Operate the local-first pcast podcast CLI for humans and automation. Use when the user wants to subscribe to RSS/Atom feeds, list podcasts, check for new episodes (latest),…
Toolkit for comprehensive PDF reading, reviwing, and creation with visual quality control. Use to work with PDFs (.pdf files) for: (1) Reading or extracting content from — from…
Fill any PDF locally and place each value precisely in a visual editor. Use when the user wants to fill out a PDF form, enter data into a PDF, complete a tax/insurance/bank form,…
Make, research, and summarize PDF files. Builds real .pdf documents — proposals, invoices, reports, one-pagers, whitepapers, case studies, price sheets, resumes — and reads the…
Convert any PDF (or DOCX/PPTX/XLSX/image) to clean Markdown. For scientific papers, produce the canonical paper-to-md bundle (Markdown plus section_audit.json and article.json)…
Convert research paper PDFs into literature-report PPTX decks using a fully offline workflow (extract text/figures, map captions, summarize findings, and generate slides).
한국어·일본어·중국어·영어 다국어 PDF 파일을 깨짐 없이 생성합니다. PyMuPDF + Noto Sans CJK 번들 폰트 조합으로 CJK(한중일) 글리프 누락 문제를 근본 해결하며, Markdown·구조화 JSON·HTML·일반 텍스트 4종 입력을 모두 지원합니다.
Convert PDF files to MP3 audio using MiniMax MCP Server's text-to-audio tool. Use when user wants to convert a PDF to audio/MP3, create audiobook from PDF, or text-to-speech for…
Use when when comparing transcript quantification outputs (NumReads counts, abundance estimates) from two mapper implementations (e.
Develop pedagogical content knowledge for a topic by surfacing common misconceptions and effective representations.
Pedalboard is a Python library built by Spotify for working with audio: reading, writing, rendering, and adding studio-quality effects.
Audit academic peer review operations -- reviewer matching algorithms, conflict of interest detection, turnaround time optimization, review quality scoring, and editorial workflow…
Uses PeerTube's REST API and federation-aware platform features to automate video uploads, channel management, moderation queues, and instance operations.
Use when writing or editing any text that must read as human-written (posts, articles, channel content, work texts, resumes) so it does not look AI-generated.
Use when when you have a tandem mass spectrometry spectrum with a known or inferred peptide sequence that may contain post-translational modifications (phosphorylation,…
content-visibility:auto, contain-intrinsic-size, contain property, will-change discipline, container queries to reduce layout thrash for long lists/articles/dashboards/off-screen…
Use when you have identified a claim that one tool outperforms another (e.g., 'IDSL.IPA outperforms MZmine 2 and xcms') in a research article's abstract or introduction, but the…
Writes a structured monthly or quarterly YouTube channel performance report from raw analytics data, with metric summaries, trend observations, and specific next-step…
Draft performance reviews, self-assessments, peer reviews, and upward feedback in your own voice. Analyzes your contributions, emails, and meeting history via WorkIQ, then…
Pull Perplexity AI invoices/receipts, cross-reference with QuickBooks, and generate spend reports for finance handoff.
Channel Luca Rossi — author of the Refactoring newsletter (refactoring.fm), known for turning engineering-leadership reality into simple, named mental models across team-building,…
Channel James Stanier — CTO, author of *Become an Effective Software Engineering Manager* and *Effective Remote Work* — as a leadership advisor grounded in 161 of his blog posts…
Use when researching, outlining, drafting, revising, or polishing a personal blog article—an explainer, idea essay, personal essay, cultural review, or technical post—or when…
Content idea bank manager — captures, mines, and ranks post ideas for LinkedIn and Substack. Three modes -- /idea for instant capture (5s), weekly mine for source-sweep (4…
Polish-only editor for an existing draft. Removes AI tells, enforces platform rules, preserves voice. Output is a diff (what changed and why), not a wholesale rewrite.
Repurposes an existing post across platforms with full voice recalibration -- not copy-paste. Substack-long → LinkedIn excerpt+link, or LinkedIn → Substack short newsletter.
Cover Letter — drafts a voice-matched, JD-tailored cover letter capped at 350 words. Tier 4 main session. Anti-AI-tells gates.
Session Handoff — appends a session entry to this project's project-log.md, then prints a copy-paste prompt for the next session that points at that log.
STAR Story Extractor — Josh's unfair advantage. Mines OpenCode session DB, project-logs, account memory, meeting transcripts, prior work artefacts to extract…
Use when writing medical school personal statements, residency application essays, fellowship statements, or graduate school admissions essays.
