[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AW501KDFX7AD412WWCF2VF":3,"skill-same:01M7AW501KDFX7AD412WWCF2VF":62},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"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":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7AW501KDFX7AD412WWCF2VF","climaker",null,"barkleesanders\u002Fclaude-code-starter","barkleesanders","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F30680901?v=4","01M7AW019CGBYWDA8MFJEN1JXC","Barklee Sanders","01M7AW01A5H994ASJ2QZPW67AV",4,"MIT","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fclimaker\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: climaker\ndescription: Generate a token-efficient Go CLI + MCP server for ANY API or website using the CLI Printing Press (mvanhorn\u002Fcli-printing-press). Use when the user wants to \"make a CLI\", \"print a CLI\", \"wrap an API in a CLI\", \"generate an MCP server for an API\", build an agent-native CLI, reprint\u002Fpolish\u002Fpublish a generated CLI, or score\u002Fdogfood\u002Fverify one. Triggers: \"climaker\", \"printing press\", \"\u002Fprinting-press\", \"make a CLI for \u003CAPI>\", \"build a CLI from these docs\", \"wrap \u003Cservice> as a CLI\", \"generate an MCP server\".\n---\n\n# climaker — CLI Printing Press wrapper\n\n`\u002Fclimaker` is a memorable entry point to the **CLI Printing Press** (`mvanhorn\u002Fcli-printing-press`): a Go generator + a set of Claude Code skills that read an API's docs (or sniff a website with no docs), absorb every competing CLI\u002FMCP feature, and print a token-efficient Go CLI **plus** an MCP server with a local-SQLite data layer, FTS5 search, compound insight commands, and agent-native flags.\n\n**This skill does not reimplement the press.** The press ships its own well-built `\u002Fprinting-press*` skills. `\u002Fclimaker` (1) installs the tool if missing, then (2) routes your request to the correct underlying skill or binary subcommand. Know what not to build — wrap the real tool.\n\n## Quick Start\n\n```text\n\u002Fclimaker Notion                          # print a CLI+MCP for an API by name\n\u002Fclimaker https:\u002F\u002Fpostman.com\u002Fexplore     # ...or point at a website (no spec needed)\n\u002Fclimaker --har .\u002Fcapture.har             # ...or a HAR export from DevTools\n```\n\nIf the press isn't installed yet, run the Preflight below first, then re-issue the command — it expands to the `\u002Fprinting-press` skill the press provides.\n\n## Preflight — ensure the press is installed\n\nTwo parts are required: the **binary** (`cli-printing-press`) and the **Printing Press skills** (`\u002Fprinting-press …`). Check both; install whatever is missing.\n\n```bash\n# 1. Binary present?\ncli-printing-press --version 2>\u002Fdev\u002Fnull || echo \"BINARY MISSING\"\n\n# 2. Skills present?  (look for the \u002Fprinting-press slash command)\nnpx -y skills@latest list -g -a claude-code 2>\u002Fdev\u002Fnull | grep -qi printing-press \\\n  && echo \"SKILLS OK\" || echo \"SKILLS MISSING\"\n```\n\nInstall (does both — binary via `go install`, then refreshes all press skills):\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmvanhorn\u002Fcli-printing-press\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n```\n\nOne side only:\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmvanhorn\u002Fcli-printing-press\u002Fmain\u002Fscripts\u002Finstall.sh | bash -s -- --cli-only\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmvanhorn\u002Fcli-printing-press\u002Fmain\u002Fscripts\u002Finstall.sh | bash -s -- --skills-only\n```\n\nCodex target instead of Claude Code: append `--agent codex`.\n\n**Prerequisites:** Go 1.26.4+, Node\u002Fnpm (for `npx`), Claude Code. Verify with `cli-printing-press --version`. If `command not found` after a good `go install`, add `$GOPATH\u002Fbin` (default `~\u002Fgo\u002Fbin`) to your `PATH`.\n\n**After a skills install\u002Frefresh you MUST reload the agent session** so the new `\u002Fprinting-press` slash commands load. Tell the user to restart Claude Code, then re-run their `\u002Fclimaker …` request.\n\n## Routing — map the request to the press\n\nAfter Preflight passes, translate the user's intent to the underlying command and invoke it. The press's slash commands ARE the supported interface; `\u002Fclimaker` is the alias that gets you there.\n\n| User intent | Run |\n|---|---|\n| Make \u002F print a CLI for an API or website | `\u002Fprinting-press \u003Cname-or-URL>` |\n| ...with 60% fewer Opus tokens (offload codegen to Codex) | `\u002Fprinting-press \u003Cname> codex` |\n| ...from a HAR capture (site uses websockets\u002Fbot-detection) | `\u002Fprinting-press --har .\u002Fcapture.har` |\n| Reprint an existing CLI under the latest machine | `\u002Fprinting-press-reprint \u003Cname>` |\n| Targeted fix-up of a generated CLI (diagnostics → fixes → clean) | `\u002Fprinting-press-polish \u003Cname>` |\n| Publish a finished CLI to the public library (validate → PR) | `\u002Fprinting-press-publish \u003Cname>` |\n| Turn friction from a dogfooding session into a library PR | `\u002Fprinting-press-amend [name]` |\n| Score \u002F dogfood \u002F verify a CLI dir (any CLI, even hand-built) | binary subcommands below |\n| Check which env tokens a printed CLI needs | `cli-printing-press auth doctor` |\n\nThe press also ships `printing-press-catalog`, `printing-press-import`, `printing-press-output-review`, `printing-press-retro`, and `printing-press-score` skills — surface those if the request matches (browse catalog, import a backup, review output, write a retro, score).\n\n## Binary subcommands (verification, no LLM loop)\n\nRun these directly on any CLI directory + spec — they don't need the skill layer:\n\n```bash\n# Two-tier quality scorecard (Grade A = 85+): infrastructure + domain correctness\ncli-printing-press scorecard --dir .\u002Fmy-pp-cli --spec .\u002Fopenapi.json\n\n# Dogfood: catches dead flags, dead functions, auth mismatches, invalid paths\ncli-printing-press dogfood  --dir .\u002Fmy-pp-cli --spec .\u002Fopenapi.json\n\n# Runtime verify against real API (read-only) or mock server\ncli-printing-press verify   --dir .\u002Fmy-pp-cli --spec .\u002Fopenapi.json --api-key \"$TOKEN\"\n\n# Baseline snapshot for the improvement cycle\ncli-printing-press emboss    --dir .\u002Fmy-pp-cli --spec .\u002Fopenapi.json --audit-only\n\n# Which library CLIs would benefit from new MCP spec surface\ncli-printing-press mcp-audit\n\n# Token diagnostics for printed CLIs (fingerprints only, never full tokens)\ncli-printing-press auth doctor [--json]\n```\n\n## Toolbelt (local augmentation CLIs)\n\nReal augmentation tools installed in `tools\u002F` that climaker shells out to *around* the\npress (never patched *into* the binary). Full versions, install commands, and per-stage\nmapping: **`tools\u002FREADME.md`**. The \"why each matters\" ranking: **`references\u002Faugmentation-registry.md`**.\n\n| Tool | Shell out when… | Command |\n|------|-----------------|---------|\n| `har2spec.sh` (wraps **har-to-openapi** 2.5.0) | user has a `.har`\u002Fsniff capture but no docs — bridge into the press's `--spec`\u002F`--har` path (Stage 2) | `tools\u002Fhar2spec.sh capture.har openapi.json` → then `cli-printing-press scorecard --spec .\u002Fopenapi.json` or `\u002Fprinting-press --spec .\u002Fopenapi.json` |\n| **restish** v2.2.0 | polishing a printed CLI's flags\u002Fauth (mine its response-shorthand + auth schemes), or smoke-testing a real API's shape (Stage 5) | `restish --version` · `restish api configure \u003Cname>` · `restish \u003Cname> \u003Cop> -f 'body.items[].name'` |\n| **ogen** v1.22.0 | hardening the typed `internal\u002Fclient` — generate a reference Go client to diff vs the press output (Stage 3) | `ogen --target .\u002Fref-ogen --package ref openapi.json` |\n| **oapi-codegen** v2.7.1 | same Stage 3 cross-check, alt generator | `oapi-codegen -generate types,client -package ref openapi.json > ref_client.go` |\n\n`mark3labs\u002Fmcp-go` and `modelcontextprotocol\u002Fgo-sdk` are **libraries, not CLIs** — nothing to\ninstall\u002Frun. They're vendored by a generated `\u003Capi>-pp-mcp` server and are PR targets for the\npress's MCP template; consult the repos, don't shell out.\n\n## What you get from one run\n\nEach `\u002Fprinting-press \u003Capi>` run produces two binaries — `\u003Capi>-pp-cli` (Cobra CLI) and `\u003Capi>-pp-mcp` (MCP server) — sharing one `internal\u002Fclient`, `internal\u002Fstore`, and auth. Plus research docs, verification proofs, and a Quality Score.\n\n- **Agent-native flags on every command:** `--json`, `--select`, `--dry-run`, `--stdin`, `--csv`, `--compact`, `--quiet`, `--yes`, `--no-input`, `--no-cache`, `--no-color`. Auto-JSON when piped (no `--json` needed). Typed exit codes: `0` success, `2` usage, `3` not-found, `4` auth, `5` API, `7` rate-limited.\n- **Local-first data layer:** domain SQLite tables (not JSON blobs), FTS5 search, incremental `sync` with cursors. `sync` pulls, `search` finds in ms, `sql` queries raw, `export`\u002F`tail`.\n- **Compound \u002F insight commands** (from domain archetype): `stale`, `orphans`, `load`, `channel-health`, `reconcile`, `health`, `similar`, `trends`, `bottleneck`.\n\n## Where output goes\n\n- Active runs: `~\u002Fprinting-press\u002F.runstate\u002F\u003Cscope>\u002Fruns\u002F\u003Crun-id>\u002Fworking\u002F\u003Capi>-pp-cli`\n- Published CLIs: `~\u002Fprinting-press\u002Flibrary\u002F\u003Capi>`\n- Archived manuscripts: `~\u002Fprinting-press\u002Fmanuscripts\u002F\u003Capi>\u002F\u003Crun-id>\u002F` (`research\u002F`, `proofs\u002F`, `discovery\u002F`, `pipeline\u002F`)\n\n`\u003Cscope>` derives from the git checkout path so parallel worktrees don't collide. `--output` overrides the generated CLI location.\n\n## Three input modes\n\n1. **API name** → press resolves the OpenAPI spec (19 pre-verified APIs in catalog: Asana, Discord, GitHub, Stripe, Twilio, …).\n2. **Website URL, no docs** → browser-sniff gate launches a browser, captures traffic, reverse-engineers the spec.\n3. **`--spec .\u002Fopenapi.json`** or **`--har .\u002Fcapture.har`** → explicit spec or DevTools capture.\n\n## Guidelines\n\n- **Default to the press's own skills.** `\u002Fclimaker` installs + routes; it does not duplicate the generation pipeline. After Preflight, hand off to `\u002Fprinting-press*`.\n- **Reload after a skills install** before expecting the `\u002Fprinting-press` slash commands to exist.\n- **Legal:** technical capability ≠ permission. Many services' ToS prohibit automated access. Confirm the user is authorized before sniffing or wrapping a service. (The press echoes this limitation; respect it.)\n- **Live verify is read-only** (GET, `--limit 1`, 10s timeout, stops on 401) — it never mutates.\n- **Codex fallback is automatic:** after 3 consecutive Codex failures, codegen falls back to local Opus, no intervention.\n- **Browser-sniff is manual capture** — point a browser or import a HAR; the press doesn't crawl autonomously.\n\n## Reference\n\n- Repo: https:\u002F\u002Fgithub.com\u002Fmvanhorn\u002Fcli-printing-press\n- Library \u002F catalog: https:\u002F\u002Fgithub.com\u002Fmvanhorn\u002Fprinting-press-library · https:\u002F\u002Fprintingpress.dev\n- Codex notes: `docs\u002FCODEX.md` · Pipeline contract: `docs\u002FPIPELINE.md`\n- **Augmentation registry:** `references\u002Faugmentation-registry.md` — ranked upstream repos (mcp-go, oapi-codegen, restish, har-to-openapi, …) mapped to the press pipeline stage each can strengthen. Consult when asked to make climaker\u002Fthe press \"stronger\" or to source an integration.\n","# climaker — CLI Printing Press wrapper\n\n`\u002Fclimaker` is a memorable entry point to the **CLI Printing Press** (`mvanhorn\u002Fcli-printing-press`): a Go generator + a set of Claude Code skills that read an API's docs (or sniff a website with no docs), absorb every competing CLI\u002FMCP feature, and print a token-efficient Go CLI **plus** an MCP server with a local-SQLite data layer, FTS5 search, compound insight commands, and agent-native flags.\n\n**This skill does not reimplement the press.** The press ships its own well-built `\u002Fprinting-press*` skills. `\u002Fclimaker` (1) installs the tool if missing, then (2) routes your request to the correct underlying skill or binary subcommand. Know what not to build — wrap the real tool.\n\n## Quick Start\n\n```text\n\u002Fclimaker Notion                          # print a CLI+MCP for an API by name\n\u002Fclimaker https:\u002F\u002Fpostman.com\u002Fexplore     # ...or point at a website (no spec needed)\n\u002Fclimaker --har .\u002Fcapture.har             # ...or a HAR export from DevTools\n```\n\nIf the press isn't installed yet, run the Preflight below first, then re-issue the command — it expands to the `\u002Fprinting-press` skill the press provides.\n\n## Preflight — ensure the press is installed\n\nTwo parts are required: the **binary** (`cli-printing-press`) and the **Printing Press skills** (`\u002Fprinting-press …`). Check both; install whatever is missing.\n\n```bash\n# 1. Binary present?\ncli-printing-press --version 2>\u002Fdev\u002Fnull || echo \"BINARY MISSING\"\n\n# 2. Skills present?  (look for the \u002Fprinting-press slash command)\nnpx -y skills@latest list -g -a claude-code 2>\u002Fdev\u002Fnull | grep -qi printing-press \\\n  && echo \"SKILLS OK\" || echo \"SKILLS MISSING\"\n```\n\nInstall (does both — binary via `go install`, then refreshes all press skills):\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmvanhorn\u002Fcli-printing-press\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n```\n\nOne side only:\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmvanhorn\u002Fcli-printing-press\u002Fmain\u002Fscripts\u002Finstall.sh | bash -s -- --cli-only\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fmvanhorn\u002Fcli-printing-press\u002Fmain\u002Fscripts\u002Finstall.sh | bash -s -- --skills-only\n```\n\nCodex target instead of Claude Code: append `--agent codex`.\n\n**Prerequisites:** Go 1.26.4+, Node\u002Fnpm (for `npx`), Claude Code. Verify with `cli-printing-press --version`. If `command not found` after a good `go install`, add `$GOPATH\u002Fbin` (default `~\u002Fgo\u002Fbin`) to your `PATH`.\n\n**After a skills install\u002Frefresh you MUST reload the agent session** so the new `\u002Fprinting-press` slash commands load. Tell the user to restart Claude Code, then re-run their `\u002Fclimaker …` request.\n\n## Routing — map the request to the press\n\nAfter Preflight passes, translate the user's intent to the underlying command and invoke it. The press's slash commands ARE the supported interface; `\u002Fclimaker` is the alias that gets you there.\n\n| User intent | Run |\n|---|---|\n| Make \u002F print a CLI for an API or website | `\u002Fprinting-press \u003Cname-or-URL>` |\n| ...with 60% fewer Opus tokens (offload codegen to Codex) | `\u002Fprinting-press \u003Cname> codex` |\n| ...from a HAR capture (site uses websockets\u002Fbot-detection) | `\u002Fprinting-press --har .\u002Fcapture.har` |\n| Reprint an existing CLI under the latest machine | `\u002Fprinting-press-reprint \u003Cname>` |\n| Targeted fix-up of a generated CLI (diagnostics → fixes → clean) | `\u002Fprinting-press-polish \u003Cname>` |\n| Publish a finished CLI to the public library (validate → PR) | `\u002Fprinting-press-publish \u003Cname>` |\n| Turn friction from a dogfooding session into a library PR | `\u002Fprinting-press-amend [name]` |\n| Score \u002F dogfood \u002F verify a CLI dir (any CLI, even hand-built) | binary subcommands below |\n| Check which env tokens a printed CLI needs | `cli-printing-press auth doctor` |\n\nThe press also ships `printing-press-catalog`, `printing-press-import`, `printing-press-output-review`, `printing-press-retro`, and `printing-press-score` skills — surface those if the request matches (browse catalog, import a backup, review output, write a retro, score).\n\n## Binary subcommands (verification, no LLM loop)\n\nRun these directly on any CLI directory + spec — they don't need the skill layer:\n\n```bash\n# Two-tier quality scorecard (Grade A = 85+): infrastructure + domain correctness\ncli-printing-press scorecard --dir .\u002Fmy-pp-cli --spec .\u002Fopenapi.json\n\n# Dogfood: catches dead flags, dead functions, auth mismatches, invalid paths\ncli-printing-press dogfood  --dir .\u002Fmy-pp-cli --spec .\u002Fopenapi.json\n\n# Runtime verify against real API (read-only) or mock server\ncli-printing-press verify   --dir .\u002Fmy-pp-cli --spec .\u002Fopenapi.json --api-key \"$TOKEN\"\n\n# Baseline snapshot for the improvement cycle\ncli-printing-press emboss    --dir .\u002Fmy-pp-cli --spec .