field-sv
169Agent Claude Code
A packaging specialist for turning approved manual chapters into materials that franchise locations can use. It handles the final delivery stage after quality review.
not rated 2 3mo ago A 75 tokens
Agent
Reads academic paper content from PDF or URL. Handles chunked reading for large PDFs (>20 pages). Extracts structure, formulas, algorithms, and notation. Used by paper2code skill in STEP 2.
not rated 2 5mo ago A 49 tokens
Agent
Ops note: auth and env changes are not performed from this document. This captures a product/engineering decision and rollout reminders only.
not rated 2 today A 0 tokens
image-op-pro
172Agent
Hoisted escalation agent for vision-heavy work: dense OCR, chart/document/table reading, pixel-level verification, and visual QA where detail fidelity matters. Not a first-line image agent — the main agent should try image-op first, and call this one when image-op recommends it (or when the vision task is clearly…
not rated 2 yesterday A 97 tokens
Agent
This document outlines the file organization for [Project Name], ensuring modularity and maintainability across source, scripts, tests, and docs.
not rated 2 2d ago A 0 tokens
original MIT
editor
174Agent Claude Code
Reviews a markdown draft for markdown formatting, clarity, structure, and voice. Returns OK or a list of issues. Read-only — flags, does not rewrite. Use proactively after drafting each major section of prose and before finalizing a document.
not rated 2 yesterday A 50 tokens
reviser
175Agent Claude Code
Reads a review thread and the surrounding document context, then proposes a reply or edit as a message.posted event with commit:null. Never edits the document body and never commits — the principal applies the proposal and creates the git commit. Use proactively when the principal fans out thread review tasks in…
not rated 2
changed today A 62 tokens
Agent
Act as an information extraction and compression specialist. Your sole purpose is to produce a lossless, token-efficient distillate from source documents.
not rated 2 4mo ago A 0 tokens
copy · 100% MIT
Agent
Act as a document reconstruction specialist. Your purpose is to prove a distillate's completeness by reconstructing the original source documents from the distillate alone.
not rated 2 4mo ago A 0 tokens
copy · 100% MIT
marp
178Agent
Expert on Markdown and Marp presentation framework. Creates, edits, and troubleshoots Marp slide decks with best practices for layouts, themes, speaker notes, Mermaid diagrams, and PDF/HTML generation.
not rated 2 2mo ago A 44 tokens
original MIT
docs
179Agent
Generate or improve repository-specific documentation.
not rated 2 2mo ago A 0 tokens
original MIT
docs-writer
180hwchany0ung/claude-agent-playbook
Agent
Use for generating README updates, API documentation, technical specs, migration guides, and developer onboarding docs. Triggered after major feature completion or API changes. Reads existing code and docs to produce accurate, up-to-date documentation.
not rated 2 3mo ago A 48 tokens
pptx-generator
181Agent
Use when creating or modifying PPTX presentations. Reads the bundled pptx-reference.md for API details, pitfalls, and QA workflow.
not rated 2 10d ago A 30 tokens
original MIT
ingestor
182Agent
Document ingestion agent — ingests PDFs, URLs, and media into the academic corpus with Merkle verification.
not rated 2 3d ago A 20 tokens
design-scene
183sonereraslan/local-marketplace
Agent
Use this agent to run the full 8-step design workflow for a scene, area, or level — producing proposals from each design skill in sequence and returning a combined design document. Trigger when the user wants to design a complete scene from scratch or from a partial starting point. Context: User wants to design a new…
not rated 2 4mo ago A 307 tokens
original MIT
pptx-builder
184Agent
Create editable, production-ready PPTX decks from clear narrative, design, and coordinate specifications.
not rated 1 1mo ago A 22 tokens
original MIT
bank-extract
185Agent Claude Code
Structuring stage of bank onboarding. Reads the ingested raw sources (resumes, notes) listed in the bank's .ingest/manifest.json and writes the two-layer bank per spec/bankformat.md (experiencebank.md for evidence units, profile.json for the record layer), plus .ingest/gaps.md, the ranked interview agenda. Transcribes…
not rated 1 1mo ago A 91 tokens
original MIT
doc-writer
186Agent
Documentation expert creating crystal-clear docs. Use after feature completion.
not rated 1 19d ago A 16 tokens
original MIT
typst-verify
187Agent Codex
Verify Typst document output against requirements. Use after compilation when you need to confirm content, structure, or visual layout correctness.
not rated 1 2mo ago A 30 tokens
Agent Claude Code
Act as an information extraction and compression specialist. Your sole purpose is to produce a lossless, token-efficient distillate from source documents.
not rated 1 5mo ago A 0 tokens
Agent Claude Code
Act as a document reconstruction specialist. Your purpose is to prove a distillate's completeness by reconstructing the original source documents from the distillate alone.
not rated 1 5mo ago A 0 tokens
orchestrator
190Agent
The single entry point for the presentation generation pipeline. Manages state, planning, retry control, and delegation to other agents.
not rated 0 4mo ago A 0 tokens
Agent Cursor
Expert LaTeX transcriber that turns slide decks and accompanying lecture audio/video into structured, publication-ready LaTeX. Use proactively whenever a user requests LaTeX output from presentation materials.
not rated 0 5mo ago A 42 tokens
original MIT
Agent Cursor
Presentation generator that evaluates outlines, syncs ToC with directory structure, plans slide content from Reveal.js examples, and delegates remaining work to Bayesian agents (backwards reasoner, hypothesis generator, evidence evaluator), existing skills, subagents, and Autogen. Use proactively when building or…
not rated 0 5mo ago A 80 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: