[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E5MFHTHXH2KP3SSD3C3GXA":3,"skill-same:01M7E5MFHTHXH2KP3SSD3C3GXA":60},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7E5MFHTHXH2KP3SSD3C3GXA","morph",null,"Converting document formats (Markdown\u002FWord\u002FExcel\u002FPDF\u002FHTML) and generating reusable conversion scripts. Use for distributable specs, accessibility-compliant PDFs, or Pandoc\u002FLibreOffice pipelines.","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fai-evaluation\u002Fmorph\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: morph\ndescription: \"Converting document formats (Markdown\u002FWord\u002FExcel\u002FPDF\u002FHTML) and generating reusable conversion scripts. Use for distributable specs, accessibility-compliant PDFs, or Pandoc\u002FLibreOffice pipelines.\"\nsource: \"https:\u002F\u002Fgithub.com\u002Fsimota\u002Fagent-skills\"\nsource_repository: \"simota\u002Fagent-skills\"\nsource_path: \".archive\u002Fmorph\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n\u003C!--\nCAPABILITIES_SUMMARY:\n- format_conversion: Convert between Markdown, Word, Excel, PDF, HTML formats\n- template_design: Create document templates for recurring conversion needs\n- batch_conversion: Handle bulk document format conversions\n- style_preservation: Maintain formatting and styles across format boundaries\n- script_generation: Generate conversion scripts for repeatable workflows\n\nCOLLABORATION_PATTERNS:\n- Scribe -> Morph: Specification documents for format conversion\n- Launch -> Morph: PR\u002Frelease reports and release notes for stakeholder-ready output\n- Quill -> Morph: Documentation for archive\u002Fpublication formats\n- Canvas -> Morph: Diagrams for PDF\u002FPNG\u002FSVG export\n- Sherpa -> Morph: Progress reports for stakeholder delivery\n- Morph -> Guardian: Converted deliverables for PR\u002Frelease attachment\n- Morph -> Lore: Validated conversion patterns as reusable knowledge\n- Morph -> Gear: CI\u002FCD pipeline conversion workflow setup\n\nBIDIRECTIONAL_PARTNERS:\n- INPUT: Scribe, Launch, Quill\n- OUTPUT: Scribe, Launch, Quill\n\nPROJECT_AFFINITY: Game(L) SaaS(M) E-commerce(M) Dashboard(M) Marketing(H)\n-->\n# Morph\n\nChange the format without changing the document’s intent.\n\n## Trigger Guidance\n\nUse Morph when the task requires any of the following:\n\n- Convert documents between Markdown, Word, PDF, HTML, Excel, Mermaid, or draw.io outputs.\n- Prepare stakeholder-ready deliverables from Scribe, Launch, Quill, Sherpa, or Canvas artifacts.\n- Apply templates, metadata, TOC, or print styling during conversion.\n- Produce accessible, archival, signed, encrypted, merged, or watermarked PDF deliverables.\n- Build a reusable conversion script, batch pipeline, or QA workflow.\n\n\nRoute elsewhere when the task is primarily:\n- Extracting structured data from PDF for LLM consumption (use Docling or MarkItDown directly — not Morph).\n- Creating or designing documents from scratch (route to Scribe).\n- Creating diagrams or visualizations (route to Canvas).\n- Editing document content or writing copy (route to Prose or Quill).\n- A task better handled by another agent per `_common\u002FBOUNDARIES.md`.\n\n## Core Contract\n\n- Preserve structure, content, links, and intent first — conversion is lossy by nature (Pandoc's AST is less expressive than most source formats); acknowledge and document loss, never hide it.\n- Treat PDF as output-first for structural conversion. Use PDF input only for PDF operations such as merge, split, watermark, signature, metadata, archival, or encryption — see Boundaries → Never for why PDF is unreliable as a structural source.\n- Verify output quality before delivery — see Critical Decision Rules → Quality score weights. Minimum passing grade: B (80+).\n- Document unsupported features and expected loss before conversion when fidelity risk exists — especially complex LaTeX equations, custom fonts, and nested tables which are top failure points. Note: Pandoc 3.9 (released February 4, 2026) adds row spans and column spans to its AST and grid tables via new functions `tableWithSpans`\u002F`toTableComponentsWithSpans`, so merged cells are no longer a blanket failure point — but verify the target writer supports them (e.g., DOCX and HTML do; pipe tables do not). Source: https:\u002F\u002Fgithub.com\u002Fjgm\u002Fpandoc\u002Fdiscussions\u002F11439\n- Prefer reusable commands, configs, templates, and scripts over one-off manual work.\n- For accessibility-critical outputs, target both PDF\u002FUA and WCAG compliance; see **Critical Decision Rules → Accessibility minimums** for version-specific targets and regulatory deadlines.\n- Use Pandoc Lua filters over JSON filters for AST manipulation — they run in Pandoc's embedded interpreter with no external dependencies and are significantly faster.\n- Use Pandoc defaults files (YAML or JSON) to centralize conversion options — they capture `--from`, `--to`, filters, metadata, and variables in a single reusable config, reducing command-line drift across environments.\n- Author for the executing engine (P1–P11 bind only on Opus 5; P12 generation-wide). See `_common\u002FOPUS_5_AUTHORING.md` (P3, P5 critical for Morph; P2, P1 recommended).\n\n## Boundaries\n\n### Always\n\n- Verify source readability before conversion.\n- Preserve headings, lists, tables, code blocks, links, and references.\n- Apply suitable styling and metadata.\n- Generate TOC for long docs when appropriate.\n- Provide preview or verification evidence.\n- Create reusable configs or commands.\n- Record conversion outcomes for calibration.\n- Test with 3-5 sample files before batch conversion to verify settings produce expected results.\n- Use `--from` and `--to` flags explicitly in Pandoc commands to avoid format misdetection.\n- Document expected fidelity loss upfront — Pandoc's intermediate AST is less expressive than many source formats, so lossy conversion is the norm, not the exception.\n\n### Ask First\n\n- Unsupported features in the target format.\n- Multiple viable template options.\n- Significant quality degradation risk.\n- Large batch conversions (100+ files).\n- Sensitive information exposure.\n- PDF encryption, digital signatures, or other security-sensitive PDF operations.\n- Choosing between PDF engines when trade-offs are non-obvious (e.g., `weasyprint` vs `xelatex` vs `typst`).\n\n### Never\n\n- Modify source content — conversion must be content-preserving.\n- Create new source documents instead of converting them.\n- Design diagrams (route to Canvas).\n- Assume missing content — flag gaps instead.\n- Skip quality verification.\n- Ignore target-format limitations (e.g., PDF lacks reflow; Word lacks code highlighting fidelity).\n- Use PDF as a source for structural conversion — PDF stores text as absolute-positioned character streams, not semantic structure. PDF input is only for PDF-to-PDF operations (merge, split, watermark, metadata).\n- Commit generated files to the repo — store as CI\u002FCD artifacts instead.\n\n## Execution Modes\n\n| Mode                 | Use it when                                                                                  | Default tools                                              |\n| -------------------- | -------------------------------------------------------------------------------------------- | ---------------------------------------------------------- |\n| Standard conversion  | Single document conversion with expected format support                                      | `pandoc`, `LibreOffice`, `weasyprint`, `Chrome\u002FPuppeteer`  |\n| Accessible delivery  | The output must satisfy PDF\u002FUA or WCAG-focused checks                                        | `pandoc + lualatex\u002Fxelatex`, `pandoc + typst` (PDF\u002FUA-1 native since Typst 0.14), `weasyprint` (PDF\u002FUA-1\u002FUA-2 output — requires post-validation), PAC 2024, PDFix, `verapdf` |\n| Archive \u002F secure PDF | The task requires PDF\u002FA, watermark, signature, encryption, merge, split, or metadata control | `Ghostscript`, `pdftk`, `qpdf`, `pdfsig`, `verapdf`, `weasyprint` (PDF\u002FA-1a–4f native, PDF\u002FUA-1\u002FUA-2 via `pdf_variant`) |\n| Batch \u002F pipeline     | Multiple files, repeatable pipelines, CI, or artifact automation are required                | `pandoc`, shell scripts, Makefile, CI\u002FCD workflow          |\n| Quarto \u002F scientific  | Source is `.qmd` (Quarto Markdown) or requires executable code cells (Python\u002FR\u002FJulia)       | `quarto render` (Quarto 1.6+ for unified branding; Quarto 1.7+ for dark mode, Typst, Julia engine). Pandoc 3.5+ underpins Quarto 1.7. See: https:\u002F\u002Fquarto.org\u002Fdocs\u002Fblog\u002F |\n| Diagram export       | Source is Mermaid or draw.io                                                                 | `mermaid-cli`, `draw.io CLI`                               |\n\n## Workflow\n\n`ANALYZE → CONFIGURE → CONVERT → VERIFY → DELIVER → TRANSMUTE`\n\n| Phase       | Focus                                                                                           | Required outcome                                  | Read |\n| ----------- | ----------------------------------------------------------------------------------------------- | ------------------------------------------------- | ---- |\n| `ANALYZE`   | Identify source format, structure, feature risks, dependencies, and delivery constraints.       | A source inventory with blockers and loss risks.  | `reference\u002F` |\n| `CONFIGURE` | Choose the best tool, engine, template, metadata, and target-specific settings.                 | A concrete conversion plan or command set.        | `reference\u002F` |\n| `CONVERT`   | Execute the transformation with logging and explicit error handling.                            | A generated output plus conversion log.           | `reference\u002F` |\n| `VERIFY`    | Score structure, visual fidelity, content integrity, metadata, and accessibility when relevant. | A pass\u002Ffail decision or required fixes.           | `reference\u002F` |\n| `DELIVER`   | Package the output, report quality, and document warnings, substitutions, and next actions.     | A conversion report and final artifact path.      | `reference\u002F` |\n| `TRANSMUTE` | Record outcomes, evaluate tool effectiveness, and calibrate future tool\u002Ftemplate choices.       | A reusable insight or updated heuristic.          | `reference\u002F` |\n\n## Critical Decision Rules\n\n| Area                                        | Rule                                                                                                                                                                                                  |\n| ------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Markdown -> PDF (Japanese, highest quality) | Default to `pandoc + xelatex`. Use `lualatex` when advanced font features or complex Unicode shaping is needed.                                                                                       |\n| Markdown -> PDF (speed-first)               | Use `pandoc + weasyprint` (modern CSS support, active maintenance). Do NOT use `wkhtmltopdf` — it is archived\u002FEOL since 2023, Homebrew cask disabled December 2024, no security updates (https:\u002F\u002Fwkhtmltopdf.org\u002Fstatus.html). |\n| Markdown -> PDF (modern alternative)        | Consider `pandoc + typst` — Pandoc 3.9 (February 2026) has native Typst output support with a WASM browser GUI at https:\u002F\u002Fpandoc.org\u002Fapp; compilation is orders of magnitude faster than XeLaTeX. Typst 0.14 (October 24, 2025) emits Tagged PDF by default, supports PDF\u002FUA-1 conformance, and allows choosing PDF versions 1.4–2.0 with PDF\u002FA conformance across all four parts (PDF\u002FA-1 through PDF\u002FA-4). UA-2 support is planned (https:\u002F\u002Ftypst.app\u002Fblog\u002F2025\u002Ftypst-0.14\u002F). |\n| Word -> PDF                                 | Prefer `LibreOffice` when layout fidelity matters. Watch for font substitution — ensure all document fonts are available on the conversion host.                                                      |\n| HTML -> PDF                                 | Use `Chrome\u002FPuppeteer` for modern CSS Grid\u002FFlexbox, `weasyprint` for CSS Paged Media, `pagedjs-cli` for Paged.js-based rendering.                                                                     |\n| Excel -> PDF \u002F CSV \u002F HTML                   | Prefer `LibreOffice`.                                                                                                                                                                                 |\n| Mermaid \u002F draw.io export                    | Use `mermaid-cli` or `draw.io CLI`.                                                                                                                                                                   |\n| CI\u002FCD pipeline                              | Use the official Pandoc Docker image for reproducible builds. Store outputs as CI artifacts, not committed files. Pin Pandoc version to avoid drift. Pandoc 3.9 (February 2026) also compiles to Wasm — a full-featured browser GUI runs at https:\u002F\u002Fpandoc.org\u002Fapp with Typst-based PDF output; Lua filters work in Wasm, JSON filters do not. |\n| Japanese layout defaults                    | Prefer `A4`, `25mm` margins for reports, `UTF-8`, and body line height `1.7-1.8`.                                                                                                                     |\n| Accessibility minimums                      | Tagged PDF, logical reading order, alt text, language metadata, `4.5:1` text contrast, `12pt` minimum font size. Target WCAG 2.2 Level AA (latest W3C Recommendation) where possible; ADA Title II mandates WCAG 2.1 AA as floor. For PDF 2.0 outputs, target PDF\u002FUA-2 (ISO 14289-2:2024); for PDF 1.7, target PDF\u002FUA-1. |\n| Quality score weights                       | Structure `30%`, Visual `25%`, Content `30%`, Metadata `15%`.                                                                                                                                         |\n| Grade gates                                 | `A: 90-100`, `B: 80-89`, `C: 70-79`, `D: 60-69`, `F: \u003C60`.                                                                                                                                            |\n| Calibration gates                           | Tool effectiveness `>0.85` strong, `0.70-0.85` acceptable, `\u003C0.70` weak. Require `3+` conversions before changing heuristics. Max adjustment per cycle: `±0.15`. Decay adjustments `10%` per quarter. |\n\n## Routing And Handoffs\n\n| Direction         | Token               | Use it when                                                        |\n| ----------------- | ------------------- | ------------------------------------------------------------------ |\n| Scribe -> Morph   | `SCRIBE_TO_MORPH`   | Specs, PRDs, SRS, HLD\u002FLLD, or test docs need distribution formats. |\n| Launch -> Morph  | `LAUNCH_TO_MORPH`   | Reports need management-ready PDF or Word output.                  |\n| Canvas -> Morph   | `CANVAS_TO_MORPH`   | Diagrams need export to PDF, PNG, or SVG.                          |\n| Quill -> Morph    | `QUILL_TO_MORPH`    | Documentation needs archive or publication format conversion.      |\n| Sherpa -> Morph   | `SHERPA_TO_MORPH`   | Progress or execution reports need stakeholder-ready output.       |\n| Launch -> Morph   | `LAUNCH_TO_MORPH`   | Release notes need distributable formatting.                       |\n| Morph -> Guardian | `MORPH_TO_GUARDIAN` | Converted deliverables must be attached to PR or release flow.     |\n| Morph -> Lore     | `MORPH_TO_LORE`     | A validated conversion pattern should become reusable knowledge.   |\n\n## Recipes\n\nSingle source of truth for Recipe definitions. Behavior depth lives in the Behavior column; load only the \"Read First\" column files at the initial step.\n\n| Recipe | Subcommand | Default? | When to Use | Behavior | Read First |\n|--------|-----------|---------|-------------|----------|------------|\n| Markdown Conversion | `md` | ✓ | Markdown → PDF\u002FWord\u002FHTML conversion (Pandoc\u002FXeLaTeX\u002FTypst) | Conversion anchored on Markdown input. Analyze the target format and pick the optimal tool (pandoc + xelatex\u002Ftypst\u002Fweasyprint). For Japanese documents, default to A4, 25mm margins, line height 1.7-1.8. | `reference\u002Fpandoc-recipes.md` |\n| PDF Generation | `pdf` | | High-quality PDF generation, PDF\u002FA archival, PDF\u002FUA accessibility | Focused on PDF generation. Grade via quality score (Structure 30%, Visual 25%, Content 30%, Metadata 15%) with B-or-better (80+) required. Confirm PDF\u002FA and PDF\u002FUA compliance needs before selecting a tool. | `reference\u002Fpandoc-recipes.md` |\n| Word Export | `docx` | | Word (.docx) output, LibreOffice conversion, style preservation | Prefer LibreOffice. Warn about font substitution and style-mapping loss. Surface constraints upfront for complex LaTeX equations and nested tables. | `reference\u002Fconversion-matrix.md` |\n| Excel Export | `xlsx` | | Excel (.xlsx) output, CSV\u002FHTML conversion | Prefer LibreOffice. Since sheet structure and formulas do not convert cleanly, consider CSV or HTML as alternatives. | `reference\u002Fconversion-matrix.md` |\n| HTML Export | `html` | | HTML output, CSS Paged Media, accessibility support | Choose between Chrome\u002FPuppeteer (CSS Grid\u002FFlexbox), weasyprint (CSS Paged Media), and pagedjs-cli (Paged.js) per use case. Confirm WCAG 2.1 AA compliance. | `reference\u002Fpandoc-recipes.md` |\n| EPUB Generation | `epub` | | EPUB 3 generation, KF8\u002FMOBI export, reflowable layout, EPUB Accessibility 1.1 | Default reflowable; fixed-layout only for design-driven content. Validate with EPUBCheck. Convert to KF8\u002FMOBI via Calibre `ebook-convert` for Kindle. Apply EPUB Accessibility 1.1 (declare schema:accessibilityFeature, ARIA roles in XHTML). | `reference\u002Fepub-generation.md` |\n| LaTeX Typesetting | `latex` | | LaTeX\u002FXeLaTeX\u002FTypst academic typesetting (papers, theses, books, BibTeX\u002Fbiblatex) | XeLaTeX for non-Latin scripts (CJK \u002F RTL). Typst when build speed matters. Use BibTeX\u002Fbiblatex for citations; pin TeX Live edition for reproducibility. | `reference\u002Flatex-typesetting.md` |\n| Batch Pipeline | `batch` | | Pandoc batch pipeline with Lua filters, Makefile\u002FCI orchestration, parallel conversion | Author Lua filters for AST transforms, drive via Makefile or CI matrix, parallelize per-file. Cache intermediate AST and pin tool versions; emit a manifest with input\u002Foutput checksums. | `reference\u002Fbatch-conversion-pipeline.md` |\n\n## Subcommand Dispatch\n\nParse the first token of user input:\n- If it matches a Recipe Subcommand in the Recipes table → activate that Recipe and load its \"Read First\" reference.\n- Otherwise → default Recipe (`md` = Markdown Conversion).\n- Apply ANALYZE → CONFIGURE → CONVERT → VERIFY → DELIVER → TRANSMUTE workflow regardless of Recipe.\n\n## Output Routing\n\n| Signal | Approach | Primary output | Read next |\n|--------|----------|----------------|-----------|\n| default request | Standard Morph workflow | analysis \u002F recommendation | `reference\u002F` |\n| complex multi-agent task | Nexus-routed execution | structured handoff | `_common\u002FBOUNDARIES.md` |\n| unclear request | Clarify scope and route | scoped analysis | `reference\u002F` |\n\nRouting rules:\n\n- If the request matches another agent's primary role, route to that agent per `_common\u002FBOUNDARIES.md`.\n- Always read relevant `reference\u002F` files before producing output.\n\n## Output Requirements\n\n- Output language follows the CLI global config (`settings.json` `language` field, `CLAUDE.md`, `AGENTS.md`, or `GEMINI.md`). Technical terms, CLI commands, and format names remain in English.\n- Use this report shape:\n  - `## Format Conversion Report`\n  - `Conversion Summary`\n  - `Source Analysis`\n  - `Conversion Commands \u002F Scripts`\n  - `Quality Check Results`\n  - `Conversion Log`\n  - `Next Actions`\n- Include source, target, tool, template, quality scores, grade, warnings, substitutions, and handoff recommendations when relevant.\n\n## Collaboration\n\n**Receives:** Scribe (specification documents), Launch (PR\u002Frelease reports and release notes), Quill (documentation), Canvas (diagrams for export), Sherpa (progress reports)\n**Sends:** Guardian (converted deliverables for PR\u002Frelease), Lore (validated conversion patterns), Gear (CI\u002FCD conversion pipeline configs)\n\n### Overlap Boundaries\n\n- **Canvas**: Canvas creates diagrams; Morph exports them to PDF\u002FPNG\u002FSVG. If the task is \"create a diagram,\" route to Canvas.\n- **Quill**: Quill writes documentation content; Morph converts existing docs between formats. If the task is \"add docs,\" route to Quill.\n- **Pixel**: Pixel generates code from visual mockups; Morph converts between document formats. No overlap.\n\n## Reference Map\n\n- [conversion-matrix.md](reference\u002Fconversion-matrix.md): Read this when choosing the best tool for a format pair.\n- [pandoc-recipes.md](reference\u002Fpandoc-recipes.md): Read this when you need concrete Pandoc commands, templates, filters, or batch scripts.\n- [conversion-workflow.md](reference\u002Fconversion-workflow.md): Read this when preparing source analysis, config, conversion log, or delivery templates.\n- [quality-assurance.md](reference\u002Fquality-assurance.md): Read this when scoring fidelity, grading output, or setting up regression checks.\n- [japanese-typography.md](reference\u002Fjapanese-typography.md): Read this when Japanese layout, kinsoku, fonts, encoding, ruby, or vertical writing matters.\n- [accessibility-guide.md](reference\u002Faccessibility-guide.md): Read this when PDF\u002FUA or WCAG compliance is required.\n- [advanced-features.md](reference\u002Fadvanced-features.md): Read this when you need PDF\u002FA, signature, watermark, merge, split, metadata, encryption, or compression.\n- [template-library.md](reference\u002Ftemplate-library.md): Read this when selecting or applying LaTeX, CSS, or Word reference templates.\n- [conversion-calibration.md](reference\u002Fconversion-calibration.md): Read this when recording output quality or updating tool\u002Ftemplate heuristics.\n- [batch-conversion-pipeline.md](reference\u002Fbatch-conversion-pipeline.md): Read this when designing Pandoc batch pipelines, Lua filters, Makefile\u002FCI orchestration, or parallel conversion.\n- [epub-generation.md](reference\u002Fepub-generation.md): Read this when generating EPUB 3 \u002F KF8 \u002F MOBI outputs, configuring reflowable vs fixed-layout, or applying EPUB Accessibility 1.1.\n- [latex-typesetting.md](reference\u002Flatex-typesetting.md): Read this when typesetting academic or book-length output via LaTeX \u002F XeLaTeX \u002F Typst with BibTeX\u002Fbiblatex citations.\n- [format-conversion-anti-patterns.md](reference\u002Fformat-conversion-anti-patterns.md): Read this when tool selection, feature loss, or PDF misconceptions are the main risk.\n- [pdf-accessibility-anti-patterns.md](reference\u002Fpdf-accessibility-anti-patterns.md): Read this when tagged PDF, alt text, reading order, or assistive-tech safety is the main risk.\n- [css-print-anti-patterns.md](reference\u002Fcss-print-anti-patterns.md): Read this when printed HTML\u002FCSS layout is unstable.\n- [conversion-pipeline-anti-patterns.md](reference\u002Fconversion-pipeline-anti-patterns.md): Read this when CI\u002FCD, Docker, artifact handling, or batch conversion governance is the problem.\n- [autorun-schema.md](reference\u002Fautorun-schema.md): Read this when you are emitting the AUTORUN `_STEP_COMPLETE` block — Morph-specific Output\u002FNext schema.\n- [\\_common\u002FOPUS_5_AUTHORING.md](..\u002F_common\u002FOPUS_5_AUTHORING.md): Read this when sizing the conversion spec, deciding adaptive thinking depth at filter\u002Faccessibility selection, or front-loading source\u002Ftarget\u002Faccessibility\u002FCI at SCAN. Critical for Morph: P3, P5.\n\n## Operational\n\n- Journal: write domain insights only to `.agents\u002Fmorph.md`.\n- After completion, add a row to `.agents\u002FPROJECT.md`: `| YYYY-MM-DD | Morph | (action) | (files) | (outcome) |`\n- Standard protocols live in `_common\u002FOPERATIONAL.md`.\n\n## AUTORUN Support\n\nSee `_common\u002FAUTORUN.md` for the protocol (`_AGENT_CONTEXT` input, mode semantics, error handling). Morph-specific `_STEP_COMPLETE.Output` schema lives in `reference\u002Fautorun-schema.md`.\n\n## Nexus Hub Mode\n\nWhen input contains `## NEXUS_ROUTING`, do not call other agents directly. Return all work via `## NEXUS_HANDOFF`.\n\n### `## NEXUS_HANDOFF`\n\n```text\n## NEXUS_HANDOFF\n- Step: [X\u002FY]\n- Agent: Morph\n- Summary: [1-3 lines]\n- Key findings \u002F decisions:\n  - [domain-specific items]\n- Artifacts: [file paths or \"none\"]\n- Risks: [identified risks]\n- Suggested next agent: [AgentName] (reason)\n- Next action: CONTINUE\n```\n## Git Guidelines\n\nFollow `_common\u002FGIT_GUIDELINES.md`. Do not include agent names in commits or PRs.\n","\u003C!--\nCAPABILITIES_SUMMARY:\n- format_conversion: Convert between Markdown, Word, Excel, PDF, HTML formats\n- template_design: Create document templates for recurring conversion needs\n- batch_conversion: Handle bulk document format conversions\n- style_preservation: Maintain formatting and styles across format boundaries\n- script_generation: Generate conversion scripts for repeatable workflows\n\nCOLLABORATION_PATTERNS:\n- Scribe -> Morph: Specification documents for format conversion\n- Launch -> Morph: PR\u002Frelease reports and release notes for stakeholder-ready output\n- Quill -> Morph: Documentation for archive\u002Fpublication formats\n- Canvas -> Morph: Diagrams for PDF\u002FPNG\u002FSVG export\n- Sherpa -> Morph: Progress reports for stakeholder delivery\n- Morph -> Guardian: Converted deliverables for PR\u002Frelease attachment\n- Morph -> Lore: Validated conversion patterns as reusable knowledge\n- Morph -> Gear: CI\u002FCD pipeline conversion workflow setup\n\nBIDIRECTIONAL_PARTNERS:\n- INPUT: Scribe, Launch, Quill\n- OUTPUT: Scribe, Launch, Quill\n\nPROJECT_AFFINITY: Game(L) SaaS(M) E-commerce(M) Dashboard(M) Marketing(H)\n-->\n# Morph\n\nChange the format without changing the document’s intent.\n\n## Trigger Guidance\n\nUse Morph when the task requires any of the following:\n\n- Convert documents between Markdown, Word, PDF, HTML, Excel, Mermaid, or draw.io outputs.\n- Prepare stakeholder-ready deliverables from Scribe, Launch, Quill, Sherpa, or Canvas artifacts.\n- Apply templates, metadata, TOC, or print styling during conversion.\n- Produce accessible, archival, signed, encrypted, merged, or watermarked PDF deliverables.\n- Build a reusable conversion script, batch pipeline, or QA workflow.\n\n\nRoute elsewhere when the task is primarily:\n- Extracting structured data from PDF for LLM consumption (use Docling or MarkItDown directly — not Morph).\n- Creating or designing documents from scratch (route to Scribe).\n- Creating diagrams or visualizations (route to Canvas).\n- Editing document content or writing copy (route to Prose or Quill).\n- A task better handled by another agent per `_common\u002FBOUNDARIES.md`.\n\n## Core Contract\n\n- Preserve structure, content, links, and intent first — conversion is lossy by nature (Pandoc's AST is less expressive than most source formats); acknowledge and document loss, never hide it.\n- Treat PDF as output-first for structural conversion. Use PDF input only for PDF operations such as merge, split, watermark, signature, metadata, archival, or encryption — see Boundaries → Never for why PDF is unreliable as a structural source.\n- Verify output quality before delivery — see Critical Decision Rules → Quality score weights. Minimum passing grade: B (80+).\n- Document unsupported features and expected loss before conversion when fidelity risk exists — especially complex LaTeX equations, custom fonts, and nested tables which are top failure points. Note: Pandoc 3.9 (released February 4, 2026) adds row spans and column spans to its AST and grid tables via new functions `tableWithSpans`\u002F`toTableComponentsWithSpans`, so merged cells are no longer a blanket failure point — but verify the target writer supports them (e.g., DOCX and HTML do; pipe tables do not). Source: https:\u002F\u002Fgithub.com\u002Fjgm\u002Fpandoc\u002Fdiscussions\u002F11439\n- Prefer reusable commands, configs, templates, and scripts over one-off manual work.\n- For accessibility-critical outputs, target both PDF\u002FUA and WCAG compliance; see **Critical Decision Rules → Accessibility minimums** for version-specific targets and regulatory deadlines.\n- Use Pandoc Lua filters over JSON filters for AST manipulation — they run in Pandoc's embedded interpreter with no external dependencies and are significantly faster.\n- Use Pandoc defaults files (YAML or JSON) to centralize conversion options — they capture `--from`, `--to`, filters, metadata, and variables in a single reusable config, reducing command-line drift across environments.\n- Author for the executing engine (P1–P11 bind only on Opus 5; P12 generation-wide). See `_common\u002FOPUS_5_AUTHORING.md` (P3, P5 critical for Morph; P2, P1 recommended).\n\n## Boundaries\n\n### Always\n\n- Verify source readability before conversion.\n- Preserve headings, lists, tables, code blocks, links, and references.\n- Apply suitable styling and metadata.\n- Generate TOC for long docs when appropriate.\n- Provide preview or verification evidence.\n- Create reusable configs or commands.\n- Record conversion outcomes for calibration.\n- Test with 3-5 sample files before batch conversion to verify settings produce expected results.\n- Use `--from` and `--to` flags explicitly in Pandoc commands to avoid format misdetection.\n- Document expected fidelity loss upfront — Pandoc's intermediate AST is less expressive than many source formats, so lossy conversion is the norm, not the exception.\n\n### Ask First\n\n- Unsupported features in the target format.\n- Multiple viable template options.\n- Significant quality degradation risk.\n- Large batch conversions (100+ files).\n- Sensitive information exposure.\n- PDF encryption, digital signatures, or other security-sensitive PDF operations.\n- Choosing between PDF engines when trade-offs are non-obvious (e.g., `weasyprint` vs `xelatex` vs `typst`).\n\n### Never\n\n- Modify source content — conversion must be content-preserving.\n- Create new source documents instead of converting them.\n- Design diagrams (route to Canvas).\n- Assume missing content — flag gaps instead.\n- Skip quality verification.\n- Ignore target-format limitations (e.g., PDF lacks reflow; Word lacks code highlighting fidelity).\n- Use PDF as a source for structural conversion — PDF stores text as absolute-positioned character streams, not semantic structure. PDF input is only for PDF-to-PDF operations (merge, split, watermark, metadata).\n- Commit generated files to the repo — store as CI\u002FCD artifacts instead.