\u002Fopenapi.json --audit-only\n\n# Which library CLIs would benefit from new MCP spec surface\ncli-printing-press mcp-audit\n\n# Token diagnostics for printed CLIs (fingerprints only, never full tokens)\ncli-printing-press auth doctor [--json]\n```\n\n## Toolbelt (local augmentation CLIs)\n\nReal augmentation tools installed in `tools\u002F` that climaker shells out to *around* the\npress (never patched *into* the binary). Full versions, install commands, and per-stage\nmapping: **`tools\u002FREADME.md`**. The \"why each matters\" ranking: **`references\u002Faugmentation-registry.md`**.\n\n| Tool | Shell out when… | Command |\n|------|-----------------|---------|\n| `har2spec.sh` (wraps **har-to-openapi** 2.5.0) | user has a `.har`\u002Fsniff capture but no docs — bridge into the press's `--spec`\u002F`--har` path (Stage 2) | `tools\u002Fhar2spec.sh capture.har openapi.json` → then `cli-printing-press scorecard --spec .\u002Fopenapi.json` or `\u002Fprinting-press --spec .\u002Fopenapi.json` |\n| **restish** v2.2.0 | polishing a printed CLI's flags\u002Fauth (mine its response-shorthand + auth schemes), or smoke-testing a real API's shape (Stage 5) | `restish --version` · `restish api configure \u003Cname>` · `restish \u003Cname> \u003Cop> -f 'body.items[].name'` |\n| **ogen** v1.22.0 | hardening the typed `internal\u002Fclient` — generate a reference Go client to diff vs the press output (Stage 3) | `ogen --target .\u002Fref-ogen --package ref openapi.json` |\n| **oapi-codegen** v2.7.1 | same Stage 3 cross-check, alt generator | `oapi-codegen -generate types,client -package ref openapi.json > ref_client.go` |\n\n`mark3labs\u002Fmcp-go` and `modelcontextprotocol\u002Fgo-sdk` are **libraries, not CLIs** — nothing to\ninstall\u002Frun. They're vendored by a generated `\u003Capi>-pp-mcp` server and are PR targets for the\npress's MCP template; consult the repos, don't shell out.\n\n## What you get from one run\n\nEach `\u002Fprinting-press \u003Capi>` run produces two binaries — `\u003Capi>-pp-cli` (Cobra CLI) and `\u003Capi>-pp-mcp` (MCP server) — sharing one `internal\u002Fclient`, `internal\u002Fstore`, and auth. Plus research docs, verification proofs, and a Quality Score.\n\n- **Agent-native flags on every command:** `--json`, `--select`, `--dry-run`, `--stdin`, `--csv`, `--compact`, `--quiet`, `--yes`, `--no-input`, `--no-cache`, `--no-color`. Auto-JSON when piped (no `--json` needed). Typed exit codes: `0` success, `2` usage, `3` not-found, `4` auth, `5` API, `7` rate-limited.\n- **Local-first data layer:** domain SQLite tables (not JSON blobs), FTS5 search, incremental `sync` with cursors. `sync` pulls, `search` finds in ms, `sql` queries raw, `export`\u002F`tail`.\n- **Compound \u002F insight commands** (from domain archetype): `stale`, `orphans`, `load`, `channel-health`, `reconcile`, `health`, `similar`, `trends`, `bottleneck`.\n\n## Where output goes\n\n- Active runs: `~\u002Fprinting-press\u002F.runstate\u002F\u003Cscope>\u002Fruns\u002F\u003Crun-id>\u002Fworking\u002F\u003Capi>-pp-cli`\n- Published CLIs: `~\u002Fprinting-press\u002Flibrary\u002F\u003Capi>`\n- Archived manuscripts: `~\u002Fprinting-press\u002Fmanuscripts\u002F\u003Capi>\u002F\u003Crun-id>\u002F` (`research\u002F`, `proofs\u002F`, `discovery\u002F`, `pipeline\u002F`)\n\n`\u003Cscope>` derives from the git checkout path so parallel worktrees don't collide. `--output` overrides the generated CLI location.\n\n## Three input modes\n\n1. **API name** → press resolves the OpenAPI spec (19 pre-verified APIs in catalog: Asana, Discord, GitHub, Stripe, Twilio, …).\n2. **Website URL, no docs** → browser-sniff gate launches a browser, captures traffic, reverse-engineers the spec.\n3. **`--spec .\u002Fopenapi.json`** or **`--har .\u002Fcapture.har`** → explicit spec or DevTools capture.\n\n## Guidelines\n\n- **Default to the press's own skills.** `\u002Fclimaker` installs + routes; it does not duplicate the generation pipeline. After Preflight, hand off to `\u002Fprinting-press*`.\n- **Reload after a skills install** before expecting the `\u002Fprinting-press` slash commands to exist.\n- **Legal:** technical capability ≠ permission. Many services' ToS prohibit automated access. Confirm the user is authorized before sniffing or wrapping a service. (The press echoes this limitation; respect it.)\n- **Live verify is read-only** (GET, `--limit 1`, 10s timeout, stops on 401) — it never mutates.\n- **Codex fallback is automatic:** after 3 consecutive Codex failures, codegen falls back to local Opus, no intervention.\n- **Browser-sniff is manual capture** — point a browser or import a HAR; the press doesn't crawl autonomously.\n\n## Reference\n\n- Repo: https:\u002F\u002Fgithub.com\u002Fmvanhorn\u002Fcli-printing-press\n- Library \u002F catalog: https:\u002F\u002Fgithub.com\u002Fmvanhorn\u002Fprinting-press-library · https:\u002F\u002Fprintingpress.dev\n- Codex notes: `docs\u002FCODEX.md` · Pipeline contract: `docs\u002FPIPELINE.md`\n- **Augmentation registry:** `references\u002Faugmentation-registry.md` — ranked upstream repos (mcp-go, oapi-codegen, restish, har-to-openapi, …) mapped to the press pipeline stage each can strengthen. Consult when asked to make climaker\u002Fthe press \"stronger\" or to source an integration.\n",{},"main","e7b39d448c7d905feed2b044d3ccdf60822596ab","skills\u002Fclimaker",0,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter","https:\u002F\u002Fgithub.com\u002Fbarkleesanders","barkleesanders.com","Stay Hungry, Stay Foolish","2026-11-06 08:47:06",{"source":7,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add barkleesanders\u002Fclaude-code-starter --skill climaker",{"tool":38,"command":39},"bunx","bunx skills add barkleesanders\u002Fclaude-code-starter --skill climaker",{"tool":41,"command":42},"pnpm","pnpm dlx skills add barkleesanders\u002Fclaude-code-starter --skill climaker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fclimaker\u002FSKILL.md",true,[46,52,58],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Faugmentation-registry.md","REFERENCE","参考文档",4946,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fclimaker\u002Freferences\u002Faugmentation-registry.md",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"tools\u002Fhar2spec.sh","SCRIPT","脚本",3168,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fclimaker\u002Ftools\u002Fhar2spec.sh",{"path":59,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":60,"sourceHtmlUrl":61},"tools\u002FREADME.md",6153,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fclimaker\u002Ftools\u002FREADME.md",[63,69,76,83,90,97],{"skillNo":64,"name":65,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M7AWV75B37B6YKG7ZKGZ783F","zi-search","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fzi-search\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M7AWTZA3JGK1T7V1HS543FG7","visualise","Render inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — directly in the conversation. Use this skill whenever the user asks to visualize, diagram, chart, illustrate, or explain something visually, or when an explanation would genuinely benefit from a spatial\u002Finteractive diagram rather than text. Also triggers for: flowcharts, architecture diagrams, data visualizations, interactive explainers, comparison layouts, UI mockups, and any request containing 'show me', 'draw', 'map out', 'visualize', or 'diagram'. Even when the user doesn't explicitly ask for a visual, use this skill proactively when the topic has spatial, sequential, or systemic relationships that a diagram would clarify better than prose.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvisualise\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M7AWTR056C3P9R3VS8YVM2WX","video","When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Runway,' 'Kling,' 'Pika,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social-content. For paid video ad creative, see ad-creative.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M7AWTHTWBMTYZPMHHEYX3TTG","manim-video","Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric\u002Fmathematical content.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-use\u002Fskills\u002Fmanim-video\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M7AWTCXDJ9NWFQW51ENM8A2Z","video-use","Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-use\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M7AWTA1D5FP895S33GHSA2G5","ui-improver","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fui-improver\u002FSKILL.md",[],[]]