[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F2RT5KP5N9JC73ZSS1XZFS":3,"skill-same:01M7F2RT5KP5N9JC73ZSS1XZFS":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":12,"updatedAt":31,"install":32,"resources":45},"01M7F2RT5KP5N9JC73ZSS1XZFS","source-command-audit-whitepapers",null,"Audit version freshness, FR\u002FEN parity, and metadata quality of all whitepapers and recap cards","313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","313DEVGRP","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34762848?v=4","01M7F2M535Z5X8XGHYD8TDVAB3","A-RMS by 313DEVGRP","01M7F2M54CR0P3631F4YM0D014",0,"MIT","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002F.agents\u002Fskills\u002Fsource-command-audit-whitepapers\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: \"source-command-audit-whitepapers\"\ndescription: \"Audit version freshness, FR\u002FEN parity, and metadata quality of all whitepapers and recap cards\"\n---\n\n# source-command-audit-whitepapers\n\nUse this skill when the user asks to run the migrated source command `audit-whitepapers`.\n\n## Command Template\n\n# Audit Whitepapers & Recap Cards\n\nComprehensive freshness and quality audit for all whitepapers (FR + EN) and recap cards (FR + EN). Scores each document against the current guide version, checks FR\u002FEN parity, and validates metadata consistency.\n\n## Arguments\n\n- `--fix` - Generate update suggestions and frontmatter patches (does not modify files)\n- `--verbose` - Show all criteria including passing ones, not just failures\n- `--cards-only` - Audit only recap cards (skip main whitepapers)\n- `--wp-only` - Audit only main whitepapers (skip recap cards)\n\n## Usage\n\n```bash\n\u002Faudit-whitepapers                  # Full audit, failures only\n\u002Faudit-whitepapers --fix            # Audit + prioritized update suggestions\n\u002Faudit-whitepapers --verbose        # Full details for all criteria\n\u002Faudit-whitepapers --cards-only     # Recap cards only\n\u002Faudit-whitepapers --wp-only        # Whitepapers only\n```\n\n---\n\n## Phase 1: Discovery\n\n**Objective**: Locate and inventory all auditable documents.\n\n### Steps\n\n1. **Read current guide version**: Read the `VERSION` file at the project root. This is the target version all documents should be synced against.\n\n2. **Scan directories** for `.qmd` files:\n   ```\n   whitepapers\u002Ffr\u002F         (main whitepapers FR)\n   whitepapers\u002Fen\u002F         (main whitepapers EN)\n   whitepapers\u002Frecap-cards\u002Ffr\u002F    (recap cards FR)\n   whitepapers\u002Frecap-cards\u002Fen\u002F    (recap cards EN)\n   ```\n\n3. **Classify each file**:\n   - **Main whitepaper**: files matching `[0-9][0-9]-*.qmd` in `whitepapers\u002Ffr\u002F` or `whitepapers\u002Fen\u002F`\n   - **Cheatsheet**: files matching `*cheatsheet*.qmd` (tracked separately, not scored)\n   - **Custom whitepaper**: files matching `*-whitepaper.qmd` or `*-cheatsheet.qmd` from external partners (strangebee, purchasely, devwithai) -- excluded from scoring, listed separately\n   - **Recap card**: all `.qmd` files in `recap-cards\u002Ffr\u002F` or `recap-cards\u002Fen\u002F`\n   - **Bundle\u002Finclude**: `fiches-recap-serie.qmd`, files in `fiches\u002F` subdirectory -- excluded (they are composed documents)\n\n4. **Parse YAML frontmatter** for each included file (read between first `---` and second `---`). Extract:\n   - `title`, `subtitle`, `author`, `date`\n   - `version` (guide version tracked in main WPs and recap cards)\n   - `wp-version` (whitepaper own semver, main WPs only)\n   - `guide-version` (explicit guide version field used in recap cards)\n   - `card-number`, `category`, `difficulty` (recap cards only)\n   - `series` (main WPs only)\n\n5. **Display discovery summary**:\n   ```\n   Guide version: {VERSION}\n   Found: {N} main whitepapers ({FR}\u002F{EN} FR\u002FEN), {N} recap cards ({FR}\u002F{EN} FR\u002FEN)\n   Excluded: {N} custom files (strangebee, purchasely, devwithai), {N} bundle files\n   ```\n\n---\n\n## Phase 2: Version Gap Analysis (40 points per file)\n\n**Objective**: Score how current each document is relative to the guide.\n\n### Semver comparison logic\n\nParse version strings as `MAJOR.MINOR.PATCH`. The staleness metric is `minor_gap = current_minor - file_minor` (using the same MAJOR). If MAJOR differs, treat as critical.\n\nFor **main whitepapers**, the guide version field is `version`.