[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJ1XCDH3QPQCDPXPSVRFDD":3,"skill-same:01M6MJ1XCDH3QPQCDPXPSVRFDD":64},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M6MJ1XCDH3QPQCDPXPSVRFDD","picking-a-format",null,"Use when choosing an output format for extracted documents — text, markdown, djot, html, or JSON. Maps consumer (LLM, parser, archive) to the right `--format` \u002F `--content-format` pair.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzberg\u002Fskills\u002Fpicking-a-format\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"format","picking a format","documents","content","markdown","archive","json","text","parser","pair","use","html","maps","output","for","when","2026-11-10 10:12:30",false,"---\nname: picking-a-format\ndescription: Use when choosing an output format for extracted documents — text, markdown, djot, html, or JSON. Maps consumer (LLM, parser, archive) to the right `--format` \u002F `--content-format` pair.\n---\n\n# Picking a format\n\nKreuzberg has two orthogonal format knobs. Get them right up front and the\ndownstream code stays simple.\n\n| Knob                | What it controls                                  | Values                                 | Default          |\n| ------------------- | ------------------------------------------------- | -------------------------------------- | ---------------- |\n| `--format`          | How the CLI prints the result                     | `text`, `json`                         | `text` (`extract`), `json` (`batch`) |\n| `--content-format`  | How extracted content is rendered inside `result` | `plain`, `markdown`, `djot`, `html`    | `plain`          |\n| `--token-reduction` | Strip whitespace \u002F boilerplate for LLM contexts   | `off`, `light`, `moderate`, `aggressive` | `off`          |\n\n`--format json` always returns the full `ExtractionResult` (content +\nmetadata + tables + images). `--format text` prints just `content`.\n`--content-format` is what shows up inside that `content` field.\n\n## Decision tree\n\n```text\nWho consumes the output?\n├── LLM (Claude, GPT, Gemini, local) — embed\u002Fprompt context\n│       --format text --content-format markdown\n├── Vector store \u002F RAG indexer\n│       --format json --content-format markdown\n│       (markdown preserves structure for chunking)\n├── Downstream parser that expects machine-readable JSON\n│       --format json --content-format plain\n│       (cleanest text + structured metadata)\n├── Human review \u002F archival\n│       --format text --content-format markdown\n├── HTML re-rendering \u002F web display\n│       --format json --content-format html\n├── Lossless intermediate for pandoc \u002F academic tooling\n│       --format json --content-format djot\n└── Token-budget-constrained pipeline\n        --format text --content-format plain\n        (drops markup; add --token-reduction moderate for further savings)\n```\n\n## Examples\n\nFeed a PDF directly into an LLM:\n\n```bash\nkreuzberg extract paper.pdf --content-format markdown\n```\n\nIndex a corpus into a RAG store with tables and headings preserved:\n\n```bash\nkreuzberg batch docs\u002F*.pdf --format json --content-format markdown \\\n  | jq -c '.[] | {path: .metadata.path, content: .content, tables: .tables}'\n```\n\nStrip a file to bare text for a token-tight summarizer:\n\n```bash\nkreuzberg extract long.pdf \\\n  --content-format plain \\\n  --token-reduction moderate\n```\n\nPull metadata only, ignore content:\n\n```bash\nkreuzberg extract file.pdf --format json | jq '.metadata'\n```\n\n## When in doubt\n\n- **Default to `markdown`** as the content format. It is the best\n  compromise across LLMs, RAG, and human review, and Kreuzberg has the\n  most faithful renderer for it.\n- Reach for `plain` only when downstream cannot tolerate any markup.\n- Reach for `djot` only if you're already in a djot\u002Fpandoc pipeline.\n- Reach for `html` only when re-rendering for the web.\n\n## Token-reduction (orthogonal)\n\n`--token-reduction` collapses whitespace, strips repeated headers\u002Ffooters,\nand trims boilerplate. It composes with any `--content-format`:\n\n- `off` (default), `light`, `moderate`, `aggressive`, `maximum`.\n\nUse `moderate` as a safe starting point for LLM context windows. `maximum`\nis lossy — verify before relying on it.\n\nSee `references\u002Fcli-reference.md` for the full flag set and\n`references\u002Fconfiguration.md` for the equivalent `output_format` and\n`token_reduction` keys in `kreuzberg.toml`.