[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C751RE178G4VMDCA0WMENR":3,"skill-same:01M7C751RE178G4VMDCA0WMENR":46},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7C751RE178G4VMDCA0WMENR","caveman-discover",null,"Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for \"discover workflows\" or breaking LLM spend down by workflow.","hriday-singh\u002Fcrossfire","hriday-singh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204199464?v=4","01M7C743B50345ZTX2155K2K1H","Hriday Singh","01M7C743BT6KAMTPAKWJ0JN7EV",4,"MIT","https:\u002F\u002Fgithub.com\u002Fhriday-singh\u002Fcrossfire\u002Fblob\u002Fmain\u002Ffrontend\u002F.agents\u002Fskills\u002Fcaveman-discover\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: caveman-discover\ndescription: >\n  Find and label every LLM workflow in the repository so Caveman Cloud groups\n  spend by workflow instead of one bucket. Use for \"discover workflows\" or\n  breaking LLM spend down by workflow.\n---\n\nYou are labeling this repository's LLM workflows for Caveman Cloud. A\n*workflow* is a job the code performs — \"answer a support ticket\", \"build the\nnightly digest\", \"run the eval suite\" — not a technology. Every gateway\nrequest can carry a workflow label; unlabeled traffic all lands in one\n`unlabeled-workflow` bucket. Your job: find the workflows, name them well,\nwire the labels, and verify nothing broke.\n\nThis changes code, so it goes through the user's normal review: **propose the\ntable first, apply after the user agrees.** Re-running on an already-labeled\nrepo must change nothing (idempotent).\n\nThis skill is operator-invoked. An `unlabeled-traffic` Cave Plan observation is\nreview-only and does not create an advisory file, proposal, or Draft PR. Do not\ninfer that telemetry selected a callsite or authorized an edit. Independently\ninventory the repository, present the labeling table, and wait for the user's\napproval before changing code.\n\n## Step 1 — Inventory the workflows\n\nWalk the repo from its entry points, not from its imports:\n\n- HTTP\u002FRPC handlers that call an LLM (directly or through layers)\n- Scheduled jobs: cron definitions, queue consumers, workers, GitHub Actions\n  that invoke LLM code\n- CLI commands and scripts (`scripts\u002F`, `bin\u002F`, package.json scripts)\n- Eval \u002F test harnesses that burn real tokens\n- Distinct agents or chains inside a framework (each LangGraph graph, each\n  crew, each agent definition is usually its own workflow)\n\nOne workflow = one job a human would name. Ten callsites inside the same\nrequest handler are one workflow; one shared `llm.ts` helper used by three\njobs is three workflows (label at the callers, never the shared helper).\n\n## Step 2 — Name them\n\nSlug grammar (the gateway enforces this): lowercase `[a-z0-9_-]`, 1–96 chars.\nName the job, not the tech:\n\n- Good: `support-reply`, `nightly-digest`, `pr-review`, `eval-suite`,\n  `onboarding-email`\n- Bad: `openai-calls` (tech), `main` (says nothing), `SupportReply` (invalid),\n  `johns-test-3` (won't age)\n\nNames are forever-ish — renaming later splits the spend history. When a job's\npurpose isn't clear from the code, derive the slug from the file name and mark\nit `review` in the table rather than inventing a purpose.\n\n## Step 3 — Propose, then apply\n\nPresent this table and ask to proceed:\n\n```\n| workflow | job | where | how it gets labeled |\n|---|---|---|---|\n| support-reply | answers inbound tickets | src\u002Fbot\u002Freply.ts:41 | defaultHeaders on the reply client |\n| nightly-digest | 02:00 summary job | jobs\u002Fdigest.ts:12 | header on the digest client |\n| eval-suite (review) | scripts\u002Feval.ts:8 — purpose inferred from filename | scripts\u002Feval.ts:8 | env override at invocation |\n```\n\nThen wire each label with the lightest mechanism available at that callsite:\n\n- **@caveman-ai\u002Fsdk \u002F caveman_cloud SDK**: per-trace `workflow` option, or\n  `defaultWorkflow` on the client a single-job service constructs.\n- **Raw provider SDKs** (OpenAI\u002FAnthropic\u002FLangChain\u002FLiteLLM\u002FVercel): add\n  `\"x-cave-workflow\": \"\u003Cslug>\"` to the same `defaultHeaders` \u002F\n  `default_headers` \u002F `extra_headers` block that already carries\n  `x-cave-api-key`. Shared client used by several jobs → pass the header per\n  call (every SDK above accepts per-request header overrides), or give each\n  job its own thin client.\n- **Wrapped coding agents** (`caveman wrap`): `--workflow \u003Cslug>` flag or\n  `CAVE_WORKFLOW=\u003Cslug>` env at the invocation site (cron line, CI step).