\nFor **recap cards**, the guide version field is `guide-version` (fall back to `version` if absent).\n\n### Scoring table\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| Guide version current (0-1 minor behind) | 15 | `minor_gap` \u003C= 1 |\n| Guide version recent (2-3 minor behind) | 10 | `minor_gap` 2-3 (partial credit, replaces the 15) |\n| Guide version old (4-10 minor behind) | 5 | `minor_gap` 4-10 (partial credit) |\n| wp-version field present and valid semver | 5 | Field exists AND matches `\\d+\\.\\d+\\.\\d+` (WP only) |\n| wp-version consistent with FR\u002FEN pair | 10 | Same `wp-version` value in the counterpart file (WP only) |\n| guide-version consistent with FR\u002FEN pair | 10 | Same `guide-version` (or `version`) in the counterpart (cards) |\n\n**Freshness labels**:\n- 0-1 minor behind: Fresh\n- 2-3 minor behind: Stale\n- 4-10 minor behind: Very Stale\n- 11+ minor behind: Critical\n\nNote: The 15, 10, 5 pts for guide version are mutually exclusive (award only the highest applicable tier).\n\n---\n\n## Phase 3: Content Staleness Check (20 points per file)\n\n**Objective**: Detect whether the guide sections a whitepaper covers have changed since it was last updated.\n\n### Whitepaper-to-guide mapping (embedded)\n\n| WP# | FR filename prefix | EN filename prefix | Guide sections |\n|-----|--------------------|--------------------|----------------|\n| 00 | `00-introduction` | `00-series-introduction` | `guide\u002Fultimate-guide.md` Ch.1-2 |\n| 01 | `01-prompts` | `01-effective-prompts` | Ch.2 prompting sections |\n| 02 | `02-personnalisation` | `02-customization` | Ch.3 Memory, Ch.4 Agents, Ch.5 Skills |\n| 03 | `03-securite` | `03-security` | Ch.7 Hooks, security sections |\n| 04 | `04-architecture` | `04-architecture` | Ch.2 internals, architecture sections |\n| 05 | `05-equipe` | `05-team` | Ch.3 team config, Ch.9 CI\u002FCD |\n| 06 | `06-privacy` | `06-privacy` | Ch.2 data\u002Fprivacy sections |\n| 07 | `07-guide-reference` | `07-reference-guide` | Ch.10 Reference |\n| 08 | `08-agent-teams` | `08-agent-teams` | Ch.9 agent teams |\n| 09 | `09-apprendre` | `09-learning` | `guide\u002Froles\u002Flearning-with-ai.md` |\n| 10 | `10-budget` | `10-ai-budget` | Business\u002FROI content |\n\n### Steps\n\n1. For each main whitepaper, extract the `date` field. If the date is not in `YYYY-MM-DD` format, parse it (e.g., \"2026-02-12\" or \"March 2026\").\n2. Run `git log --since=\"{date}\" --oneline -- guide\u002Fultimate-guide.md guide\u002Froles\u002F guide\u002Fcore\u002F` to count commits that touched guide content since the whitepaper's date.\n3. Score:\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| No guide commits since wp date | 10 | `git log` returns 0 commits |\n| Few commits since wp date (1-5) | 7 | 1-5 commits (partial) |\n| Moderate commits (6-15) | 4 | 6-15 commits (partial) |\n| Many commits (>15) | 0 | More than 15 commits |\n| Mapping defined for this WP | 5 | WP number is in the mapping table above |\n| Git history accessible | 5 | `git log` command executes without error |\n\n**Recap cards**: Skip detailed git analysis. Award a flat staleness score based on `minor_gap`:\n- 0-1 behind: 20 pts\n- 2-3 behind: 15 pts\n- 4-10 behind: 8 pts\n- 11+ behind: 0 pts\n\n---\n\n## Phase 4: FR\u002FEN Parity Check (20 points per file)\n\n**Objective**: Every document should have a complete, version-consistent counterpart in the other language.\n\n### Pairing strategy\n\n**Main whitepapers**: Match on the two-digit numeric prefix (e.g., `00`, `03`, `10`). FR and EN filenames differ but the prefix is consistent.\n\n**Recap cards**: Match on identical filename (both language directories use the same filenames).\n\n### Scoring table\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| Counterpart file exists in other language | 10 | File with matching prefix (WP) or identical name (cards) found |\n| wp-version matches between pairs | 5 | Same `wp-version` value (WP only) |\n| guide version matches between pairs | 5 | Same `version`\u002F`guide-version` value |\n\nScore both the FR and EN files of a pair identically on parity (if the pair is complete, both get 20; if one is missing, the existing file scores 0 on parity).\n\n---\n\n## Phase 5: Metadata Quality (20 points per file)\n\n**Objective**: Validate frontmatter completeness, field formats, and consistency across files of the same type.