[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD06QJRPP0S1PJBZ1AZ2CE":3,"skill-same:01M7FD06QJRPP0S1PJBZ1AZ2CE":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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7FD06QJRPP0S1PJBZ1AZ2CE","setup-batcave",null,"Configure which models batcave uses per role. Detects available models and writes the current runtime's override sheet. Use for \u002Fsetup-batcave, \"configure batcave models\", changing batcave's model choices, or turning the SessionStart hook on or off.","Abhiman67\u002Fbatcave","Abhiman67","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F137296581?v=4","01M7FCTFR2F0WBMG11VKWGN0KB","ABHISHEK CHHANDAK","01M7FCTFRWXRGV9ZY0060XPK62",0,"MIT","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fsetup-batcave\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: setup-batcave\ndescription: Configure which models batcave uses per role. Detects available models and writes the current runtime's override sheet. Use for \u002Fsetup-batcave, \"configure batcave models\", changing batcave's model choices, or turning the SessionStart hook on or off.\n---\n\n# Setup batcave\n\nOn Codex, read the [platform mapping](..\u002Fbatcave-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fbatcave-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, follow [the Copilot setup](copilot.md) in place of steps 1, 3, 4, and 7 and step 6's header.\n\nOn another runtime, read [Other runtimes](#other-runtimes) below for where the sheet lives and how it loads; the steps are the same.\n\nWrite the current runtime's per-role model override sheet, using the path in [Other runtimes](#other-runtimes). Each batcave skill names a default model inline; the override sheet adapts those defaults to the models you actually have access to.\n\nClaude Code has no auto-applied \"rules\" mechanism like Cursor's `.mdc`. The Claude Code config directory is `$CLAUDE_CONFIG_DIR` when that variable is set and `~\u002F.claude` otherwise. This skill calls it `\u003Cconfig>`. Inclusion is explicit: the user adds a line to `\u003Cconfig>\u002FCLAUDE.md` (or their project `CLAUDE.md`) such as:\n\n```text\n@\u003Cconfig>\u002Fbatcave-models.md\n```\n\nwith `\u003Cconfig>` written as the resolved path, so the file is loaded as context for every session.\n\nThe Codex home directory is `$CODEX_HOME` when that variable is set and `~\u002F.codex` otherwise. This skill calls it `\u003Ccodex-home>`.\n\n## Steps\n\n### 1. Detect available models\n\nEnumerate the model names the `Agent` tool's `model` parameter accepts in this session. That is the dependable source. On Claude Code they are the family names listed in [Models](#models) below, each running that family's current model, and a full model ID is rejected. The default panel is listed there too. The panel is chosen for cross-family diversity. Ask the user to confirm or paste any additional slugs they want available. Never write a real slug you have not confirmed is available. The aliases `inherit-parent` and `auto` are always valid even though they are not detected slugs. Both mean the role runs on the parent session's model, which the `Agent` call expresses by omitting `model`.\n\n### 2. Load current state\n\nThe default role-to-model mapping is the rule shape shown in the Write the override sheet step below. If the current runtime's sheet already exists, read it and treat its values as the current choices. Otherwise start from those defaults. A line whose role is not in that shape, such as `how critics`, is from a retired role. Drop it. An older sheet may name full model IDs that start with `claude-`, which the `Agent` tool rejects. Replace each with its family name, the word after `claude-`.\n\n### 3. Map and confirm\n\nShow every role with its current model, marking any real slug not in the detected set as needing a choice. Also list each line step 2 dropped or rewrote. Ask whether to accept as-is or change specific roles, offering the detected models plus `inherit-parent` and `auto` as the options. Prefer `AskUserQuestion` over free text. For panel roles (arena runners, architect runners, interrogate reviewers) the value is a list, and one subagent runs per entry, alias entries included, so the list length sets the count. `arena cross-judge pool` is also a list, but Arena selects one value from it whose model family differs from the parent's when possible. `swarm workers` is the default model for every worker unless a race or comparison assigns another model per arm.\n\nThen ask for the default reasoning effort, the `default effort` line. It is `session`, which keeps the parent session's effort, or one of the levels in [Models](#models). Start from the default listed there. Every role value without a suffix runs at it. Then ask whether any role should run at another level. On Claude Code a role value may carry one after its slug, as in `\u003Cslug> @xhigh`; panel entries take their own, as in `\u003Cslug> @xhigh, \u003Cslug> @max`. Each level dispatches through the plugin's effort agent of that level, so the choice holds without changing the session. Leave the suffix off for the default effort.\n\n### 4. Choose whether the session hook routes tasks\n\nOn Claude Code and Codex, the plugin's `SessionStart` hook injects the batcave-mode mandate on startup, resume, clear, and compact. Codex asks the user to trust plugin hooks through `\u002Fhooks` before running them. On Pi, the batcave extension adds the same mandate to the system prompt at every agent start. Ask whether to keep the hook. The default is on. The answer is the `session hook` line in the current runtime's sheet: `on` or `off`. With no sheet or no line, the hook injects. The line is inert on other runtimes.\n\n### 5. Validate\n\nEvery real slug written must be in the detected set. `inherit-parent` and `auto` always pass. Validate the slug without any `@\u003Clevel>` suffix, and the level against the effort levels in [Models](#models). The `default effort` value is one of those levels or `session`. On Codex, the levels are the `reasoning_effort` values your Codex models accept instead. If a chosen real slug or level is not available, stop and ask again.\n\n### 6. Write the override sheet\n\nWrite the current runtime's sheet with the shape below. Overwrite the whole file so re-runs stay idempotent.\n\n```markdown\n# batcave model configuration\n\nPer-role model overrides for batcave skills. Each batcave SKILL.md names its defaults in a Models section; the values here override those defaults. Delete a line to fall back to the skill default. A value of `inherit-parent` or `auto` runs that role on the parent session's model (the `Agent` call omits `model`); an alias entry in a panel list still counts toward that panel's fan-out. A model may carry a reasoning effort, as in `opus @xhigh` (levels: low, medium, high, xhigh, max); the role then runs through the batcave effort agent of that level, each entry of a panel list on its own. `default effort` sets the level for a value without one; `session` keeps the parent session's effort. `session hook: off` stops the Claude Code or Codex SessionStart hook, or the batcave Pi extension, from injecting the batcave-mode mandate; any other value, or no line, leaves it on.\n\nfeature, refactoring: sonnet\nbug-fix: opus\nperf-issue: opus\nhillclimb: opus\njudgment and prose: opus\nstrongest judgment: fable\nhow explorer: opus\nhow explainer: opus\nwhy investigators: opus\nwhy synthesizer: opus\nreflect tooling: opus\nreflect judgment, divergent, synthesizer: opus\narena runners: opus, fable, sonnet, haiku\narena cross-judge pool: opus, fable, sonnet, haiku\nswarm workers: opus\narchitect runners: opus, fable, sonnet, haiku\ninterrogate reviewers: opus, fable, sonnet, haiku\n\ndefault effort: session\nsession hook: on\n```\n\n### 7. Wire it in\n\nOn Claude Code, if `\u003Cconfig>\u002FCLAUDE.md` does not already include `\u003Cconfig>\u002Fbatcave-models.md`, append an `@` line naming the sheet's resolved path, such as `@~\u002F.claude\u002Fbatcave-models.md`, so the model rows load on every session. If the user prefers project scope, add the include to the project's `CLAUDE.md` instead.\n\nOn Codex, paste the model rows and the `default effort` line into `\u003Ccodex-home>\u002FAGENTS.md`; Codex has no `@` include. Do not paste the `session hook` line there: the plugin hook reads it directly from `\u003Ccodex-home>\u002Fbatcave-models.md`.\n\n### 8. Confirm\n\nTell the user where the override was written, how its model rows load, and whether the plugin hook is on. Re-running this skill updates the override sheet.\n\n### 9. Offer a verification skill (optional)\n\nCheck whether the project has a way to drive the real app for proof (a project `verify` or `verify-*` skill, or an existing harness). If not, offer once: \"want a project-local verification skill, so agents can drive the app the way a user does and prove changes work? I can generate one with \u002Fcreate-verification-skill.