\n- **Raw HTTP**: add the `x-cave-workflow` header to the request.\n\nLabel the callers, keep the diff minimal, match the repo's style. If a\ncallsite is not routed through the Caveman gateway at all, don't label it —\nlist it under \"not wired\" in the report (labels only travel on gateway\ntraffic; wiring is the caveman-setup skill's job).\n\n## Step 4 — Verify\n\nRun whatever the repo already uses to exercise one labeled path (a test, a\ndev script, one curl). Then confirm: the request still succeeds (the gateway\nrejects an invalid label with 400 `cave_invalid_request_header` — fix the slug\nif so). Labeled spend appears on the dashboard at `\u002Factivity?tab=workflows` as\neach workflow next runs; jobs on a schedule show up when the schedule fires,\nand that's worth saying in the report rather than pretending they're live.\n\n## Step 5 — Report\n\n```\n## Workflows labeled\n\n| workflow | job | where |\n|---|---|---|\n| support-reply | answers inbound tickets | src\u002Fbot\u002Freply.ts:41 |\n| nightly-digest | 02:00 summary job | jobs\u002Fdigest.ts:12 |\n\nVerified: \u003Cthe labeled path you actually exercised, and what you observed>\nLands at: \u003CDASHBOARD>\u002Factivity?tab=workflows — each row appears as that workflow\nnext runs. Anything still unlabeled shows as `unlabeled-workflow`.\nNot wired (no gateway routing, so no label): \u003Clist or \"none\">\nMarked review: \u003Cslugs whose purpose was inferred from filenames, or \"none\">\n```\n\nIf you found no LLM entry points at all: say exactly that, and point at the\nsetup skill (`\u003Cdocs origin>\u002Fdocs\u002Fagent-setup.md`) instead of manufacturing a\ntable.\n","You are labeling this repository's LLM workflows for Caveman Cloud. A\n*workflow* is a job the code performs — \"answer a support ticket\", \"build the\nnightly digest\", \"run the eval suite\" — not a technology. Every gateway\nrequest can carry a workflow label; unlabeled traffic all lands in one\n`unlabeled-workflow` bucket. Your job: find the workflows, name them well,\nwire the labels, and verify nothing broke.\n\nThis changes code, so it goes through the user's normal review: **propose the\ntable first, apply after the user agrees.** Re-running on an already-labeled\nrepo must change nothing (idempotent).\n\nThis skill is operator-invoked. An `unlabeled-traffic` Cave Plan observation is\nreview-only and does not create an advisory file, proposal, or Draft PR. Do not\ninfer that telemetry selected a callsite or authorized an edit. Independently\ninventory the repository, present the labeling table, and wait for the user's\napproval before changing code.\n\n## Step 1 — Inventory the workflows\n\nWalk the repo from its entry points, not from its imports:\n\n- HTTP\u002FRPC handlers that call an LLM (directly or through layers)\n- Scheduled jobs: cron definitions, queue consumers, workers, GitHub Actions\n  that invoke LLM code\n- CLI commands and scripts (`scripts\u002F`, `bin\u002F`, package.json scripts)\n- Eval \u002F test harnesses that burn real tokens\n- Distinct agents or chains inside a framework (each LangGraph graph, each\n  crew, each agent definition is usually its own workflow)\n\nOne workflow = one job a human would name. Ten callsites inside the same\nrequest handler are one workflow; one shared `llm.ts` helper used by three\njobs is three workflows (label at the callers, never the shared helper).\n\n## Step 2 — Name them\n\nSlug grammar (the gateway enforces this): lowercase `[a-z0-9_-]`, 1–96 chars.\nName the job, not the tech:\n\n- Good: `support-reply`, `nightly-digest`, `pr-review`, `eval-suite`,\n  `onboarding-email`\n- Bad: `openai-calls` (tech), `main` (says nothing), `SupportReply` (invalid),\n  `johns-test-3` (won't age)\n\nNames are forever-ish — renaming later splits the spend history. When a job's\npurpose isn't clear from the code, derive the slug from the file name and mark\nit `review` in the table rather than inventing a purpose.\n\n## Step 3 — Propose, then apply\n\nPresent this table and ask to proceed:\n\n```\n| workflow | job | where | how it gets labeled |\n|---|---|---|---|\n| support-reply | answers inbound tickets | src\u002Fbot\u002Freply.ts:41 | defaultHeaders on the reply client |\n| nightly-digest | 02:00 summary job | jobs\u002Fdigest.ts:12 | header on the digest client |\n| eval-suite (review) | scripts\u002Feval.ts:8 — purpose inferred from filename | scripts\u002Feval.ts:8 | env override at invocation |\n```\n\nThen wire each label with the lightest mechanism available at that callsite:\n\n- **@caveman-ai\u002Fsdk \u002F caveman_cloud SDK**: per-trace `workflow` option, or\n  `defaultWorkflow` on the client a single-job service constructs.\n- **Raw provider SDKs** (OpenAI\u002FAnthropic\u002FLangChain\u002FLiteLLM\u002FVercel): add\n  `\"x-cave-workflow\": \"\u003Cslug>\"` to the same `defaultHeaders` \u002F\n  `default_headers` \u002F `extra_headers` block that already carries\n  `x-cave-api-key`. Shared client used by several jobs → pass the header per\n  call (every SDK above accepts per-request header overrides), or give each\n  job its own thin client.\n- **Wrapped coding agents** (`caveman wrap`): `--workflow \u003Cslug>` flag or\n  `CAVE_WORKFLOW=\u003Cslug>` env at the invocation site (cron line, CI step).\n- **Raw HTTP**: add the `x-cave-workflow` header to the request.\n\nLabel the callers, keep the diff minimal, match the repo's style. If a\ncallsite is not routed through the Caveman gateway at all, don't label it —\nlist it under \"not wired\" in the report (labels only travel on gateway\ntraffic; wiring is the caveman-setup skill's job).\n\n## Step 4 — Verify\n\nRun whatever the repo already uses to exercise one labeled path (a test, a\ndev script, one curl). Then confirm: the request still succeeds (the gateway\nrejects an invalid label with 400 `cave_invalid_request_header` — fix the slug\nif so). Labeled spend appears on the dashboard at `\u002Factivity?tab=workflows` as\neach workflow next runs; jobs on a schedule show up when the schedule fires,\nand that's worth saying in the report rather than pretending they're live.\n\n## Step 5 — Report\n\n```\n## Workflows labeled\n\n| workflow | job | where |\n|---|---|---|\n| support-reply | answers inbound tickets | src\u002Fbot\u002Freply.ts:41 |\n| nightly-digest | 02:00 summary job | jobs\u002Fdigest.ts:12 |\n\nVerified: \u003Cthe labeled path you actually exercised, and what you observed>\nLands at: \u003CDASHBOARD>\u002Factivity?tab=workflows — each row appears as that workflow\nnext runs. Anything still unlabeled shows as `unlabeled-workflow`.\nNot wired (no gateway routing, so no label): \u003Clist or \"none\">\nMarked review: \u003Cslugs whose purpose was inferred from filenames, or \"none\">\n```\n\nIf you found no LLM entry points at all: say exactly that, and point at the\nsetup skill (`\u003Cdocs origin>\u002Fdocs\u002Fagent-setup.md`) instead of manufacturing a\ntable.\n",{"name":5,"description":7},"main","50209fc6639d3c2c5daccfec9793046ee821cd25","frontend\u002F.agents\u002Fskills\u002Fcaveman-discover",1,"https:\u002F\u002Fgithub.com\u002Fhriday-singh\u002Fcrossfire","https:\u002F\u002Fgithub.com\u002Fhriday-singh","I build scalable products, built for production. ","2026-10-17 03:11:09",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add hriday-singh\u002Fcrossfire --skill caveman-discover",{"tool":38,"command":39},"bunx","bunx skills add hriday-singh\u002Fcrossfire --skill caveman-discover",{"tool":41,"command":42},"pnpm","pnpm dlx skills add hriday-singh\u002Fcrossfire --skill caveman-discover","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhriday-singh\u002Fcrossfire\u002Fblob\u002Fmain\u002Ffrontend\u002F.agents\u002Fskills\u002Fcaveman-discover\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7C7CEAR7JAK56GA653AKZC7","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","https:\u002F\u002Fgithub.com\u002Fhriday-singh\u002Fcrossfire\u002Fblob\u002Fmain\u002Ffrontend\u002F.agents\u002Fskills\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7C7CCY4Q1SXZW1CS8ZTFHJ3","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Fhriday-singh\u002Fcrossfire\u002Fblob\u002Fmain\u002Ffrontend\u002F.agents\u002Fskills\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7C7CA1D1R2RGKK57VRF0HQ9","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fhriday-singh\u002Fcrossfire\u002Fblob\u002Fmain\u002Ffrontend\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7C7C81RPXFAPXZ7Z0SNJEMN","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Fhriday-singh\u002Fcrossfire\u002Fblob\u002Fmain\u002Ffrontend\u002F.agents\u002Fskills\u002Fwriting-beats\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7C7C4PTXTRBSEB0ZTD8JM96","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fhriday-singh\u002Fcrossfire\u002Fblob\u002Fmain\u002Ffrontend\u002F.agents\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7C7C2A2X9N73M5QQ4S4AWAV","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fhriday-singh\u002Fcrossfire\u002Fblob\u002Fmain\u002Ffrontend\u002F.agents\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[]]