\n\n### Main whitepapers (20 points max)\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| Required fields present | 6 | Has all of: `title`, `subtitle`, `author`, `date`, `version`, `wp-version`, `series` |\n| `version` follows semver pattern | 3 | Matches `\\d+\\.\\d+\\.\\d+` |\n| `wp-version` follows semver pattern | 3 | Matches `\\d+\\.\\d+\\.\\d+` |\n| `date` is parseable and not in the future | 3 | Valid date, not after today |\n| `series` value is consistent | 2 | Equals \"Codex Ultimate Guide\" |\n| No missing `wp-version` (not left empty or absent) | 3 | Field has a non-empty value |\n\n### Recap cards (20 points max)\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| Required fields present | 5 | Has all of: `title`, `subtitle`, `card-number`, `category`, `difficulty`, `guide-version`, `author`, `version`, `date` |\n| `card-number` matches filename prefix | 4 | e.g., `C01` in `card-number` matches `c01-` in filename |\n| `category` valid for language | 4 | FR: one of \"Technique\", \"Methodologie\", \"Conception\"; EN: one of \"Technical\", \"Methodology\", \"Design\" (flag \"Conceptual\" as inconsistent in EN) |\n| `difficulty` is valid value | 3 | One of: \"beginner\", \"intermediate\", \"advanced\" |\n| `guide-version` and `version` fields match each other | 4 | Both fields exist and have the same value within the same file |\n\n**Known issue to detect automatically**: EN C-series cards use two different category values (\"Conceptual\" on c01-c05, \"Design\" on c06+). Flag this inconsistency explicitly in the Metadata Issues section of the report.\n\n---\n\n## Phase 6: Scoring and Grading\n\n### Score formula (per file)\n\n```\nTotal = Version Gap (40) + Content Staleness (20) + FR\u002FEN Parity (20) + Metadata Quality (20)\nScore = (Total \u002F 100) * 100  [as a percentage]\n```\n\n### Grade scale\n\n| Grade | Score | Status |\n|-------|-------|--------|\n| A | 90-100 | Fresh, fully synced |\n| B | 80-89 | Good (production threshold) |\n| C | 70-79 | Needs update soon |\n| D | 60-69 | Stale, should prioritize |\n| F | \u003C60 | Critical: likely outdated content |\n\n### Overall health score\n\n```\nWeighted Health = (Sum of WP scores * 2 + Sum of card scores * 1) \u002F (WP count * 2 + card count * 1)\n```\n\nWhitepapers are weighted 2x because they are 20-80 pages each vs. 2-page recap cards. A stale whitepaper carries more risk.\n\n---\n\n## Phase 7: Report\n\nOutput the following Markdown report. Use `\u003Cdetails>` blocks for individual file breakdowns to keep the top level scannable.\n\n```markdown\n# Whitepaper & Recap Card Audit\n\n**Date**: {today}\n**Guide Version**: {VERSION}\n**Overall Health**: {score}% ({grade})\n**Files Audited**: {total} ({wp_count} whitepapers, {card_count} recap cards)\n\n---\n\n## Version Status Dashboard\n\n| Status | Whitepapers | Recap Cards | Total |\n|--------|-------------|-------------|-------|\n| Fresh (0-1 minor behind)   | N | N | N |\n| Stale (2-3 minor behind)   | N | N | N |\n| Very Stale (4-10 behind)   | N | N | N |\n| Critical (11+ behind)      | N | N | N |\n\n**Versions currently in use**:\n- Main WP 00-09: {version} ({gap} minor versions behind)\n- Main WP 10: {version} ({gap} minor versions behind)\n- Recap cards: {guide-version} ({gap} minor versions behind)\n\n---\n\n## Whitepaper Scores\n\n| WP# | Title | version | Gap | wp-version | Parity | Score | Grade |\n|-----|-------|---------|-----|------------|--------|-------|-------|\n| 00  | ...   | ...     | -N  | ...        | OK\u002Fgap | N%    | X     |\n...\n\n\u003Cdetails>\n\u003Csummary>Individual criteria breakdown (WP 00)\u003C\u002Fsummary>\n\n| Phase | Criterion | Result | Points |\n|-------|-----------|--------|--------|\n| Version Gap | Guide version current | Critical (-11) | 0\u002F15 |\n| Version Gap | wp-version valid semver | OK | 5\u002F5 |\n| ... | ... | ... | ... |\n| **Total** | | | **N\u002F100** |\n\u003C\u002Fdetails>\n\n---\n\n## Recap Card Scores\n\n| Series | Cards | Avg guide-version | Avg Gap | Avg Score | Grade |\n|--------|-------|-------------------|---------|-----------|-------|\n| T (Technical)    | 22 | ... | -N | N% | X |\n| M (Methodology)  | 22 | ... | -N | N% | X |\n| C (Conceptual)   | 13 | ... | -N | N% | X |\n\n\u003Cdetails>\n\u003Csummary>Individual card scores\u003C\u002Fsummary>\n\n| Card | Category | guide-version | Gap | Parity | Metadata | Score | Grade |\n|------|----------|---------------|-----|--------|----------|-------|-------|\n...