\" On yes, invoke [`\u002Fcreate-verification-skill`](..\u002Fcreate-verification-skill\u002FSKILL.md). On no, move on without pushing.\n\n### 10. Offer a formal verification skill (optional)\n\nCheck whether the project already has a formal verification skill (a project skill that runs a model checker, a proof, or another verifier against the code). If not, offer once: \"want a formal verification skill, so agents can prove a key property of your code holds in every case in scope, not only the cases tests reach? I can generate one with \u002Fcreate-formal-verification-skill.\" On yes, invoke [`\u002Fcreate-formal-verification-skill`](..\u002Fcreate-formal-verification-skill\u002FSKILL.md). On no, move on without pushing.\n\n## Other runtimes\n\nThe role lines are the same everywhere. What differs is the sheet path, how the runtime loads it, and how you list models. Detect models with the runtime's own tool and never write a slug you have not seen listed. A runtime whose subagent call has no model parameter still gets the sheet, as the record of the user's choice, and applies it where it can. The `session hook` line applies to the Claude Code, Codex, and GitHub Copilot plugins and to the batcave Pi extension.\n\n| Runtime | Sheet | Load | List models | Status |\n| --- | --- | --- | --- | --- |\n| Claude Code | `\u003Cconfig>\u002Fbatcave-models.md` | `@\u003Cconfig>\u002Fbatcave-models.md` in `\u003Cconfig>\u002FCLAUDE.md` | the `Agent` tool's model parameter | verified live |\n| Codex | `\u003Ccodex-home>\u002Fbatcave-models.md` | model rows: paste into `\u003Ccodex-home>\u002FAGENTS.md`; hook setting: read by the plugin | your configured Codex models, see [codex-tools.md](..\u002Fbatcave-mode\u002Freferences\u002Fcodex-tools.md#model-names) | hook contract tested; discovery verified |\n| Pi | `batcave-models.md` in the Pi agent directory, `$PI_CODING_AGENT_DIR` or `~\u002F.pi\u002Fagent` | read by the batcave Pi extension, model rows and hook setting both; no include line | `pi --list-models`, see [pi-tools.md](..\u002Fbatcave-mode\u002Freferences\u002Fpi-tools.md#model-names) and its `setup-batcave` note | extension contract tested offline; live results in the repository's `docs\u002Fpi-equivalence.md` |\n| GitHub Copilot (CLI and app) | `${COPILOT_HOME:-~\u002F.copilot}\u002Fbatcave-models.md` | the plugin hook checks it and injects its role lines at session start; skills-only installs read it with `view` | the `task` tool's `model` enum, see [copilot-tools.md](..\u002Fbatcave-mode\u002Freferences\u002Fcopilot-tools.md#model-names) | hook contract tested; CLI install smoke-tested |\n| opencode | `~\u002F.config\u002Fopencode\u002Fbatcave-models.md` | add the path to the `instructions` array in `opencode.json` | the `models` slash command in the session | from published docs, no live session |\n| Gemini CLI | `~\u002F.gemini\u002Fbatcave-models.md` | `@~\u002F.gemini\u002Fbatcave-models.md` in `~\u002F.gemini\u002FGEMINI.md` | the `model` slash command in the session | from published docs, no live session |\n| Prime Agent | no documented sheet path; Prime's configuration chooses models | | | no live session |\n\n## Models\n\nStamped from `plugins\u002Fbatcave\u002Fmodels.json` (edit there, rerun `tools\u002Fgenerate.mjs`).\n\n- Available Claude models: `opus`, `fable`, `sonnet`, `haiku`\n- Default panel: `opus`, `fable`, `sonnet`, `haiku`\n- Reasoning effort levels: `low`, `medium`, `high`, `xhigh`, `max`\n- Default reasoning effort: `session`\n- Single-role default: `opus`\n","# Setup batcave\n\nOn Codex, read the [platform mapping](..\u002Fbatcave-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fbatcave-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, follow [the Copilot setup](copilot.md) in place of steps 1, 3, 4, and 7 and step 6's header.\n\nOn another runtime, read [Other runtimes](#other-runtimes) below for where the sheet lives and how it loads; the steps are the same.\n\nWrite the current runtime's per-role model override sheet, using the path in [Other runtimes](#other-runtimes). Each batcave skill names a default model inline; the override sheet adapts those defaults to the models you actually have access to.