feat(skills): restructure Docx/Pdf/Pptx/Xlsx into Documents pack#153
feat(skills): restructure Docx/Pdf/Pptx/Xlsx into Documents pack#153Steffen025 merged 2 commits intodevfrom
Conversation
Resolve naming redundancy where Utilities/Documents/ existed as a hub skill alongside individual Docx/Pdf/Pptx/Xlsx skills in Utilities/. Changes: - Create new Documents/ category as sibling of Utilities/ - Move Docx, Pdf, Pptx, Xlsx from Utilities/ to Documents/ (git mv preserves history) - Remove obsolete Utilities/Documents/ hub skill - Migrate ProcessLargePdfGemini3 workflow into Documents/Pdf/Workflows/ (gold nugget preserved) - Add new Documents/SKILL.md hub with routing logic and best practices Best practices captured per format (DOCX/PDF/PPTX/XLSX) from the legacy Documents hub — tracked changes for DOCX, library selection for PDF, design-first for PPTX, formula-based XLSX. Skill-index regenerated: Documents category now has 4 skills, Utilities reduced from 23 to 17 skills, total structure cleaner.
|
Warning Rate limit exceeded
Your organization is not enrolled in usage-based pricing. Contact your admin to enable usage-based pricing to continue reviews beyond the rate limit, or try again in 48 minutes and 1 seconds. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
📝 WalkthroughWalkthroughReorganized the Documents skill from the Utilities category to a top-level category. Replaced the Utilities-based SKILL.md documentation with a new Documents-based version and updated skill-index.json metadata to reflect the new category hierarchy, file paths, and skill structure for document format handlers. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
.opencode/skills/skill-index.json (1)
1130-1155:⚠️ Potential issue | 🟡 MinorRemove stale document-routing keywords from Utilities skill.
The
utilitiesentry in skill-index.json still advertises "process documents, PDF, Word, Excel" and triggers ondocuments,word,excel. After restructuring these into the separateDocumentspack, SkillSearch will route document queries to both packs—directing traffic away from the dedicated Documents skill.Fix: In
.opencode/skills/Utilities/SKILL.mdfrontmatter (line 2), removeprocess documents, PDF, Word, Excelfrom the description. Then run:bun .opencode/PAI/Tools/GenerateSkillIndex.tsThis regenerates skill-index.json without the stale triggers.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.opencode/skills/skill-index.json around lines 1130 - 1155, The Utilities skill still lists stale document-routing keywords ("process documents, PDF, Word, Excel") in its SKILL.md frontmatter, causing duplicate routing; edit the Utilities SKILL.md frontmatter to remove that phrase and any triggers for documents/pdf/word/excel, then regenerate the index by running the skill index generator (GenerateSkillIndex.ts) so .opencode/skills/skill-index.json is rebuilt without the stale triggers.
🧹 Nitpick comments (1)
.opencode/skills/Documents/SKILL.md (1)
1-94: Hub SKILL.md looks good; routing table and per-format guidance are clear.Frontmatter
USE WHENtriggers are present and the routing logic cleanly maps intents to the four sub-skills. One small nit: consider explicitMANDATORY/OPTIONALsection markers to match PAI v3.0 strictly, though the current hub-style layout is consistent with other category hubs in the repo.As per coding guidelines: "SKILL.md follows PAI v3.0 format (USE WHEN triggers, MANDATORY/OPTIONAL sections)".
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.opencode/skills/Documents/SKILL.md around lines 1 - 94, Add explicit "MANDATORY" and "OPTIONAL" section markers to the frontmatter/metadata in the Documents SKILL.md so it conforms to PAI v3.0: keep the existing USE WHEN triggers but split them into two labeled lists (MANDATORY for required intent keywords and OPTIONAL for helpful/secondary triggers), and ensure the routing logic sections (Word/PDF/PPTX/XLSX headings) reference those MANDATORY/OPTIONAL groups; look for the frontmatter block containing "USE WHEN" and the routing headings (e.g., Word Documents (.docx), PDFs (.pdf), Presentations (.pptx), Spreadsheets (.xlsx, .csv)) and insert the labeled sections without changing existing triggers or routing text.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Outside diff comments:
In @.opencode/skills/skill-index.json:
- Around line 1130-1155: The Utilities skill still lists stale document-routing
keywords ("process documents, PDF, Word, Excel") in its SKILL.md frontmatter,
causing duplicate routing; edit the Utilities SKILL.md frontmatter to remove
that phrase and any triggers for documents/pdf/word/excel, then regenerate the
index by running the skill index generator (GenerateSkillIndex.ts) so
.opencode/skills/skill-index.json is rebuilt without the stale triggers.