\n\u003C\u002Fdetails>\n\n---\n\n## FR\u002FEN Parity Report\n\n### Whitepapers\n| WP# | FR | EN | wp-version Match | version Match |\n|-----|----|----|------------------|---------------|\n...\n\n### Recap Cards\n- **FR count**: {N} | **EN count**: {N}\n- **Missing FR**: [list or \"None\"]\n- **Missing EN**: [list or \"None\"]\n- **Version mismatches**: [list or \"None\"]\n\n---\n\n## Metadata Issues\n\n### Known: EN Recap Card Category Inconsistency\nEN C-series cards use two different values for the \"Conceptual\u002FDesign\" category:\n- \"Conceptual\": c01, c02, c03, c04, c05\n- \"Design\": c06, c07, c08, ...\nRecommendation: standardize to \"Design\" to match guide terminology.\nAffected files: whitepapers\u002Frecap-cards\u002Fen\u002Fc01-*.qmd through c05-*.qmd (change \"Conceptual\" to \"Design\")\n\n### Other issues\n[List any missing fields, bad formats, date issues...]\n\n---\n\n## Prioritized Action Items\n\n### Critical (Grade F, 11+ versions behind)\n[List specific whitepapers with filename paths]\n\n### High (Grade D-F, 2+ versions behind)\n[List specific files]\n\n### Medium (Metadata quality, category fixes)\n[List specific issues]\n\n### Low (Polish, date alignment)\n[List specific issues]\n\n---\n\n## Next Steps\n\n1. Run `\u002Fupdate-whitepapers --since {oldest_version}` to update all stale WPs\n2. Fix EN category inconsistency (5 files: c01 through c05, change \"Conceptual\" to \"Design\")\n3. Re-run `\u002Faudit-whitepapers` after updates to track progress\n4. Target: 80%+ health (Grade B) across all files\n```\n\n---\n\n## Fix Mode (`--fix`)\n\nWhen `--fix` is passed, append a **Fix Suggestions** section after the report. This section provides concrete patches but does NOT modify any files.\n\n### Frontmatter version patches\n\nFor each file with a stale guide version, output:\n```yaml\n# File: whitepapers\u002Ffr\u002F00-introduction-serie.qmd\n# Change:\nversion: \"3.27.6\"  ->  version: \"{current_VERSION}\"\ndate: 2026-02-12   ->  date: {today}\n```\n\n### Category fix patches (EN recap cards)\n\n```\nFiles to update (category: \"Conceptual\" -> \"Design\"):\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc01-trust-calibration.qmd\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc02-*.qmd\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc03-*.qmd\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc04-*.qmd\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc05-*.qmd\n```\n\n### Update command checklist\n\nBased on the stale WPs detected, output the `\u002Fupdate-whitepapers` commands to run in order:\n```\nSuggested update sequence:\n1. \u002Fupdate-whitepapers --since {oldest_stale_version} --wp 00,01,02,03,04,05,06,07,08,09\n2. \u002Fupdate-whitepapers --since {oldest_stale_version} --wp 10\n3. Review and bump wp-version for each updated WP (patch = content corrections, minor = new sections)\n4. Bump guide-version in all recap cards to {current_VERSION}\n5. Re-run \u002Faudit-whitepapers to verify\n```\n\n---\n\n## Verbose Mode (`--verbose`)\n\nWhen `--verbose` is passed, expand all `\u003Cdetails>` blocks by default and show the complete per-file criteria table (all criteria, not just failures) for every audited file.\n\n---\n\n## Exclusions Reference\n\nThe following files are excluded from scoring (listed in discovery summary only):\n\n| Pattern | Reason |\n|---------|--------|\n| `strangebee-*.qmd`, `purchasely-*.qmd`, `devwithai-*.qmd` | Client\u002Fpartner custom files, separate lifecycle |\n| `fiches-recap-serie.qmd`, `fiches\u002F*.qmd` | Bundle\u002Finclude files, no independent versioning |\n| `*_quarto.yml`, `references.bib` | Build config, not content |\n| `cheatsheet.qmd` | Listed separately in discovery, not scored in main audit |\n","# source-command-audit-whitepapers\n\nUse this skill when the user asks to run the migrated source command `audit-whitepapers`.\n\n## Command Template\n\n# Audit Whitepapers & Recap Cards\n\nComprehensive freshness and quality audit for all whitepapers (FR + EN) and recap cards (FR + EN). Scores each document against the current guide version, checks FR\u002FEN parity, and validates metadata consistency.\n\n## Arguments\n\n- `--fix` - Generate update suggestions and frontmatter patches (does not modify files)\n- `--verbose` - Show all criteria including passing ones, not just failures\n- `--cards-only` - Audit only recap cards (skip main whitepapers)\n- `--wp-only` - Audit only main whitepapers (skip recap cards)\n\n## Usage\n\n```bash\n\u002Faudit-whitepapers                  # Full audit, failures only\n\u002Faudit-whitepapers --fix            # Audit + prioritized update suggestions\n\u002Faudit-whitepapers --verbose        # Full details for all criteria\n\u002Faudit-whitepapers --cards-only     # Recap cards only\n\u002Faudit-whitepapers --wp-only        # Whitepapers only\n```\n\n---\n\n## Phase 1: Discovery\n\n**Objective**: Locate and inventory all auditable documents.\n\n### Steps\n\n1. **Read current guide version**: Read the `VERSION` file at the project root. This is the target version all documents should be synced against.\n\n2. **Scan directories** for `.qmd` files:\n   ```\n   whitepapers\u002Ffr\u002F         (main whitepapers FR)\n   whitepapers\u002Fen\u002F         (main whitepapers EN)\n   whitepapers\u002Frecap-cards\u002Ffr\u002F    (recap cards FR)\n   whitepapers\u002Frecap-cards\u002Fen\u002F    (recap cards EN)\n   ```\n\n3. **Classify each file**:\n   - **Main whitepaper**: files matching `[0-9][0-9]-*.qmd` in `whitepapers\u002Ffr\u002F` or `whitepapers\u002Fen\u002F`\n   - **Cheatsheet**: files matching `*cheatsheet*.qmd` (tracked separately, not scored)\n   - **Custom whitepaper**: files matching `*-whitepaper.qmd` or `*-cheatsheet.qmd` from external partners (strangebee, purchasely, devwithai) -- excluded from scoring, listed separately\n   - **Recap card**: all `.qmd` files in `recap-cards\u002Ffr\u002F` or `recap-cards\u002Fen\u002F`\n   - **Bundle\u002Finclude**: `fiches-recap-serie.qmd`, files in `fiches\u002F` subdirectory -- excluded (they are composed documents)\n\n4. **Parse YAML frontmatter** for each included file (read between first `---` and second `---`). Extract:\n   - `title`, `subtitle`, `author`, `date`\n   - `version` (guide version tracked in main WPs and recap cards)\n   - `wp-version` (whitepaper own semver, main WPs only)\n   - `guide-version` (explicit guide version field used in recap cards)\n   - `card-number`, `category`, `difficulty` (recap cards only)\n   - `series` (main WPs only)\n\n5. **Display discovery summary**:\n   ```\n   Guide version: {VERSION}\n   Found: {N} main whitepapers ({FR}\u002F{EN} FR\u002FEN), {N} recap cards ({FR}\u002F{EN} FR\u002FEN)\n   Excluded: {N} custom files (strangebee, purchasely, devwithai), {N} bundle files\n   ```\n\n---\n\n## Phase 2: Version Gap Analysis (40 points per file)\n\n**Objective**: Score how current each document is relative to the guide.\n\n### Semver comparison logic\n\nParse version strings as `MAJOR.MINOR.PATCH`. The staleness metric is `minor_gap = current_minor - file_minor` (using the same MAJOR). If MAJOR differs, treat as critical.\n\nFor **main whitepapers**, the guide version field is `version`.\nFor **recap cards**, the guide version field is `guide-version` (fall back to `version` if absent).\n\n### Scoring table\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| Guide version current (0-1 minor behind) | 15 | `minor_gap` \u003C= 1 |\n| Guide version recent (2-3 minor behind) | 10 | `minor_gap` 2-3 (partial credit, replaces the 15) |\n| Guide version old (4-10 minor behind) | 5 | `minor_gap` 4-10 (partial credit) |\n| wp-version field present and valid semver | 5 | Field exists AND matches `\\d+\\.\\d+\\.\\d+` (WP only) |\n| wp-version consistent with FR\u002FEN pair | 10 | Same `wp-version` value in the counterpart file (WP only) |\n| guide-version consistent with FR\u002FEN pair | 10 | Same `guide-version` (or `version`) in the counterpart (cards) |\n\n**Freshness labels**:\n- 0-1 minor behind: Fresh\n- 2-3 minor behind: Stale\n- 4-10 minor behind: Very Stale\n- 11+ minor behind: Critical\n\nNote: The 15, 10, 5 pts for guide version are mutually exclusive (award only the highest applicable tier).\n\n---\n\n## Phase 3: Content Staleness Check (20 points per file)\n\n**Objective**: Detect whether the guide sections a whitepaper covers have changed since it was last updated.