\n\nClaude Code has no auto-applied \"rules\" mechanism like Cursor's `.mdc`. The Claude Code config directory is `$CLAUDE_CONFIG_DIR` when that variable is set and `~\u002F.claude` otherwise. This skill calls it `\u003Cconfig>`. Inclusion is explicit: the user adds a line to `\u003Cconfig>\u002FCLAUDE.md` (or their project `CLAUDE.md`) such as:\n\n```text\n@\u003Cconfig>\u002Fbatcave-models.md\n```\n\nwith `\u003Cconfig>` written as the resolved path, so the file is loaded as context for every session.\n\nThe Codex home directory is `$CODEX_HOME` when that variable is set and `~\u002F.codex` otherwise. This skill calls it `\u003Ccodex-home>`.\n\n## Steps\n\n### 1. Detect available models\n\nEnumerate the model names the `Agent` tool's `model` parameter accepts in this session. That is the dependable source. On Claude Code they are the family names listed in [Models](#models) below, each running that family's current model, and a full model ID is rejected. The default panel is listed there too. The panel is chosen for cross-family diversity. Ask the user to confirm or paste any additional slugs they want available. Never write a real slug you have not confirmed is available. The aliases `inherit-parent` and `auto` are always valid even though they are not detected slugs. Both mean the role runs on the parent session's model, which the `Agent` call expresses by omitting `model`.\n\n### 2. Load current state\n\nThe default role-to-model mapping is the rule shape shown in the Write the override sheet step below. If the current runtime's sheet already exists, read it and treat its values as the current choices. Otherwise start from those defaults. A line whose role is not in that shape, such as `how critics`, is from a retired role. Drop it. An older sheet may name full model IDs that start with `claude-`, which the `Agent` tool rejects. Replace each with its family name, the word after `claude-`.\n\n### 3. Map and confirm\n\nShow every role with its current model, marking any real slug not in the detected set as needing a choice. Also list each line step 2 dropped or rewrote. Ask whether to accept as-is or change specific roles, offering the detected models plus `inherit-parent` and `auto` as the options. Prefer `AskUserQuestion` over free text. For panel roles (arena runners, architect runners, interrogate reviewers) the value is a list, and one subagent runs per entry, alias entries included, so the list length sets the count. `arena cross-judge pool` is also a list, but Arena selects one value from it whose model family differs from the parent's when possible. `swarm workers` is the default model for every worker unless a race or comparison assigns another model per arm.\n\nThen ask for the default reasoning effort, the `default effort` line. It is `session`, which keeps the parent session's effort, or one of the levels in [Models](#models). Start from the default listed there. Every role value without a suffix runs at it. Then ask whether any role should run at another level. On Claude Code a role value may carry one after its slug, as in `\u003Cslug> @xhigh`; panel entries take their own, as in `\u003Cslug> @xhigh, \u003Cslug> @max`. Each level dispatches through the plugin's effort agent of that level, so the choice holds without changing the session. Leave the suffix off for the default effort.\n\n### 4. Choose whether the session hook routes tasks\n\nOn Claude Code and Codex, the plugin's `SessionStart` hook injects the batcave-mode mandate on startup, resume, clear, and compact. Codex asks the user to trust plugin hooks through `\u002Fhooks` before running them. On Pi, the batcave extension adds the same mandate to the system prompt at every agent start. Ask whether to keep the hook. The default is on. The answer is the `session hook` line in the current runtime's sheet: `on` or `off`. With no sheet or no line, the hook injects. The line is inert on other runtimes.\n\n### 5. Validate\n\nEvery real slug written must be in the detected set. `inherit-parent` and `auto` always pass. Validate the slug without any `@\u003Clevel>` suffix, and the level against the effort levels in [Models](#models). The `default effort` value is one of those levels or `session`. On Codex, the levels are the `reasoning_effort` values your Codex models accept instead. If a chosen real slug or level is not available, stop and ask again.\n\n### 6. Write the override sheet\n\nWrite the current runtime's sheet with the shape below. Overwrite the whole file so re-runs stay idempotent.