\n","# Picking a format\n\nKreuzberg has two orthogonal format knobs. Get them right up front and the\ndownstream code stays simple.\n\n| Knob                | What it controls                                  | Values                                 | Default          |\n| ------------------- | ------------------------------------------------- | -------------------------------------- | ---------------- |\n| `--format`          | How the CLI prints the result                     | `text`, `json`                         | `text` (`extract`), `json` (`batch`) |\n| `--content-format`  | How extracted content is rendered inside `result` | `plain`, `markdown`, `djot`, `html`    | `plain`          |\n| `--token-reduction` | Strip whitespace \u002F boilerplate for LLM contexts   | `off`, `light`, `moderate`, `aggressive` | `off`          |\n\n`--format json` always returns the full `ExtractionResult` (content +\nmetadata + tables + images). `--format text` prints just `content`.\n`--content-format` is what shows up inside that `content` field.\n\n## Decision tree\n\n```text\nWho consumes the output?\n├── LLM (Claude, GPT, Gemini, local) — embed\u002Fprompt context\n│       --format text --content-format markdown\n├── Vector store \u002F RAG indexer\n│       --format json --content-format markdown\n│       (markdown preserves structure for chunking)\n├── Downstream parser that expects machine-readable JSON\n│       --format json --content-format plain\n│       (cleanest text + structured metadata)\n├── Human review \u002F archival\n│       --format text --content-format markdown\n├── HTML re-rendering \u002F web display\n│       --format json --content-format html\n├── Lossless intermediate for pandoc \u002F academic tooling\n│       --format json --content-format djot\n└── Token-budget-constrained pipeline\n        --format text --content-format plain\n        (drops markup; add --token-reduction moderate for further savings)\n```\n\n## Examples\n\nFeed a PDF directly into an LLM:\n\n```bash\nkreuzberg extract paper.pdf --content-format markdown\n```\n\nIndex a corpus into a RAG store with tables and headings preserved:\n\n```bash\nkreuzberg batch docs\u002F*.pdf --format json --content-format markdown \\\n  | jq -c '.[] | {path: .metadata.path, content: .content, tables: .tables}'\n```\n\nStrip a file to bare text for a token-tight summarizer:\n\n```bash\nkreuzberg extract long.pdf \\\n  --content-format plain \\\n  --token-reduction moderate\n```\n\nPull metadata only, ignore content:\n\n```bash\nkreuzberg extract file.pdf --format json | jq '.metadata'\n```\n\n## When in doubt\n\n- **Default to `markdown`** as the content format. It is the best\n  compromise across LLMs, RAG, and human review, and Kreuzberg has the\n  most faithful renderer for it.\n- Reach for `plain` only when downstream cannot tolerate any markup.\n- Reach for `djot` only if you're already in a djot\u002Fpandoc pipeline.\n- Reach for `html` only when re-rendering for the web.\n\n## Token-reduction (orthogonal)\n\n`--token-reduction` collapses whitespace, strips repeated headers\u002Ffooters,\nand trims boilerplate. It composes with any `--content-format`:\n\n- `off` (default), `light`, `moderate`, `aggressive`, `maximum`.\n\nUse `moderate` as a safe starting point for LLM context windows. `maximum`\nis lossy — verify before relying on it.\n\nSee `references\u002Fcli-reference.md` for the full flag set and\n`references\u002Fconfiguration.md` for the equivalent `output_format` and\n`token_reduction` keys in `kreuzberg.toml`.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzberg\u002Fskills\u002Fpicking-a-format",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill picking-a-format",{"tool":56,"command":57},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill picking-a-format",{"tool":59,"command":60},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill picking-a-format","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzberg\u002Fskills\u002Fpicking-a-format\u002FSKILL.md",true,[],[65,75,83,91,99,107],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":74},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":69,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":74},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":74},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":74},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\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":69,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":74},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":74},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]