\n\n### Whitepaper-to-guide mapping (embedded)\n\n| WP# | FR filename prefix | EN filename prefix | Guide sections |\n|-----|--------------------|--------------------|----------------|\n| 00 | `00-introduction` | `00-series-introduction` | `guide\u002Fultimate-guide.md` Ch.1-2 |\n| 01 | `01-prompts` | `01-effective-prompts` | Ch.2 prompting sections |\n| 02 | `02-personnalisation` | `02-customization` | Ch.3 Memory, Ch.4 Agents, Ch.5 Skills |\n| 03 | `03-securite` | `03-security` | Ch.7 Hooks, security sections |\n| 04 | `04-architecture` | `04-architecture` | Ch.2 internals, architecture sections |\n| 05 | `05-equipe` | `05-team` | Ch.3 team config, Ch.9 CI\u002FCD |\n| 06 | `06-privacy` | `06-privacy` | Ch.2 data\u002Fprivacy sections |\n| 07 | `07-guide-reference` | `07-reference-guide` | Ch.10 Reference |\n| 08 | `08-agent-teams` | `08-agent-teams` | Ch.9 agent teams |\n| 09 | `09-apprendre` | `09-learning` | `guide\u002Froles\u002Flearning-with-ai.md` |\n| 10 | `10-budget` | `10-ai-budget` | Business\u002FROI content |\n\n### Steps\n\n1. For each main whitepaper, extract the `date` field. If the date is not in `YYYY-MM-DD` format, parse it (e.g., \"2026-02-12\" or \"March 2026\").\n2. Run `git log --since=\"{date}\" --oneline -- guide\u002Fultimate-guide.md guide\u002Froles\u002F guide\u002Fcore\u002F` to count commits that touched guide content since the whitepaper's date.\n3. Score:\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| No guide commits since wp date | 10 | `git log` returns 0 commits |\n| Few commits since wp date (1-5) | 7 | 1-5 commits (partial) |\n| Moderate commits (6-15) | 4 | 6-15 commits (partial) |\n| Many commits (>15) | 0 | More than 15 commits |\n| Mapping defined for this WP | 5 | WP number is in the mapping table above |\n| Git history accessible | 5 | `git log` command executes without error |\n\n**Recap cards**: Skip detailed git analysis. Award a flat staleness score based on `minor_gap`:\n- 0-1 behind: 20 pts\n- 2-3 behind: 15 pts\n- 4-10 behind: 8 pts\n- 11+ behind: 0 pts\n\n---\n\n## Phase 4: FR\u002FEN Parity Check (20 points per file)\n\n**Objective**: Every document should have a complete, version-consistent counterpart in the other language.\n\n### Pairing strategy\n\n**Main whitepapers**: Match on the two-digit numeric prefix (e.g., `00`, `03`, `10`). FR and EN filenames differ but the prefix is consistent.\n\n**Recap cards**: Match on identical filename (both language directories use the same filenames).\n\n### Scoring table\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| Counterpart file exists in other language | 10 | File with matching prefix (WP) or identical name (cards) found |\n| wp-version matches between pairs | 5 | Same `wp-version` value (WP only) |\n| guide version matches between pairs | 5 | Same `version`\u002F`guide-version` value |\n\nScore both the FR and EN files of a pair identically on parity (if the pair is complete, both get 20; if one is missing, the existing file scores 0 on parity).\n\n---\n\n## Phase 5: Metadata Quality (20 points per file)\n\n**Objective**: Validate frontmatter completeness, field formats, and consistency across files of the same type.\n\n### Main whitepapers (20 points max)\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| Required fields present | 6 | Has all of: `title`, `subtitle`, `author`, `date`, `version`, `wp-version`, `series` |\n| `version` follows semver pattern | 3 | Matches `\\d+\\.\\d+\\.\\d+` |\n| `wp-version` follows semver pattern | 3 | Matches `\\d+\\.\\d+\\.\\d+` |\n| `date` is parseable and not in the future | 3 | Valid date, not after today |\n| `series` value is consistent | 2 | Equals \"Codex Ultimate Guide\" |\n| No missing `wp-version` (not left empty or absent) | 3 | Field has a non-empty value |\n\n### Recap cards (20 points max)\n\n| Criterion | Points | Detection |\n|-----------|--------|-----------|\n| Required fields present | 5 | Has all of: `title`, `subtitle`, `card-number`, `category`, `difficulty`, `guide-version`, `author`, `version`, `date` |\n| `card-number` matches filename prefix | 4 | e.g., `C01` in `card-number` matches `c01-` in filename |\n| `category` valid for language | 4 | FR: one of \"Technique\", \"Methodologie\", \"Conception\"; EN: one of \"Technical\", \"Methodology\", \"Design\" (flag \"Conceptual\" as inconsistent in EN) |\n| `difficulty` is valid value | 3 | One of: \"beginner\", \"intermediate\", \"advanced\" |\n| `guide-version` and `version` fields match each other | 4 | Both fields exist and have the same value within the same file |\n\n**Known issue to detect automatically**: EN C-series cards use two different category values (\"Conceptual\" on c01-c05, \"Design\" on c06+). Flag this inconsistency explicitly in the Metadata Issues section of the report.