---
Nitpick comments:
In @.opencode/skills/Documents/SKILL.md:
- Around line 1-94: Add explicit "MANDATORY" and "OPTIONAL" section markers to
the frontmatter/metadata in the Documents SKILL.md so it conforms to PAI v3.0:
keep the existing USE WHEN triggers but split them into two labeled lists
(MANDATORY for required intent keywords and OPTIONAL for helpful/secondary
triggers), and ensure the routing logic sections (Word/PDF/PPTX/XLSX headings)
reference those MANDATORY/OPTIONAL groups; look for the frontmatter block
containing "USE WHEN" and the routing headings (e.g., Word Documents (.docx),
PDFs (.pdf), Presentations (.pptx), Spreadsheets (.xlsx, .csv)) and insert the
labeled sections without changing existing triggers or routing text.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 5dacb07a-9d1b-4414-8ae7-4e8dec5181d3
📒 Files selected for processing (42)
.opencode/skills/Documents/Docx/LICENSE.txt.opencode/skills/Documents/Docx/Ooxml/Scripts/pack.py.opencode/skills/Documents/Docx/Ooxml/Scripts/unpack.py.opencode/skills/Documents/Docx/Ooxml/Scripts/validate.py.opencode/skills/Documents/Docx/SKILL.md.opencode/skills/Documents/Docx/Scripts/__init__.py.opencode/skills/Documents/Docx/Scripts/document.py.opencode/skills/Documents/Docx/Scripts/utilities.py.opencode/skills/Documents/Docx/docx-js.md.opencode/skills/Documents/Docx/ooxml.md.opencode/skills/Documents/Pdf/LICENSE.txt.opencode/skills/Documents/Pdf/SKILL.md.opencode/skills/Documents/Pdf/Scripts/check_bounding_boxes.py.opencode/skills/Documents/Pdf/Scripts/check_bounding_boxes_test.py.opencode/skills/Documents/Pdf/Scripts/check_fillable_fields.py.opencode/skills/Documents/Pdf/Scripts/convert_pdf_to_images.py.opencode/skills/Documents/Pdf/Scripts/create_validation_image.py.opencode/skills/Documents/Pdf/Scripts/extract_form_field_info.py.opencode/skills/Documents/Pdf/Scripts/fill_fillable_fields.py.opencode/skills/Documents/Pdf/Scripts/fill_pdf_form_with_annotations.py.opencode/skills/Documents/Pdf/Workflows/ProcessLargePdfGemini3.md.opencode/skills/Documents/Pdf/forms.md.opencode/skills/Documents/Pdf/reference.md.opencode/skills/Documents/Pptx/LICENSE.txt.opencode/skills/Documents/Pptx/Ooxml/Scripts/pack.py.opencode/skills/Documents/Pptx/Ooxml/Scripts/unpack.py.opencode/skills/Documents/Pptx/Ooxml/Scripts/validate.py.opencode/skills/Documents/Pptx/SKILL.md.opencode/skills/Documents/Pptx/Scripts/html2pptx.js.opencode/skills/Documents/Pptx/Scripts/inventory.py.opencode/skills/Documents/Pptx/Scripts/package.json.opencode/skills/Documents/Pptx/Scripts/rearrange.py.opencode/skills/Documents/Pptx/Scripts/replace.py.opencode/skills/Documents/Pptx/Scripts/thumbnail.py.opencode/skills/Documents/Pptx/html2pptx.md.opencode/skills/Documents/Pptx/ooxml.md.opencode/skills/Documents/SKILL.md.opencode/skills/Documents/Xlsx/LICENSE.txt.opencode/skills/Documents/Xlsx/SKILL.md.opencode/skills/Documents/Xlsx/recalc.py.opencode/skills/Utilities/Documents/SKILL.md.opencode/skills/skill-index.json
💤 Files with no reviewable changes (1)
- .opencode/skills/Utilities/Documents/SKILL.md
…ments pack split Addresses CodeRabbit review feedback: Utilities SKILL.md frontmatter still advertised 'process documents, PDF, Word, Excel' as triggers, causing duplicate routing with the new Documents pack. Changes: - Remove document keywords from Utilities frontmatter description - Remove the Documents table row that referenced the removed sub-skill - Add pointer to the dedicated Documents pack under 'When to Use' - Regenerate skill-index to reflect clean routing
1 participant
Summary
Resolves the naming redundancy where
Utilities/Documents/existed as a hub skill alongside individualDocx/Pdf/Pptx/Xlsxskills inUtilities/. Document-processing skills now live in their ownDocuments/pack with a proper hub SKILL.md; the obsolete hub is removed.Changes
Documents/category as sibling ofUtilities/Docx,Pdf,Pptx,XlsxfromUtilities/→Documents/viagit mv(history preserved)Utilities/Documents/hub skillProcessLargePdfGemini3.mdworkflow intoDocuments/Pdf/Workflows/Documents/SKILL.mdhub with routing logic and per-format best practicesWhy
Before: ambiguity between hub and specific skills. After: proper Pack category consistent with Investigation/Media/Security/Thinking organization. Skill-index cleaner (Documents=4, Utilities 23→17).
Verification
bun .opencode/PAI/Tools/GenerateSkillIndex.tsproduces clean indexgit mv(renames, not delete+add)Summary by CodeRabbit