\n\n```markdown\n# batcave model configuration\n\nPer-role model overrides for batcave skills. Each batcave SKILL.md names its defaults in a Models section; the values here override those defaults. Delete a line to fall back to the skill default. A value of `inherit-parent` or `auto` runs that role on the parent session's model (the `Agent` call omits `model`); an alias entry in a panel list still counts toward that panel's fan-out. A model may carry a reasoning effort, as in `opus @xhigh` (levels: low, medium, high, xhigh, max); the role then runs through the batcave effort agent of that level, each entry of a panel list on its own. `default effort` sets the level for a value without one; `session` keeps the parent session's effort. `session hook: off` stops the Claude Code or Codex SessionStart hook, or the batcave Pi extension, from injecting the batcave-mode mandate; any other value, or no line, leaves it on.\n\nfeature, refactoring: sonnet\nbug-fix: opus\nperf-issue: opus\nhillclimb: opus\njudgment and prose: opus\nstrongest judgment: fable\nhow explorer: opus\nhow explainer: opus\nwhy investigators: opus\nwhy synthesizer: opus\nreflect tooling: opus\nreflect judgment, divergent, synthesizer: opus\narena runners: opus, fable, sonnet, haiku\narena cross-judge pool: opus, fable, sonnet, haiku\nswarm workers: opus\narchitect runners: opus, fable, sonnet, haiku\ninterrogate reviewers: opus, fable, sonnet, haiku\n\ndefault effort: session\nsession hook: on\n```\n\n### 7. Wire it in\n\nOn Claude Code, if `\u003Cconfig>\u002FCLAUDE.md` does not already include `\u003Cconfig>\u002Fbatcave-models.md`, append an `@` line naming the sheet's resolved path, such as `@~\u002F.claude\u002Fbatcave-models.md`, so the model rows load on every session. If the user prefers project scope, add the include to the project's `CLAUDE.md` instead.\n\nOn Codex, paste the model rows and the `default effort` line into `\u003Ccodex-home>\u002FAGENTS.md`; Codex has no `@` include. Do not paste the `session hook` line there: the plugin hook reads it directly from `\u003Ccodex-home>\u002Fbatcave-models.md`.\n\n### 8. Confirm\n\nTell the user where the override was written, how its model rows load, and whether the plugin hook is on. Re-running this skill updates the override sheet.\n\n### 9. Offer a verification skill (optional)\n\nCheck whether the project has a way to drive the real app for proof (a project `verify` or `verify-*` skill, or an existing harness). If not, offer once: \"want a project-local verification skill, so agents can drive the app the way a user does and prove changes work? I can generate one with \u002Fcreate-verification-skill.\" On yes, invoke [`\u002Fcreate-verification-skill`](..\u002Fcreate-verification-skill\u002FSKILL.md). On no, move on without pushing.\n\n### 10. Offer a formal verification skill (optional)\n\nCheck whether the project already has a formal verification skill (a project skill that runs a model checker, a proof, or another verifier against the code). If not, offer once: \"want a formal verification skill, so agents can prove a key property of your code holds in every case in scope, not only the cases tests reach? I can generate one with \u002Fcreate-formal-verification-skill.\" On yes, invoke [`\u002Fcreate-formal-verification-skill`](..\u002Fcreate-formal-verification-skill\u002FSKILL.md). On no, move on without pushing.\n\n## Other runtimes\n\nThe role lines are the same everywhere. What differs is the sheet path, how the runtime loads it, and how you list models. Detect models with the runtime's own tool and never write a slug you have not seen listed. A runtime whose subagent call has no model parameter still gets the sheet, as the record of the user's choice, and applies it where it can. The `session hook` line applies to the Claude Code, Codex, and GitHub Copilot plugins and to the batcave Pi extension.\n\n| Runtime | Sheet | Load | List models | Status |\n| --- | --- | --- | --- | --- |\n| Claude Code | `\u003Cconfig>\u002Fbatcave-models.md` | `@\u003Cconfig>\u002Fbatcave-models.md` in `\u003Cconfig>\u002FCLAUDE.md` | the `Agent` tool's model parameter | verified live |\n| Codex | `\u003Ccodex-home>\u002Fbatcave-models.md` | model rows: paste into `\u003Ccodex-home>\u002FAGENTS.md`; hook setting: read by the plugin | your configured Codex models, see [codex-tools.md](..\u002Fbatcave-mode\u002Freferences\u002Fcodex-tools.md#model-names) | hook contract tested; discovery verified |\n| Pi | `batcave-models.md` in the Pi agent directory, `$PI_CODING_AGENT_DIR` or `~\u002F.pi\u002Fagent` | read by the batcave Pi extension, model rows and hook setting both; no include line | `pi --list-models`, see [pi-tools.md](..\u002Fbatcave-mode\u002Freferences\u002Fpi-tools.md#model-names) and its `setup-batcave` note | extension contract tested offline; live results in the repository's `docs\u002Fpi-equivalence.md` |\n| GitHub Copilot (CLI and app) | `${COPILOT_HOME:-~\u002F.copilot}\u002Fbatcave-models.md` | the plugin hook checks it and injects its role lines at session start; skills-only installs read it with `view` | the `task` tool's `model` enum, see [copilot-tools.md](..\u002Fbatcave-mode\u002Freferences\u002Fcopilot-tools.md#model-names) | hook contract tested; CLI install smoke-tested |\n| opencode | `~\u002F.config\u002Fopencode\u002Fbatcave-models.md` | add the path to the `instructions` array in `opencode.json` | the `models` slash command in the session | from published docs, no live session |\n| Gemini CLI | `~\u002F.gemini\u002Fbatcave-models.md` | `@~\u002F.gemini\u002Fbatcave-models.md` in `~\u002F.gemini\u002FGEMINI.md` | the `model` slash command in the session | from published docs, no live session |\n| Prime Agent | no documented sheet path; Prime's configuration chooses models | | | no live session |\n\n## Models\n\nStamped from `plugins\u002Fbatcave\u002Fmodels.json` (edit there, rerun `tools\u002Fgenerate.mjs`).\n\n- Available Claude models: `opus`, `fable`, `sonnet`, `haiku`\n- Default panel: `opus`, `fable`, `sonnet`, `haiku`\n- Reasoning effort levels: `low`, `medium`, `high`, `xhigh`, `max`\n- Default reasoning effort: `session`\n- Single-role default: `opus`\n",{"name":5,"description":7},"master","ffa275487ca7faa89d4a38dbc6eecab994d812dd","plugins\u002Fbatcave\u002Fskills\u002Fsetup-batcave","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave","https:\u002F\u002Fgithub.com\u002FAbhiman67","https:\u002F\u002Fabhishekchhandak.vercel.app\u002F","hehehehehe\r\n","2026-11-12 08:25:16",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Abhiman67\u002Fbatcave --skill setup-batcave",{"tool":38,"command":39},"bunx","bunx skills add Abhiman67\u002Fbatcave --skill setup-batcave",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Abhiman67\u002Fbatcave --skill setup-batcave","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fsetup-batcave\u002FSKILL.md",true,[46,52,58,62,66],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"copilot.md","REFERENCE","参考文档",11288,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fsetup-batcave\u002Fcopilot.md",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"scripts\u002Fcheck-sheet.awk","SCRIPT","脚本",224,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fsetup-batcave\u002Fscripts\u002Fcheck-sheet.awk",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fcheck-sheet.sh",792,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fsetup-batcave\u002Fscripts\u002Fcheck-sheet.sh",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fread-sheet.sh",474,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fsetup-batcave\u002Fscripts\u002Fread-sheet.sh",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fsheet.awk",5434,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fsetup-batcave\u002Fscripts\u002Fsheet.awk",[71,78,85,92,99,106],{"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":19},"01M7FD1NSBZDQSC0TP75CQN7A8","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7FD1KGG5Q5MZ3T8C0TQG7CN","what-did-i-get-done","Summarize authored commits over a user-specified time period into a concise update","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fwhat-did-i-get-done\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7FD1HZPM0F0YKYXMYASCPA7","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7FD1FXWCE2MY0VZYZ0TRBMW","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7FD1D8QPK5VVKABPGX4CENW","thermos","Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug\u002Fsecurity and code-quality branch audits.","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fthermos\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7FD18VJ6EGHPFKXFJB8PN3S","thermo-nuclear-review","Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch\u002FPR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fthermo-nuclear-review\u002FSKILL.md",[],[]]