\n\n---\n\n## Phase 6: Scoring and Grading\n\n### Score formula (per file)\n\n```\nTotal = Version Gap (40) + Content Staleness (20) + FR\u002FEN Parity (20) + Metadata Quality (20)\nScore = (Total \u002F 100) * 100  [as a percentage]\n```\n\n### Grade scale\n\n| Grade | Score | Status |\n|-------|-------|--------|\n| A | 90-100 | Fresh, fully synced |\n| B | 80-89 | Good (production threshold) |\n| C | 70-79 | Needs update soon |\n| D | 60-69 | Stale, should prioritize |\n| F | \u003C60 | Critical: likely outdated content |\n\n### Overall health score\n\n```\nWeighted Health = (Sum of WP scores * 2 + Sum of card scores * 1) \u002F (WP count * 2 + card count * 1)\n```\n\nWhitepapers are weighted 2x because they are 20-80 pages each vs. 2-page recap cards. A stale whitepaper carries more risk.\n\n---\n\n## Phase 7: Report\n\nOutput the following Markdown report. Use `\u003Cdetails>` blocks for individual file breakdowns to keep the top level scannable.\n\n```markdown\n# Whitepaper & Recap Card Audit\n\n**Date**: {today}\n**Guide Version**: {VERSION}\n**Overall Health**: {score}% ({grade})\n**Files Audited**: {total} ({wp_count} whitepapers, {card_count} recap cards)\n\n---\n\n## Version Status Dashboard\n\n| Status | Whitepapers | Recap Cards | Total |\n|--------|-------------|-------------|-------|\n| Fresh (0-1 minor behind)   | N | N | N |\n| Stale (2-3 minor behind)   | N | N | N |\n| Very Stale (4-10 behind)   | N | N | N |\n| Critical (11+ behind)      | N | N | N |\n\n**Versions currently in use**:\n- Main WP 00-09: {version} ({gap} minor versions behind)\n- Main WP 10: {version} ({gap} minor versions behind)\n- Recap cards: {guide-version} ({gap} minor versions behind)\n\n---\n\n## Whitepaper Scores\n\n| WP# | Title | version | Gap | wp-version | Parity | Score | Grade |\n|-----|-------|---------|-----|------------|--------|-------|-------|\n| 00  | ...   | ...     | -N  | ...        | OK\u002Fgap | N%    | X     |\n...\n\n\u003Cdetails>\n\u003Csummary>Individual criteria breakdown (WP 00)\u003C\u002Fsummary>\n\n| Phase | Criterion | Result | Points |\n|-------|-----------|--------|--------|\n| Version Gap | Guide version current | Critical (-11) | 0\u002F15 |\n| Version Gap | wp-version valid semver | OK | 5\u002F5 |\n| ... | ... | ... | ... |\n| **Total** | | | **N\u002F100** |\n\u003C\u002Fdetails>\n\n---\n\n## Recap Card Scores\n\n| Series | Cards | Avg guide-version | Avg Gap | Avg Score | Grade |\n|--------|-------|-------------------|---------|-----------|-------|\n| T (Technical)    | 22 | ... | -N | N% | X |\n| M (Methodology)  | 22 | ... | -N | N% | X |\n| C (Conceptual)   | 13 | ... | -N | N% | X |\n\n\u003Cdetails>\n\u003Csummary>Individual card scores\u003C\u002Fsummary>\n\n| Card | Category | guide-version | Gap | Parity | Metadata | Score | Grade |\n|------|----------|---------------|-----|--------|----------|-------|-------|\n...\n\u003C\u002Fdetails>\n\n---\n\n## FR\u002FEN Parity Report\n\n### Whitepapers\n| WP# | FR | EN | wp-version Match | version Match |\n|-----|----|----|------------------|---------------|\n...\n\n### Recap Cards\n- **FR count**: {N} | **EN count**: {N}\n- **Missing FR**: [list or \"None\"]\n- **Missing EN**: [list or \"None\"]\n- **Version mismatches**: [list or \"None\"]\n\n---\n\n## Metadata Issues\n\n### Known: EN Recap Card Category Inconsistency\nEN C-series cards use two different values for the \"Conceptual\u002FDesign\" category:\n- \"Conceptual\": c01, c02, c03, c04, c05\n- \"Design\": c06, c07, c08, ...\nRecommendation: standardize to \"Design\" to match guide terminology.\nAffected files: whitepapers\u002Frecap-cards\u002Fen\u002Fc01-*.qmd through c05-*.qmd (change \"Conceptual\" to \"Design\")\n\n### Other issues\n[List any missing fields, bad formats, date issues...]\n\n---\n\n## Prioritized Action Items\n\n### Critical (Grade F, 11+ versions behind)\n[List specific whitepapers with filename paths]\n\n### High (Grade D-F, 2+ versions behind)\n[List specific files]\n\n### Medium (Metadata quality, category fixes)\n[List specific issues]\n\n### Low (Polish, date alignment)\n[List specific issues]\n\n---\n\n## Next Steps\n\n1. Run `\u002Fupdate-whitepapers --since {oldest_version}` to update all stale WPs\n2. Fix EN category inconsistency (5 files: c01 through c05, change \"Conceptual\" to \"Design\")\n3. Re-run `\u002Faudit-whitepapers` after updates to track progress\n4. Target: 80%+ health (Grade B) across all files\n```\n\n---\n\n## Fix Mode (`--fix`)\n\nWhen `--fix` is passed, append a **Fix Suggestions** section after the report. This section provides concrete patches but does NOT modify any files.