Docs & Writing

marvin-lijunzan Bundle

Codex + Zotero bridge for academic note-taking: synchronizes literature metadata, parses reader highlights and PDF annotations, and generates structured scientific literature cards.

marvin-lijunzan Skill

Humanize academic and technical writing: eliminates telltale AI patterns, bureaucratic padding, monotonous sentence rhythms, and clichéd transitional fluff, restoring authentic human authorial voice.

marvin-lijunzan Skill

Visual status tags, technology stack shields, and documentation badges using Markdown Badges (Ileriayo/markdown-badges). Standardizes Shields.io-style pills, licenses, build badges, and tech icons for software deliverables.

marvin-lijunzan Bundle

Automated massive-scale academic literature search (up to 1000 papers per keyword), per-keyword BibTeX generation with full abstracts, Web of Science & OpenAlex multi-source integration, cross-corpus deduplication & matrix synthesis, and 5-stage publication-grade LaTeX/Markdown Introduction drafting.

marvin-lijunzan Bundle

Professional LaTeX to Word (docx) conversion engine tailored for journal submissions: enforces journal-specific templates/styles, standard publication three-line tables (booktabs), multi-panel subfigures alignment, Word SEQ field cross-referencing (Figures, Tables, Equations), native MathType engine invocation, and strict active Zotero citation library synchronization (TeX bib import -> Zotero library update -> CSL dynamic field injection into Word).

marvin-lijunzan Skill

End-to-end literature review workflow: search strategy design, full-text PDF acquisition, structured deep reading, cross-paper evidence matrix compilation, and publication-ready review drafting.

marvin-lijunzan Bundle

AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable Brand/Style/Layout/Deck workspaces, filling native PPTX templates, and enhancing finished PPTX files. Use when the user asks to create, generate, reconstruct, regenerate, beautify, redesign, template, fill, or enhance a presentation, PPT, PPTX, slide deck, or courseware — including adding narration or animation to one — requests a presentation-authored narrated/self-running video, or mentions ppt-master.

marvin-lijunzan Bundle

Orchestrates the PaperSpine suite for motivation-driven paper/report rewriting or building from materials.

marvin-lijunzan Bundle

Builds a paper or report from materials using the shared PaperSpine research, motivation, and rationale workflow.

dragoon0x Skill

Generate a shareable OPTIK score card. Produces an SVG/image showing score, category breakdowns, and grade.

ferroxlabs Skill

Eligibility analysis and documentation for FMLA / state PFML / personal / medical leave - covers federal FMLA (50+ EE within 75 mi, 12 months / 1,250 hrs), state PFML (CA CFRA, NY PFL, NJ FLI, MA PFML, WA PFML, CT PFMLA, CO FAMLI, OR PFMLI, RI TCI, DC PFL, plus 2026 states), request-response letter, return-to-work plan, intermittent-leave tracking. Templates only - not employment-law advice.

ferroxlabs Skill

Wayfair economic-nexus tracker, marketplace facilitator law handling, multi-state filing checklist, exemption certificate management, tax-on-shipping rules. Outputs a state-by-state nexus exposure report. Templates only - not personalized sales-tax advice.

ferroxlabs Skill

Orchestrates the full incident lifecycle from initial triage through postmortem documentation, chaining five software-development skills into a structured incident management workflow. This workflow chains the incident-response skill with logging, monitoring, deployment, and documentation skills. Use when the user is handling an active production incident and needs a structured process from detection through resolution and postmortem. Do NOT use for non-production issues, planned maintenance, or post-incident analysis only (use technical-documentation directly for standalone postmortems).

ferroxlabs Skill

Quarterly Form 941 and annual Form 940 prep checklist, state UI / WC matrix, new-hire reporting, S-corp reasonable-salary documentation (Watson, Glass Blocks, Fleischer factors), and fringe-benefit valuation. Templates only - not personalized payroll, tax, or legal advice.

openaccountant Skill

Performs a comprehensive review of spending for a given period. Summarizes by category, compares to budgets, highlights anomalies, and provides actionable recommendations. Trigger when user says "review my spending", "how did I do this month", "spending report", or "where is my money going".

openaccountant Skill

Generates a comprehensive annual financial summary with category breakdowns, month-over-month trends, top merchants, and highlights. Trigger when user asks for "annual summary", "year in review", or "yearly report".

johnqtcg Bundle

Keep repository documentation synchronized with the latest code. Use when updating README/docs/codemaps after code changes, running docs-drift checks, or producing scoped evidence-backed doc patches for service/library/CLI/monorepo projects.

johnqtcg Bundle

Perform auditable research with executable mode budgets, mandatory source-content verification, typed web and repository evidence, confidence assessment, honest degradation, and one fixed nine-section report. Use for web research, claim verification, technical comparisons, trend analysis, pure codebase research, and hybrid codebase-plus-web investigations that need traceable conclusions rather than search-result summaries.

johnqtcg Bundle

Write, review, and improve technical documents (技术文档, 设计文档, 操作手册, 故障报告, API文档). Use when users ask to write/draft/review/improve a technical document, create an RFC/ADR, write a runbook or operation guide, produce API docs, or create any structured technical writing deliverable. Audience-aware, evidence-based, with quality gates, a mechanical linter, and staleness detection (age against review cadence, not merely a date field). Supports concept docs, task docs, reference docs, troubleshooting docs, and design docs (RFC/ADR).

johnqtcg Bundle

Generate or refactor project README.md files using repository evidence. Use when the user asks to create/rewrite/standardize README, improve documentation structure, or produce maintainable README templates for different project types (service/library/CLI/monorepo).

johnqtcg Bundle

Incident post-mortem specialist for writing blameless post-mortems, extracting timelines from logs/events, conducting root cause analysis (5-Why, fishbone), classifying severity, and generating tracked action items. ALWAYS use when writing a post-mortem, reviewing an incident, extracting a timeline, performing root cause analysis, or converting incident data into organizational knowledge. Complements systematic-debugging (finds the cause) with structured documentation that prevents recurrence.

johnqtcg Bundle

Compress chaotic information into a leader-ready structure before output. ALWAYS use when the user is preparing to brief a senior leader, present a technical proposal, write a one-pager, or otherwise turn scattered facts and feelings into Frame → Crux → Nodes → Tilt + Reasoning that fits in 3–5 minutes of reading. Trigger phrases include "向领导汇报", "做技术方案 presentation", "整理思路", "report up", "brief the boss", "summarize for leadership", "executive briefing", "one-pager". NOT for writing the final polished document (use tech-doc-writer), NOT for decomposing tasks into implementation steps (use writing-plans), NOT for incident root-cause analysis (use incident-postmortem), NOT for aggregating research with citations (use deep-research).

creatorland Skill

Keep a running log of searches run and creators already reviewed this engagement so repeat searches (and repeat credits) are avoided — before a new search, diff it against prior runs and report what's new. Use when the user says "have I searched this before", "what have we searched", "show the search log", "dedupe this against earlier", or wants to avoid paying twice for the same query. Produces/updates a session search memo; near-zero credits.

dauquangthanh Bundle

Translate between Word (.docx) files and Markdown with high-fidelity round-trip. Use this skill whenever the user wants to convert a Word document to Markdown, edit a .docx as text, regenerate a .docx from Markdown, diff/review Word content in git, or keep a canonical text version of a document alongside the .docx. Triggers: 'docx to markdown', 'word to md', 'convert this Word doc to markdown', 'rebuild this docx from markdown', 'edit my report in markdown', 'extract word text with formatting', 'round-trip my Word doc'. Preserves headings, lists, tables, images, footnotes, comments, tracked changes, and document styles via pandoc plus a sidecar metadata file. Not a replacement for the base docx skill when the user is authoring a new Word document from scratch — use that skill for new content, and use this one for round-trip translation.

dauquangthanh Bundle

Translate between PowerPoint (.pptx) files and Markdown with high-fidelity round-trip. Use this skill whenever the user wants to convert a deck to Markdown, edit a deck as Markdown, regenerate a .pptx from Markdown, diff/review slide content as text, or version-control a presentation. Triggers: 'convert slides to markdown', 'edit this deck in markdown', 'pptx to md', 'md to pptx', 'round-trip my presentation', 'export slides as text', 'rebuild this pptx from markdown', or anytime a .pptx and a .md file both appear in the task. Not a replacement for the base pptx skill when the user is creating a visually rich deck from scratch — use that skill for new designs, and use this one for round-trip translation.

dauquangthanh Bundle

Extracts architecture from an existing codebase — containers, components, data flow, external dependencies. Produces an architecture doc that can seed new ADRs and C4 diagrams. Use when reverse-engineering a codebase, onboarding to a new project, or when architecture documentation needs to be generated from existing code.

dauquangthanh Bundle

Builds and maintains a Requirements Traceability Matrix (RTM) that links every requirement (FR-NNN / NFR-NNN from the SRS) to its design section, implementation task, test case, and bug report. Supports forward traceability (requirements → delivery) and backward traceability (artefacts → requirements). Use when a Waterfall project needs to demonstrate that every requirement is designed, implemented, and tested; when a customer or auditor asks for full traceability evidence; or when performing a coverage gap analysis before a phase gate.

nexadevapp Bundle

Creates structured bug report documents with reproduction steps, expected vs actual behavior, and severity classification. Use when the user asks to "report a bug", "file a bug", "document a defect", "log an issue", or mentions a bug, defect, regression, or unexpected behavior that needs to be tracked.

mindgoblinstudios Bundle

Maintain a project's canonical documentation system so durable decisions, workflows, constraints, and lessons remain easy for humans and agents to find. Use when documentation, AGENTS.md routing, remembered corrections, or self-improving project workflows are involved. AutoDocs may read docs for planning context, but it does not authorize creating planning documents.

mindgoblinstudios Bundle

Text Editor Workbench: Open a minimal browser note editor with a collapsible file sidebar and autosynced Markdown/text files.

skyosev Bundle

Use when reviewing Go, Python, or TypeScript code for AI-generated noise before merging AI-assisted changes, cleaning up a branch after heavy AI pair-programming, enforcing project conventions on new contributions, or reducing review noise. Defaults to the branch diff. Covers redundant comments, verbose documentation, style drift from the project's own conventions, trivially dead code, hedging and narration, and Go's unnecessary error wrapping.

davie521 Bundle

PDF Processing Guide

creatorland Skill

Map which creators are creating around your competitor brands — surface creators with corpus-known affinities to named competitors, plus similar not-yet-affiliated creators as whitespace casting targets. Use when the user says "who's creating for [competitor]", "which creators work with our competitors", "competitor creator watch", "map [brand]'s creator roster", or names rival brands and wants the creator landscape around them. Deliverable is a competitor creator-landscape report.

creatorland Skill

Self-healing tiered casting — build a premium/mid/value (or macro/mid/micro) shortlist, reach tier-1 only first, then on a decline or Day-7 no-reply release that slot's budget and reach the next-best creator down the tiers until the role is filled or budget runs out. Use when the user says "waterfall casting", "reach tier 1 then fall back", "auto-fallback to the next tier if they pass", or "tiered outreach with backfill". Reaches a wave, advances on report-back; never promises a yes. Deliverable is the tiered plan + the wave's Reached table.

creatorland Skill

Recurring "conditions report" for a vertical — re-pull corpus aggregates, compare against stored prior snapshots, and report what the active_since-windowed data actually shows as deltas ("recency signals warming in Fitness"). Use when the user says "what's changed in [vertical]", "vertical forecast", "conditions report", "deltas since last run", or runs a scheduled vertical check. Stores a snapshot each run for next time. For a point-in-time portrait with no deltas, use vertical-briefing.

creatorland Skill

Produce a standardized, credit-report-style diligence one-pager for a single creator — profile facts, audience geo, brand affiliations, freshness status, and vertical benchmark position — formatted for procurement and legal review. Use when the user says "run diligence on [creator]", "diligence report", "vet this creator", "one-pager on [creator] for legal/procurement", or needs an institutional artifact before contracting. Not for finding creators or pricing a live quote.