Drafts a Substack piece from an idea ID + voice + platform rules + STAR bank for grounding. Two modes -- long (1000-2500w, Tier 4 Opus + adversary pass) and short (300-800w…
Write PR descriptions, PR messages, inline PR review comments, Slack messages, update comments, RFCs, design docs, and copy-pasteable summaries in Gui's writing style.
Translate internal markdown artifacts (pitch decks, business plans, research) into per-persona client-facing storefront surfaces in the client's domain language with ELI5/TLDR…
Use when the user asks for Content Repurposing from supplied source materials. Trigger language: content repurposing; video repurposing; webinar repurposing; turn recordings into…
Drafts, rewrites, and reviews prose in Petar's personal voice while removing generic AI writing patterns.
Review content against PatternFly and Red Hat voice and tone standards. Use when contributing to patternfly.org, writing UI copy for Red Hat products, reviewing design guidelines,…
pfcc_extras (Matlantis/ASE workflow utilities) を使うコード生成時に使用します。 可視化 (show_gui, view_ngl, SurfaceEditor)、構造加工 (smiles_to_atoms, LiquidGenerator, make_alloy, makesurface, 各種…
Write essays, articles, and blog posts in Paul Graham's voice — plain, spoken prose that reasons out loud and lands surprising true claims, not AI filler.
Generate safe, read-only PostgreSQL queries from natural language. Use when users need to query blog_small, ecommerce_medium, or saas_crm_large databases.
Build a meeting / interview prep packet for a booked conversation on a specific role. Triggers on "prep me for X", "build prep packet for X", "interview prep X", "/prep …
Phase agent for the 10th/terminal step of the pipeline (CTL-703). Performs all terminal wrap-up after monitor-deploy — verifies the PR merged, posts a final Linear comment with…
Use when responding to a Progress in Human Geography (PiHG) decision letter (major/minor revision) — building a point-by-point response to the editor and referees that strengthens…
Use when starting or navigating any Progress in Human Geography (PiHG) manuscript and you need the entry point.
필로의 블로그 글 작성. 질문연구소의 설립 과정, 개발 일지, 캐릭터 이야기, 교육 인사이트를 필로의 톤으로 블로그 글 초안을 생성한다. Trigger: "블로그 써줘", "필로 블로그", "개발일지", "/philo-blog"
Dựng bài giảng/clip giới thiệu hoàn chỉnh từ video talking-head quay thô trong thư mục xưởng (transcript, phương án cắt và overlay, đồ họa, timeline.json, assemble.py, nghiệm thu…
Nghiên cứu và thu thập tư liệu minh họa cho clip của người dùng - hình ảnh, video phụ trợ, số liệu trích dẫn - có kiểm định nội dung, nguồn gốc và bản quyền, tải về thư mục dự án…
Make outgoing phone calls, receive incoming calls, and pull up past call transcripts
Make AI-powered phone calls via Bland AI - book restaurants, make appointments, inquire about services. The AI calls on your behalf and reports back with transcripts.
Estimate the phoneme count and optional IPA transcription for one English word in a declared dialect, with uncertainty made explicit.
Sound systems of human language -- phoneme inventories, the International Phonetic Alphabet, articulatory and acoustic phonetics, phonological rules, suprasegmental features…
Apply reviewed text, layout, highlighting, title, or optional image changes to an owned PhonicsMaker story and return a new versioned PDF without overwriting the source.
Produce reviewable command or structured operations applied to an owned story, new PDF/thumbnail/JSON with validation, safety checks, and structured output.
Assemble a source-faithful photograph with a supplied editorial abstraction panel as a sharp comparison board, preserving orientation, aspect ratio, source provenance, and…
Write a publication-ready photo caption from an image description and story context — following the conventions of news photography captioning (who, what, where, when, plus a…
Arrange two to ten supplied photos into one intentional multi-panel or artistic collage while controlling source fidelity, crop, hierarchy, spacing, overlap, borders, material,…
Expert in photo content recognition, intelligent curation, and quality filtering. Specializes in face/animal/place recognition, perceptual hashing for de-duplication, scr — from…
Expert in photo content recognition, intelligent curation, and quality filtering. Specializes in face/animal/place recognition, perceptual hashing for de-duplication, scr — from…
Edit, resize, crop, filter, and optimize images using code-based image processing
Editor de foto senior estilo Photoshop/Lightroom/Capture One. Retoque avanzado, compositing, color science.
Rescue a photo library drowning in duplicates, screenshots, and 40,000 unsorted items — the triage order that shrinks first (screenshots, bursts, dupes), the album-vs-search…