\n\n### Frontmatter version patches\n\nFor each file with a stale guide version, output:\n```yaml\n# File: whitepapers\u002Ffr\u002F00-introduction-serie.qmd\n# Change:\nversion: \"3.27.6\"  ->  version: \"{current_VERSION}\"\ndate: 2026-02-12   ->  date: {today}\n```\n\n### Category fix patches (EN recap cards)\n\n```\nFiles to update (category: \"Conceptual\" -> \"Design\"):\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc01-trust-calibration.qmd\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc02-*.qmd\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc03-*.qmd\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc04-*.qmd\n- whitepapers\u002Frecap-cards\u002Fen\u002Fc05-*.qmd\n```\n\n### Update command checklist\n\nBased on the stale WPs detected, output the `\u002Fupdate-whitepapers` commands to run in order:\n```\nSuggested update sequence:\n1. \u002Fupdate-whitepapers --since {oldest_stale_version} --wp 00,01,02,03,04,05,06,07,08,09\n2. \u002Fupdate-whitepapers --since {oldest_stale_version} --wp 10\n3. Review and bump wp-version for each updated WP (patch = content corrections, minor = new sections)\n4. Bump guide-version in all recap cards to {current_VERSION}\n5. Re-run \u002Faudit-whitepapers to verify\n```\n\n---\n\n## Verbose Mode (`--verbose`)\n\nWhen `--verbose` is passed, expand all `\u003Cdetails>` blocks by default and show the complete per-file criteria table (all criteria, not just failures) for every audited file.\n\n---\n\n## Exclusions Reference\n\nThe following files are excluded from scoring (listed in discovery summary only):\n\n| Pattern | Reason |\n|---------|--------|\n| `strangebee-*.qmd`, `purchasely-*.qmd`, `devwithai-*.qmd` | Client\u002Fpartner custom files, separate lifecycle |\n| `fiches-recap-serie.qmd`, `fiches\u002F*.qmd` | Bundle\u002Finclude files, no independent versioning |\n| `*_quarto.yml`, `references.bib` | Build config, not content |\n| `cheatsheet.qmd` | Listed separately in discovery, not scored in main audit |\n",{"name":5,"description":7},"main","f2cc95bc769ca4c3a398965b767dfb41cdf8d698","reference\u002Fclaude-code-ultimate-guide-main\u002F.agents\u002Fskills\u002Fsource-command-audit-whitepapers",2,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","https:\u002F\u002Fgithub.com\u002F313DEVGRP","https:\u002F\u002Fwww.a-rms.net","2026-10-18 12:48:10",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill source-command-audit-whitepapers",{"tool":38,"command":39},"bunx","bunx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill source-command-audit-whitepapers",{"tool":41,"command":42},"pnpm","pnpm dlx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill source-command-audit-whitepapers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002F.agents\u002Fskills\u002Fsource-command-audit-whitepapers\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7F343WNVHZWWYJDD77QEJ7J","voice-refine","Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvoice-refine\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7F3417SNXASFTDA1B2X4XYZ","validate-changes","Evaluate staged changes using LLM-as-a-Judge before committing","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvalidate-changes\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7F33YN9QK88H2B81PVHMNG1","update-threat-db","Delegate threat-intelligence research and updates to AgentSec, then validate the guide and landing mirrors.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fupdate-threat-db\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7F33SXQ57G2FVFK094T4584","token-audit","Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan. Use when hitting rate limits, experiencing early context compression, or after adding significant config files.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftoken-audit\u002Fskill.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7F33NAWXFPHW59CF52EAGGK","talk-stage6-revision","Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-6-revision\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7F33G9V96HVZKAGZ84J4EBR","talk-stage5-script","Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-5-script\u002FSKILL.md",[],[]]