Technical Writing Agent Skills

Generates publication-quality figures for ML papers, including architecture diagrams via Gemini and data-driven charts via matplotlib/seaborn.

Records research provenance as a post-task epilogue, scanning conversation history to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with provenance tags.

Merges multiple diagnosis snapshots from dbs-save into a single, timestamped Markdown report organized by topic.

Scans copy for AI-generated writing patterns and outputs a diagnostic report. Diagnosis only by default.

Reconciles project documentation, agent memory, and rule files against the actual codebase after a development session, ensuring accuracy and consistency across all knowledge layers.

Analyzes Mintlify's design system, documenting its dual-mode aesthetic of atmospheric marketing heroes and dense developer documentation surfaces, including color tokens, typography hierarchy, and layout patterns.

Generates task-oriented technical documentation with progressive disclosure for READMEs, API docs, architecture docs, and security reports after reverse engineering, penetration testing, or CTF tasks.

Audits documentation health by scanning for README, changelog, API docs, ADRs, runbooks, onboarding guides, and diagrams, scoring coverage against project maturity, and recommending sub-skills to fill gaps.

Audits and rewrites user-facing copy across web and mobile codebases, improving clarity, tone, and actionability of labels, errors, CTAs, and empty states.

Produces academic papers, literature reviews, grant proposals, and clinical reports with LaTeX formatting and verified citations, using research-lookup and parallel-web skills.

Generates a candid improvement report for a software requirements specification, covering deferred features, technical risks, FR refinement suggestions, NFR gaps, validation warnings, and process recommendations.

Provides verified legal references and templates for business formation, employment, and contract drafting across US, EU, and Canadian jurisdictions.

Creates CodeTour .tour files with real file and line anchors for onboarding, architecture, PR, RCA, and security walkthroughs.

Extracts a language-agnostic ghost package (spec, tests, install and verify docs) from an existing repository, preserving behavior via tests.yaml and evidence bundles.

Generates a complete Custom GPT knowledge package from the current workspace project, producing 20 markdown documentation files plus optimized custom instructions for a strategic consultant.

Generates or executes a remediation prompt for a book flagged YELLOW or RED by /book-audit, writing a fix-<book-slug>.md that enumerates defects with verbatim PDF source text and verification commands, then optionally executes the fixes to bring the book to GREEN.

Audits type-safety documentation against the live codebase, checking for drift from validators and folder layout.

Extracts a YouTube transcript with yt-dlp, cleans it while preserving all substantive speech, and saves a structured markdown file with metadata, overview, and optional timestamps.

Designs scalable REST and GraphQL APIs, creates OpenAPI 3.1 specifications, and plans versioning, pagination, and error handling.

Documents and explains an existing codebase as it is, without suggesting improvements or architectural changes.

Generates a candid improvement report for a software requirements specification, covering deferred features, technical risks, FR refinements, NFR gaps, validation warnings, and process recommendations.

Guides a structured software requirements specification workflow from topic intake through brainstorming, spec writing, planning, review, SRS generation, validation, and improvement reporting.

Analyzes codebase structure and generates token-lean architecture documentation in codemap files, with diff detection and metadata tracking.

Synchronizes documentation, READMEs, release notes, and operating docs with current shipped behavior when they have drifted.

Converts technical books and documents (PDF, EPUB, DOCX, HTML, Markdown, RTF, MOBI) into structured agent skills with frameworks, mental models, chapter references, and decision rules. Includes a full extraction pipeline for turning owned documents into reusable skills.

Provides a structured README template for documenting XDG config directories, dotfiles, and script folders, helping users remember the purpose and contents of their local configuration.

Generates interactive comparison table MicroSims for educational content, including star ratings, difficulty badges, logos, hover tooltips, and mkdocs.yml navigation updates.

Closes out a working session by updating docs/progress.md, reporting uncommitted and unpushed git work, and listing decisions and open threads. Read-only on git, never commits or pushes.

Manages shadcn/ui components and projects, providing context, documentation, and usage patterns for building modern design systems.

Manages shadcn/ui components and projects, providing context, documentation, and usage patterns for building modern design systems.

Analyzes code directories to produce C4 code-level documentation with function signatures, dependencies, and structure.

Creates and maintains minimal, high-signal AGENTS.md files for AI coding agents, following research-backed best practices for concise agent documentation.

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term, helping users name effects for prompting AI or designers.