothing is executed. It\nis **one informational line, never a prompt**: `gh` is optional (every stage degrades to manual\nsteps without it), and this check cannot return `na`, so a machine without `gh` must not be\ninterrogated about it on every init.\n`root-version-skew` is reported the same way: a second install shadowing this one is worth\nknowing about before the first stage runs.\n\n`plugin-root` is reported the same way, **advisory here despite its `blocking` severity**. The\nprelude above already exits 1 when the resolver fails, so below it the check warns only when the\nresolved root is un-built canon (no `.feature-forge-bundle.json` — a repo checkout loaded\ndirectly): its skills cannot read their shared references and will break mid-stage. Say so once\nwith the check's `remedy.description` (advise-only, `network`) and continue.\n\n## Root hygiene — tooling feedback\n\nOffer the project-root **Tooling feedback** section, per `references\u002Fshared-conventions.md`\n§ Root Hygiene (Tooling Feedback) — that block owns the protocol text, the copy commands, the\nthree-case analysis, and the never-overwrite rule; do not restate them here. In short: decide\nwhich variants are **missing** first, ask once as a `local-write` only for those, and stay silent\nabout a file that already carries the section. `AGENTS.md` always; `CLAUDE.md` only on Claude,\nread from the bundle's own `agent` field — never from tool availability. **At rung 3 this step\nwrites nothing and says so** (that block's declared default). This is what makes the `specs\u002F`\nhygiene files' \"see the project-root `AGENTS.md`\" pointer resolve.\n\nAfter initialization, start the pipeline with `forge-1-prd \u003Cfeature-name>`.\n\n---\n\n## Host execution notes (Codex)\n\nThis skill was authored Claude-first; the body above refers to \"the host's question mechanism\", \"the host's subagent mechanism\", and \"the host's background-execution mechanism\". On Codex:\n\n- **User input:** Codex has no structured question tool. Which rung you are on is **not** observable from inside the session — a `codex exec` run looks exactly like an interactive one — so read it from the Interaction Capability Ladder's `interaction-mode` record instead of judging it. Interactive session — ask the question directly and wait for the reply; never assume an answer. Non-interactive — don't wait: take the Interaction Capability Ladder's declared conservative default, state it in your output, and use `no-default: abort — \u003Cquestion> requires a human answer` for an interview question with no sane default (`references\u002Fshared-conventions.md`).\n- **Subagents:** spawn a Codex subagent using the named custom agent under `.codex\u002Fagents\u002F\u003Cname>.toml`. Codex spawns a subagent only when explicitly asked; if the custom agent is unavailable, run that step inline yourself.\n- **Background \u002F monitoring (forge-5-loop):** Codex cannot wake you when a background process prints or exits, so **never end your turn while the loop runs**. Launch it detached and supervise it from inside the turn with the `rauf loop wait` loop — one bounded wait per shell call, print each card, decide from the status JSON — exactly as `references\u002Frunner-contract.md` (Steps 3b\u002F3d) says for this host. The optional rauf Stop hook (`rauf hook codex-stop`; wire it with `npx @garygentry\u002Ffeature-forge install -a codex --codex-stop-hook`) holds the session open if it tries to end its turn while the loop still runs. Other long-lived commands: run them in your shell session and report progress as it arrives.\n","# Initialize Feature Forge\n\nRun the initialization script to create `forge.config.json` with default settings:\n\n```bash\nR=\"$(bash -c '[ -z \"${FEATURE_FORGE_ROOT:-}\" ] || [ -x \"$FEATURE_FORGE_ROOT\u002Fscripts\u002Fforge-root.sh\" ] || { echo \"feature-forge: FEATURE_FORGE_ROOT=$FEATURE_FORGE_ROOT has no scripts\u002Fforge-root.sh\" >&2; exit 2; }; for d in \"${FEATURE_FORGE_ROOT:-}\" \"${CLAUDE_PLUGIN_ROOT:-}\" \"$HOME\"\u002F.claude\u002Fskills\u002Ffeature-forge \"$HOME\"\u002F.claude\u002Fplugins\u002Fcache\u002F*\u002Ffeature-forge\u002F* \"$HOME\"\u002F.claude\u002Fplugins\u002F*\u002Ffeature-forge \"$HOME\"\u002F.agents\u002Fskills\u002Ffeature-forge .\u002F.agents\u002Fskills\u002Ffeature-forge; do [ -x \"$d\u002Fscripts\u002Fforge-root.sh\" ] && exec \"$d\u002Fscripts\u002Fforge-root.sh\"; done')\"\n[ -n \"$R\" ] || { echo \"feature-forge: cannot locate plugin root\" >&2; exit 1; }\nbash \"$R\u002Fscripts\u002Fforge-init.sh\"\n```\n\nAfter initialization, the config file will contain defaults for:\n- `specsDir`: `.\u002Fspecs`\n- `docsDir`: `.\u002Fdocs\u002Farchitecture`\n- `backlogDir`: `null` (backlog lives alongside specs)\n- `gitCommitAfterStage`: `true`\n- `commitPrefix`: `forge`\n- `stack`: `null` (detected during `forge-2-tech`)\n- `typeCheckCommand`: `null` (set during `forge-2-tech`)\n- `testCommand`: `null` (set during `forge-2-tech`)\n- `smokeCommand`: `null` (optional end-to-end smoke that boots the wired app and drives one request; set it to enable impl-verify's runnability check `CHECK-I21` — distinct from `testCommand`)\n- `autoInvokeNextStage`: `true` (the navigator auto-starts the next stage after you confirm; set `false` to only print the command)\n- `contextWindowTokens`: `null` (the navigator infers the context window; set to your model's window, e.g. `1000000` for a 1M-context model, for accurate context-usage advice)\n- `contextWarnThreshold`: `0.7` (fraction of the window past which the navigator suggests a clean session)\n- `autoVerify`: `false` (set `true` to run `forge-verify` automatically after each authoring stage completes — in-stage, in the same session, before the exit block; it costs an extra clean-room verify per stage, so it trades a little time\u002Ftokens for catching errors early)\n- `autoVerifyStages`: `{}` (per-stage overrides for `autoVerify`)\n- `autoFix`: `false` (set `true` to chain `forge-fix` after an auto-verify finds issues)\n\nIf `forge.config.json` already exists, the script will not overwrite it.\n\n## Offer auto-verify\n\nThe template writes `autoVerify: false`. After the config is created (and only when the script\nactually created it — skip this if it reported the file already exists), offer to turn\nauto-verify on, then write the choice back into `forge.config.json`.\n\nIf the host's question mechanism is available, ask exactly one question:\n\n> **Enable auto-verify?** Verification runs in a clean-room subagent in-stage after each\n> authoring stage completes — in the same session, before the exit block, so any fix\n> decision keeps its context. It never needs a session clear and only returns a compact digest.\n> **Recommended: on.** (Change later by editing `autoVerify` in `forge.config.json`.)\n\nOptions: **Enable (recommended)** \u002F **Leave off**.\n\n- On **Enable**: patch `\"autoVerify\": false` → `\"autoVerify\": true` in the generated\n  `forge.config.json` in place, preserving formatting and every other key.\n- On **Leave off**: leave the config as written (`autoVerify: false`).\n\nThis is the run's **first question**, so determine your rung before asking it, per the\nInteraction Capability Ladder (`references\u002Fshared-conventions.md`) — **read** the rung from\n`doctor`'s `interaction-mode` record as that section directs; never judge it from your own tool\nsurface, which cannot see whether anyone is there to answer:\n\n```bash\nR=\"$(bash -c '[ -z \"${FEATURE_FORGE_ROOT:-}\" ] || [ -x \"$FEATURE_FORGE_ROOT\u002Fscripts\u002Fforge-root.sh\" ] || { echo \"feature-forge: FEATURE_FORGE_ROOT=$FEATURE_FORGE_ROOT has no scripts\u002Fforge-root.sh\" >&2; exit 2; }; for d in \"${FEATURE_FORGE_ROOT:-}\" \"${CLAUDE_PLUGIN_ROOT:-}\" \"$HOME\"\u002F.claude\u002Fskills\u002Ffeature-forge \"$HOME\"\u002F.claude\u002Fplugins\u002Fcache\u002F*\u002Ffeature-forge\u002F* \"$HOME\"\u002F.claude\u002Fplugins\u002F*\u002Ffeature-forge \"$HOME\"\u002F.agents\u002Fskills\u002Ffeature-forge .\u002F.agents\u002Fskills\u002Ffeature-forge; do [ -x \"$d\u002Fscripts\u002Fforge-root.sh\" ] && exec \"$d\u002Fscripts\u002Fforge-root.sh\"; done')\"\n[ -n \"$R\" ] || { echo \"feature-forge: cannot locate plugin root\" >&2; exit 1; }\npython3 \"$R\u002Fscripts\u002Fforge-session.py\" doctor --json --check interaction-mode\n```\n\nAt rung 1 or 2, ask (structured tool, or the same choice in plain prose — then wait for the\nreply). At rung 3 this question's declared default is the no-write \u002F no-proceed option — skip the\nprompt, leave `autoVerify: false`, state the rung-3 default taken, and print the one-line note\n`Set \"autoVerify\": true in forge.config.json to verify automatically after each stage.` — then\n**continue with the steps below**; declining this edit never ends the skill. The same rung governs\nevery remaining step: never emit a question a rung-3 run cannot answer.\n\n## Preflight the install\n\nOnce the config exists, check the tooling this project's pipeline will lean on:\n\n```bash\nR=\"$(bash -c '[ -z \"${FEATURE_FORGE_ROOT:-}\" ] || [ -x \"$FEATURE_FORGE_ROOT\u002Fscripts\u002Fforge-root.sh\" ] || { echo \"feature-forge: FEATURE_FORGE_ROOT=$FEATURE_FORGE_ROOT has no scripts\u002Fforge-root.sh\" >&2; exit 2; }; for d in \"${FEATURE_FORGE_ROOT:-}\" \"${CLAUDE_PLUGIN_ROOT:-}\" \"$HOME\"\u002F.claude\u002Fskills\u002Ffeature-forge \"$HOME\"\u002F.claude\u002Fplugins\u002Fcache\u002F*\u002Ffeature-forge\u002F* \"$HOME\"\u002F.claude\u002Fplugins\u002F*\u002Ffeature-forge \"$HOME\"\u002F.agents\u002Fskills\u002Ffeature-forge .\u002F.agents\u002Fskills\u002Ffeature-forge; do [ -x \"$d\u002Fscripts\u002Fforge-root.sh\" ] && exec \"$d\u002Fscripts\u002Fforge-root.sh\"; done')\"\n[ -n \"$R\" ] || { echo \"feature-forge: cannot locate plugin root\" >&2; exit 1; }\npython3 \"$R\u002Fscripts\u002Fforge-session.py\" doctor --json \\\n  --check plugin-root --check root-version-skew --check gh-available\n```\n\nFollow `references\u002Fpreflight-and-self-heal.md` with that result: all `ok`\u002F`na` → say nothing and\nmove on. Otherwise cluster and report. **No check here is a stop for `forge-init`** — report and\ncontinue; a `warn` here never aborts initialization (the procedure returns statuses; the caller\nowns its own gate). `gh-available` matters because the tooling-feedback step below tells agents\nto file issues with `gh issue create`; when `gh` is missing or unauthenticated, say so once — its\nremedies are `global-install`\u002F`network`, so they are **advise-only** and nothing is executed. It\nis **one informational line, never a prompt**: `gh` is optional (every stage degrades to manual\nsteps without it), and this check cannot return `na`, so a machine without `gh` must not be\ninterrogated about it on every init.\n`root-version-skew` is reported the same way: a second install shadowing this one is worth\nknowing about before the first stage runs.\n\n`plugin-root` is reported the same way, **advisory here despite its `blocking` severity**. The\nprelude above already exits 1 when the resolver fails, so below it the check warns only when the\nresolved root is un-built canon (no `.feature-forge-bundle.json` — a repo checkout loaded\ndirectly): its skills cannot read their shared references and will break mid-stage. Say so once\nwith the check's `remedy.description` (advise-only, `network`) and continue.\n\n## Root hygiene — tooling feedback\n\nOffer the project-root **Tooling feedback** section, per `references\u002Fshared-conventions.md`\n§ Root Hygiene (Tooling Feedback) — that block owns the protocol text, the copy commands, the\nthree-case analysis, and the never-overwrite rule; do not restate them here. In short: decide\nwhich variants are **missing** first, ask once as a `local-write` only for those, and stay silent\nabout a file that already carries the section. `AGENTS.md` always; `CLAUDE.md` only on Claude,\nread from the bundle's own `agent` field — never from tool availability. **At rung 3 this step\nwrites nothing and says so** (that block's declared default). This is what makes the `specs\u002F`\nhygiene files' \"see the project-root `AGENTS.md`\" pointer resolve.\n\nAfter initialization, start the pipeline with `forge-1-prd \u003Cfeature-name>`.\n\n---\n\n## Host execution notes (Codex)\n\nThis skill was authored Claude-first; the body above refers to \"the host's question mechanism\", \"the host's subagent mechanism\", and \"the host's background-execution mechanism\". On Codex:\n\n- **User input:** Codex has no structured question tool. Which rung you are on is **not** observable from inside the session — a `codex exec` run looks exactly like an interactive one — so read it from the Interaction Capability Ladder's `interaction-mode` record instead of judging it. Interactive session — ask the question directly and wait for the reply; never assume an answer. Non-interactive — don't wait: take the Interaction Capability Ladder's declared conservative default, state it in your output, and use `no-default: abort — \u003Cquestion> requires a human answer` for an interview question with no sane default (`references\u002Fshared-conventions.md`).\n- **Subagents:** spawn a Codex subagent using the named custom agent under `.codex\u002Fagents\u002F\u003Cname>.toml`. Codex spawns a subagent only when explicitly asked; if the custom agent is unavailable, run that step inline yourself.\n- **Background \u002F monitoring (forge-5-loop):** Codex cannot wake you when a background process prints or exits, so **never end your turn while the loop runs**. Launch it detached and supervise it from inside the turn with the `rauf loop wait` loop — one bounded wait per shell call, print each card, decide from the status JSON — exactly as `references\u002Frunner-contract.md` (Steps 3b\u002F3d) says for this host. The optional rauf Stop hook (`rauf hook codex-stop`; wire it with `npx @garygentry\u002Ffeature-forge install -a codex --codex-stop-hook`) holds the session open if it tries to end its turn while the loop still runs. Other long-lived commands: run them in your shell session and report progress as it arrives.\n",{"name":5,"description":7},"main","ce0d6d40bba1d87039b0397041d15cb56c934037","adapters\u002Fcodex\u002Fskills\u002Fforge-init","https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge","https:\u002F\u002Fgarygentry.github.io\u002Ffeature-forge\u002F","https:\u002F\u002Fgithub.com\u002Fgarygentry","2026-10-15 10:14:13",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add garygentry\u002Ffeature-forge --skill forge-init",{"tool":36,"command":37},"bunx","bunx skills add garygentry\u002Ffeature-forge --skill forge-init",{"tool":39,"command":40},"pnpm","pnpm dlx skills add garygentry\u002Ffeature-forge --skill forge-init","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Fadapters\u002Fcodex\u002Fskills\u002Fforge-init\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"references\u002Fpreflight-and-self-heal.md","REFERENCE","参考文档",12075,"https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Fadapters\u002Fcodex\u002Fskills\u002Fforge-init\u002Freferences\u002Fpreflight-and-self-heal.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fshared-conventions.md",74084,"https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Fadapters\u002Fcodex\u002Fskills\u002Fforge-init\u002Freferences\u002Fshared-conventions.md",[55,62,67,73,78,84],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M75H8RTWSJ2HYCPPKA3FRG42","alpha","A valid skill description.","https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Freader-nested-metadata\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":63,"name":57,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M75H8QXKFS116EF1009KB3CY","https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Freader-malformed\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":68,"name":57,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M75H8PKNSV4WEREK6D91G9T4","This is a folded scalar description.","https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Freader-folded-scalar\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":74,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M75H8MAV261C8QJ4S8CGRHV5","https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Freader-crlf\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":79,"name":57,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M75H8KDW98YF0PBHPD5V1GKR","foo: bar","https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Freader-colon-value\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":85,"name":57,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M75H8JFYFCGYNRCRTS4PMKKX","A valid description.","https:\u002F\u002Fgithub.com\u002Fgarygentry\u002Ffeature-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Freader-blank-lines\u002Fskills\u002Falpha\u002FSKILL.md",[],[]]