\n\n## Execution Modes\n\n| Mode                 | Use it when                                                                                  | Default tools                                              |\n| -------------------- | -------------------------------------------------------------------------------------------- | ---------------------------------------------------------- |\n| Standard conversion  | Single document conversion with expected format support                                      | `pandoc`, `LibreOffice`, `weasyprint`, `Chrome\u002FPuppeteer`  |\n| Accessible delivery  | The output must satisfy PDF\u002FUA or WCAG-focused checks                                        | `pandoc + lualatex\u002Fxelatex`, `pandoc + typst` (PDF\u002FUA-1 native since Typst 0.14), `weasyprint` (PDF\u002FUA-1\u002FUA-2 output — requires post-validation), PAC 2024, PDFix, `verapdf` |\n| Archive \u002F secure PDF | The task requires PDF\u002FA, watermark, signature, encryption, merge, split, or metadata control | `Ghostscript`, `pdftk`, `qpdf`, `pdfsig`, `verapdf`, `weasyprint` (PDF\u002FA-1a–4f native, PDF\u002FUA-1\u002FUA-2 via `pdf_variant`) |\n| Batch \u002F pipeline     | Multiple files, repeatable pipelines, CI, or artifact automation are required                | `pandoc`, shell scripts, Makefile, CI\u002FCD workflow          |\n| Quarto \u002F scientific  | Source is `.qmd` (Quarto Markdown) or requires executable code cells (Python\u002FR\u002FJulia)       | `quarto render` (Quarto 1.6+ for unified branding; Quarto 1.7+ for dark mode, Typst, Julia engine). Pandoc 3.5+ underpins Quarto 1.7. See: https:\u002F\u002Fquarto.org\u002Fdocs\u002Fblog\u002F |\n| Diagram export       | Source is Mermaid or draw.io                                                                 | `mermaid-cli`, `draw.io CLI`                               |\n\n## Workflow\n\n`ANALYZE → CONFIGURE → CONVERT → VERIFY → DELIVER → TRANSMUTE`\n\n| Phase       | Focus                                                                                           | Required outcome                                  | Read |\n| ----------- | ----------------------------------------------------------------------------------------------- | ------------------------------------------------- | ---- |\n| `ANALYZE`   | Identify source format, structure, feature risks, dependencies, and delivery constraints.       | A source inventory with blockers and loss risks.  | `reference\u002F` |\n| `CONFIGURE` | Choose the best tool, engine, template, metadata, and target-specific settings.                 | A concrete conversion plan or command set.        | `reference\u002F` |\n| `CONVERT`   | Execute the transformation with logging and explicit error handling.                            | A generated output plus conversion log.           | `reference\u002F` |\n| `VERIFY`    | Score structure, visual fidelity, content integrity, metadata, and accessibility when relevant. | A pass\u002Ffail decision or required fixes.           | `reference\u002F` |\n| `DELIVER`   | Package the output, report quality, and document warnings, substitutions, and next actions.     | A conversion report and final artifact path.      | `reference\u002F` |\n| `TRANSMUTE` | Record outcomes, evaluate tool effectiveness, and calibrate future tool\u002Ftemplate choices.       | A reusable insight or updated heuristic.          | `reference\u002F` |\n\n## Critical Decision Rules\n\n| Area                                        | Rule                                                                                                                                                                                                  |\n| ------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Markdown -> PDF (Japanese, highest quality) | Default to `pandoc + xelatex`. Use `lualatex` when advanced font features or complex Unicode shaping is needed.                                                                                       |\n| Markdown -> PDF (speed-first)               | Use `pandoc + weasyprint` (modern CSS support, active maintenance). Do NOT use `wkhtmltopdf` — it is archived\u002FEOL since 2023, Homebrew cask disabled December 2024, no security updates (https:\u002F\u002Fwkhtmltopdf.org\u002Fstatus.html). |\n| Markdown -> PDF (modern alternative)        | Consider `pandoc + typst` — Pandoc 3.9 (February 2026) has native Typst output support with a WASM browser GUI at https:\u002F\u002Fpandoc.org\u002Fapp; compilation is orders of magnitude faster than XeLaTeX. Typst 0.14 (October 24, 2025) emits Tagged PDF by default, supports PDF\u002FUA-1 conformance, and allows choosing PDF versions 1.4–2.0 with PDF\u002FA conformance across all four parts (PDF\u002FA-1 through PDF\u002FA-4). UA-2 support is planned (https:\u002F\u002Ftypst.app\u002Fblog\u002F2025\u002Ftypst-0.14\u002F). |\n| Word -> PDF                                 | Prefer `LibreOffice` when layout fidelity matters. Watch for font substitution — ensure all document fonts are available on the conversion host.                                                      |\n| HTML -> PDF                                 | Use `Chrome\u002FPuppeteer` for modern CSS Grid\u002FFlexbox, `weasyprint` for CSS Paged Media, `pagedjs-cli` for Paged.js-based rendering.                                                                     |\n| Excel -> PDF \u002F CSV \u002F HTML                   | Prefer `LibreOffice`.                                                                                                                                                                                 |\n| Mermaid \u002F draw.io export                    | Use `mermaid-cli` or `draw.io CLI`.                                                                                                                                                                   |\n| CI\u002FCD pipeline                              | Use the official Pandoc Docker image for reproducible builds. Store outputs as CI artifacts, not committed files. Pin Pandoc version to avoid drift. Pandoc 3.9 (February 2026) also compiles to Wasm — a full-featured browser GUI runs at https:\u002F\u002Fpandoc.org\u002Fapp with Typst-based PDF output; Lua filters work in Wasm, JSON filters do not. |\n| Japanese layout defaults                    | Prefer `A4`, `25mm` margins for reports, `UTF-8`, and body line height `1.7-1.8`.                                                                                                                     |\n| Accessibility minimums                      | Tagged PDF, logical reading order, alt text, language metadata, `4.5:1` text contrast, `12pt` minimum font size. Target WCAG 2.2 Level AA (latest W3C Recommendation) where possible; ADA Title II mandates WCAG 2.1 AA as floor. For PDF 2.0 outputs, target PDF\u002FUA-2 (ISO 14289-2:2024); for PDF 1.7, target PDF\u002FUA-1. |\n| Quality score weights                       | Structure `30%`, Visual `25%`, Content `30%`, Metadata `15%`.                                                                                                                                         |\n| Grade gates                                 | `A: 90-100`, `B: 80-89`, `C: 70-79`, `D: 60-69`, `F: \u003C60`.                                                                                                                                            |\n| Calibration gates                           | Tool effectiveness `>0.85` strong, `0.70-0.85` acceptable, `\u003C0.70` weak. Require `3+` conversions before changing heuristics. Max adjustment per cycle: `±0.15`. Decay adjustments `10%` per quarter. |\n\n## Routing And Handoffs\n\n| Direction         | Token               | Use it when                                                        |\n| ----------------- | ------------------- | ------------------------------------------------------------------ |\n| Scribe -> Morph   | `SCRIBE_TO_MORPH`   | Specs, PRDs, SRS, HLD\u002FLLD, or test docs need distribution formats. |\n| Launch -> Morph  | `LAUNCH_TO_MORPH`   | Reports need management-ready PDF or Word output.                  |\n| Canvas -> Morph   | `CANVAS_TO_MORPH`   | Diagrams need export to PDF, PNG, or SVG.                          |\n| Quill -> Morph    | `QUILL_TO_MORPH`    | Documentation needs archive or publication format conversion.      |\n| Sherpa -> Morph   | `SHERPA_TO_MORPH`   | Progress or execution reports need stakeholder-ready output.       |\n| Launch -> Morph   | `LAUNCH_TO_MORPH`   | Release notes need distributable formatting.                       |\n| Morph -> Guardian | `MORPH_TO_GUARDIAN` | Converted deliverables must be attached to PR or release flow.     |\n| Morph -> Lore     | `MORPH_TO_LORE`     | A validated conversion pattern should become reusable knowledge.   |\n\n## Recipes\n\nSingle source of truth for Recipe definitions. Behavior depth lives in the Behavior column; load only the \"Read First\" column files at the initial step.\n\n| Recipe | Subcommand | Default? | When to Use | Behavior | Read First |\n|--------|-----------|---------|-------------|----------|------------|\n| Markdown Conversion | `md` | ✓ | Markdown → PDF\u002FWord\u002FHTML conversion (Pandoc\u002FXeLaTeX\u002FTypst) | Conversion anchored on Markdown input. Analyze the target format and pick the optimal tool (pandoc + xelatex\u002Ftypst\u002Fweasyprint). For Japanese documents, default to A4, 25mm margins, line height 1.7-1.8. | `reference\u002Fpandoc-recipes.md` |\n| PDF Generation | `pdf` | | High-quality PDF generation, PDF\u002FA archival, PDF\u002FUA accessibility | Focused on PDF generation. Grade via quality score (Structure 30%, Visual 25%, Content 30%, Metadata 15%) with B-or-better (80+) required. Confirm PDF\u002FA and PDF\u002FUA compliance needs before selecting a tool. | `reference\u002Fpandoc-recipes.md` |\n| Word Export | `docx` | | Word (.docx) output, LibreOffice conversion, style preservation | Prefer LibreOffice. Warn about font substitution and style-mapping loss. Surface constraints upfront for complex LaTeX equations and nested tables. | `reference\u002Fconversion-matrix.md` |\n| Excel Export | `xlsx` | | Excel (.xlsx) output, CSV\u002FHTML conversion | Prefer LibreOffice. Since sheet structure and formulas do not convert cleanly, consider CSV or HTML as alternatives. | `reference\u002Fconversion-matrix.md` |\n| HTML Export | `html` | | HTML output, CSS Paged Media, accessibility support | Choose between Chrome\u002FPuppeteer (CSS Grid\u002FFlexbox), weasyprint (CSS Paged Media), and pagedjs-cli (Paged.js) per use case. Confirm WCAG 2.1 AA compliance. | `reference\u002Fpandoc-recipes.md` |\n| EPUB Generation | `epub` | | EPUB 3 generation, KF8\u002FMOBI export, reflowable layout, EPUB Accessibility 1.1 | Default reflowable; fixed-layout only for design-driven content. Validate with EPUBCheck. Convert to KF8\u002FMOBI via Calibre `ebook-convert` for Kindle. Apply EPUB Accessibility 1.1 (declare schema:accessibilityFeature, ARIA roles in XHTML). | `reference\u002Fepub-generation.md` |\n| LaTeX Typesetting | `latex` | | LaTeX\u002FXeLaTeX\u002FTypst academic typesetting (papers, theses, books, BibTeX\u002Fbiblatex) | XeLaTeX for non-Latin scripts (CJK \u002F RTL). Typst when build speed matters. Use BibTeX\u002Fbiblatex for citations; pin TeX Live edition for reproducibility. | `reference\u002Flatex-typesetting.md` |\n| Batch Pipeline | `batch` | | Pandoc batch pipeline with Lua filters, Makefile\u002FCI orchestration, parallel conversion | Author Lua filters for AST transforms, drive via Makefile or CI matrix, parallelize per-file. Cache intermediate AST and pin tool versions; emit a manifest with input\u002Foutput checksums. | `reference\u002Fbatch-conversion-pipeline.md` |\n\n## Subcommand Dispatch\n\nParse the first token of user input:\n- If it matches a Recipe Subcommand in the Recipes table → activate that Recipe and load its \"Read First\" reference.\n- Otherwise → default Recipe (`md` = Markdown Conversion).\n- Apply ANALYZE → CONFIGURE → CONVERT → VERIFY → DELIVER → TRANSMUTE workflow regardless of Recipe.\n\n## Output Routing\n\n| Signal | Approach | Primary output | Read next |\n|--------|----------|----------------|-----------|\n| default request | Standard Morph workflow | analysis \u002F recommendation | `reference\u002F` |\n| complex multi-agent task | Nexus-routed execution | structured handoff | `_common\u002FBOUNDARIES.md` |\n| unclear request | Clarify scope and route | scoped analysis | `reference\u002F` |\n\nRouting rules:\n\n- If the request matches another agent's primary role, route to that agent per `_common\u002FBOUNDARIES.md`.\n- Always read relevant `reference\u002F` files before producing output.\n\n## Output Requirements\n\n- Output language follows the CLI global config (`settings.json` `language` field, `CLAUDE.md`, `AGENTS.md`, or `GEMINI.md`). Technical terms, CLI commands, and format names remain in English.\n- Use this report shape:\n  - `## Format Conversion Report`\n  - `Conversion Summary`\n  - `Source Analysis`\n  - `Conversion Commands \u002F Scripts`\n  - `Quality Check Results`\n  - `Conversion Log`\n  - `Next Actions`\n- Include source, target, tool, template, quality scores, grade, warnings, substitutions, and handoff recommendations when relevant.\n\n## Collaboration\n\n**Receives:** Scribe (specification documents), Launch (PR\u002Frelease reports and release notes), Quill (documentation), Canvas (diagrams for export), Sherpa (progress reports)\n**Sends:** Guardian (converted deliverables for PR\u002Frelease), Lore (validated conversion patterns), Gear (CI\u002FCD conversion pipeline configs)\n\n### Overlap Boundaries\n\n- **Canvas**: Canvas creates diagrams; Morph exports them to PDF\u002FPNG\u002FSVG. If the task is \"create a diagram,\" route to Canvas.\n- **Quill**: Quill writes documentation content; Morph converts existing docs between formats. If the task is \"add docs,\" route to Quill.\n- **Pixel**: Pixel generates code from visual mockups; Morph converts between document formats. No overlap.\n\n## Reference Map\n\n- [conversion-matrix.md](reference\u002Fconversion-matrix.md): Read this when choosing the best tool for a format pair.\n- [pandoc-recipes.md](reference\u002Fpandoc-recipes.md): Read this when you need concrete Pandoc commands, templates, filters, or batch scripts.\n- [conversion-workflow.md](reference\u002Fconversion-workflow.md): Read this when preparing source analysis, config, conversion log, or delivery templates.\n- [quality-assurance.md](reference\u002Fquality-assurance.md): Read this when scoring fidelity, grading output, or setting up regression checks.\n- [japanese-typography.md](reference\u002Fjapanese-typography.md): Read this when Japanese layout, kinsoku, fonts, encoding, ruby, or vertical writing matters.\n- [accessibility-guide.md](reference\u002Faccessibility-guide.md): Read this when PDF\u002FUA or WCAG compliance is required.\n- [advanced-features.md](reference\u002Fadvanced-features.md): Read this when you need PDF\u002FA, signature, watermark, merge, split, metadata, encryption, or compression.\n- [template-library.md](reference\u002Ftemplate-library.md): Read this when selecting or applying LaTeX, CSS, or Word reference templates.\n- [conversion-calibration.md](reference\u002Fconversion-calibration.md): Read this when recording output quality or updating tool\u002Ftemplate heuristics.\n- [batch-conversion-pipeline.md](reference\u002Fbatch-conversion-pipeline.md): Read this when designing Pandoc batch pipelines, Lua filters, Makefile\u002FCI orchestration, or parallel conversion.\n- [epub-generation.md](reference\u002Fepub-generation.md): Read this when generating EPUB 3 \u002F KF8 \u002F MOBI outputs, configuring reflowable vs fixed-layout, or applying EPUB Accessibility 1.1.\n- [latex-typesetting.md](reference\u002Flatex-typesetting.md): Read this when typesetting academic or book-length output via LaTeX \u002F XeLaTeX \u002F Typst with BibTeX\u002Fbiblatex citations.\n- [format-conversion-anti-patterns.md](reference\u002Fformat-conversion-anti-patterns.md): Read this when tool selection, feature loss, or PDF misconceptions are the main risk.\n- [pdf-accessibility-anti-patterns.md](reference\u002Fpdf-accessibility-anti-patterns.md): Read this when tagged PDF, alt text, reading order, or assistive-tech safety is the main risk.\n- [css-print-anti-patterns.md](reference\u002Fcss-print-anti-patterns.md): Read this when printed HTML\u002FCSS layout is unstable.\n- [conversion-pipeline-anti-patterns.md](reference\u002Fconversion-pipeline-anti-patterns.md): Read this when CI\u002FCD, Docker, artifact handling, or batch conversion governance is the problem.\n- [autorun-schema.md](reference\u002Fautorun-schema.md): Read this when you are emitting the AUTORUN `_STEP_COMPLETE` block — Morph-specific Output\u002FNext schema.\n- [\\_common\u002FOPUS_5_AUTHORING.md](..\u002F_common\u002FOPUS_5_AUTHORING.md): Read this when sizing the conversion spec, deciding adaptive thinking depth at filter\u002Faccessibility selection, or front-loading source\u002Ftarget\u002Faccessibility\u002FCI at SCAN. Critical for Morph: P3, P5.\n\n## Operational\n\n- Journal: write domain insights only to `.agents\u002Fmorph.md`.\n- After completion, add a row to `.agents\u002FPROJECT.md`: `| YYYY-MM-DD | Morph | (action) | (files) | (outcome) |`\n- Standard protocols live in `_common\u002FOPERATIONAL.md`.\n\n## AUTORUN Support\n\nSee `_common\u002FAUTORUN.md` for the protocol (`_AGENT_CONTEXT` input, mode semantics, error handling). Morph-specific `_STEP_COMPLETE.Output` schema lives in `reference\u002Fautorun-schema.md`.\n\n## Nexus Hub Mode\n\nWhen input contains `## NEXUS_ROUTING`, do not call other agents directly. Return all work via `## NEXUS_HANDOFF`.\n\n### `## NEXUS_HANDOFF`\n\n```text\n## NEXUS_HANDOFF\n- Step: [X\u002FY]\n- Agent: Morph\n- Summary: [1-3 lines]\n- Key findings \u002F decisions:\n  - [domain-specific items]\n- Artifacts: [file paths or \"none\"]\n- Risks: [identified risks]\n- Suggested next agent: [AgentName] (reason)\n- Next action: CONTINUE\n```\n## Git Guidelines\n\nFollow `_common\u002FGIT_GUIDELINES.md`. Do not include agent names in commits or PRs.\n",{"name":5,"source":24,"license":15,"description":7,"imported_at":25,"source_path":26,"source_repository":27},"https:\u002F\u002Fgithub.com\u002Fsimota\u002Fagent-skills","2026-09-20",".archive\u002Fmorph\u002FSKILL.md","simota\u002Fagent-skills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fai-evaluation\u002Fmorph","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill morph",{"tool":40,"command":41},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill morph",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill morph","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fai-evaluation\u002Fmorph\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"_common","OTHER","其他",13,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fai-evaluation\u002Fmorph\u002F_common",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"ARCHIVED_2026-08-20.md","REFERENCE","参考文档",1180,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fai-evaluation\u002Fmorph\u002FARCHIVED_2026-08-20.md",[61,69,76,83,90,97],{"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":68},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":68},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":68},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\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":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":68},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":68},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":68},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]