Use this agent for writing comprehensive Product Requirements Documents (PRDs) for software projects or features. This includes documenting business goals, user personas, functional requirements, user experience flows, success metrics, and user stories. Use when you need to formalize product specifications or plan new…
An agent that writes analysis paragraphs for a fixed 10-chapter report from structured product and market data. It fills insight, findings, and conclusion fields rather than formatting the whole report.
Reviews project docs (docs/.md, per-crate CLAUDE.md, root CLAUDE.md, .github/copilot-instructions.md, README) after a feature is implemented, and updates or creates whatever is out of sync. Use PROACTIVELY at the end of any PR/feature that changes public API, markdown syntax, TUI shortcut, slash command, sidecar, op…
Use this agent to assemble the final report files in Phase 5 and to apply post-gate fixes in Phase 6 of deep research. The editor formats and structures; it never adds facts.
Use this agent when writing new Python files, editing existing Python files, or reviewing recently written code to ensure full compliance with the CodeDNA v0.9 annotation standard. This includes enforcing module docstrings, export contracts, semantic variable naming, function-level Rules docstrings, message…
Use this agent when documentation in the docs directory needs to be updated to reflect the actual state of the codebase. This includes after refactoring, API changes, new features, or any code modifications that make existing documentation outdated or inaccurate.\n\n \nContext: The user has just refactored a module…
A writing assistant for technical articles about harness9, a software project. It researches the project’s documentation and code, explains its design choices, and creates prompts for simple Ghibli-style illustrations.
A documentation workflow for completed Protocol Launcher tools, which open applications through special links. It gathers implementation details and produces matching English and Chinese documentation pages.
Expert agent for creating PRPM blog posts - ensures consistent structure, tone, format, and technical depth aligned with PRPM's vision of distributable intelligence.
Generates complete MCP server documentation pages. Use when a new MCP server package is added to the monorepo and needs a docs page, or when an existing MCP server page needs to be regenerated from source. Reads the package source code and produces a fully formatted Fumadocs MDX page.
Use this agent when you need to create, update, or maintain technical documentation including README files, API documentation, architecture guides, or code comments. This agent should be invoked after implementing new features, changing APIs, or when documentation gaps are identified. Examples:\n\n \nContext: The user…
Independent evaluator for the book pipeline. Scores chapters it did NOT write using Genesis Score (7 dimensions), 4-reader simulation including casual reader, 20-pattern anti-AI scan, "Would You Remember This Tomorrow" test, and cross-book pattern detection.
Use when developing anti-vibe-writing, a writing skill for AI agents that rewrites generated drafts into a more classic, polished, human style. Handles skill design, prompt assets, editing heuristics, README cleanup, docs maintenance, and safe local git automation.
Use after editing SKILL.md, README.md, or any file under skills/graph-engineer/references/ to verify the cross-file invariants documented in CLAUDE.md still hold. Trigger proactively whenever one of those files changes, or when the user asks "did I break anything by editing the docs" / "check consistency" / "audit the…
A read-only assistant that searches a structured story project and returns details about characters, settings, plot clues, timeline events, relationships, and writing progress.
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: