rn-wechat-extract
Extract full text from WeChat public account articles (mp.weixin.qq.com). Use when the user provides a WeChat article URL and asks for 提取文章, 抓取公众号, 读一下这篇, or…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
Writing & research
13,999 results
8d-report-writing
Submit an 8D to a customer, format a Ford 8D report, BMW G8D, VW QMSS, or OEM complaint response for formal submission. Covers OEM-specific format…
x-writing
Transforms notes into X (Twitter) posts. Triggers when user asks to create social content, draft tweets, or turn notes/ideas into posts.
reframe-voice
Write, rewrite, or review content in the evidence-led reframe voice style. Use when the user explicitly asks to write in "reframe voice" or "reframe style". Do…
personas
Apply one or more expert lenses to feedback, critique, or guidance.
shunk031-writing-kosshi
Organize and rewrite articles and notes into an outline bullet list consisting of claims and the evidence supporting them. Use this for requests such as "write an outline" or "organize the points in bullet form." Do not use it for listing items or task management. When creating slides, do not launch it on its own,`shunk031-writing-technical-slides` skill…
shunk031-writing-technical-slides
Rewrite technical explanation and paper introduction slide text into a structure where the hierarchy of sections and items within slides is clear at a glance. Do not use it for general telegraphic style, recap sentences, slide visual design, or file creation.
shunk031-writing-telegraph
Compose and rewrite articles and notes into telegraphic-style skeleton bullet points that convey one item per line, omitting words understood from context. Use for requests like "write a report," "make it an HTML report," "in telegraphic style," and "shorten the bullet points." Do not use for requests that merely proofread or polish a report while keeping it in paragraph form. On technical slides, do not launch it on its own; `shunk0…
source-trace-wx
After the agent answers, trace the original basis and sources of that answer. Use when the user says "check the source", "show sources", "where is the original basis", "what is the source of this answer", or wants to verify the URLs/documents used to support an answer; first list the sources the agent actually read in the conversation, then for claims without sources go check primary sources, and write it into a Markdown file.
topic-agent
Topic selection system master control Agent. Coordinates the three stages of hotspot collection, topic generation, and topic review, supporting iteration until qualified topics are produced. Trigger methods: (1) "Start today's topic selection" starts the complete process (2) "Today's AI hotspots" only collects hotspots without generating topics (3) "I have a topic" enters single topic analysis (4) "Recommend some good topics" directly outputs recommendations. Output is saved to the Obsidian topic library.
ad-copywriting
Use this skill when writing ad copy — headline formulas, visual direction, and voice-of-customer sourcing that makes ads specific instead of generic.
mdpreview
Catppuccin-themed live-reloading Markdown viewer with multi-tab support, margin annotations, sidebar TOC, and Chrome --app mode. This skill should be used when…
update-documentation
Coordinate docs.tenzir.com updates alongside code changes. Use when preparing the `.docs/` checkout, creating a matching docs branch, opening a `tenzir/docs`…
research-library
Use when working with, adding to, or updating the shared cross-project research library at $RESEARCH_HOME (vendor repo clones, reference PDFs/epubs, mirrored…
academic-paper
12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebut…
best-practices-researcher
Researches and synthesizes external best practices, documentation, and examples for any technology or framework. Use when you need industry standards,…
obsidian-vault-search
Search an Obsidian vault three ways — Meilisearch for topic and fuzzy queries, ripgrep for exact strings/tags/task glyphs, and a date-aware helper for…
anchor-sheet
Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of…
limitation-weaver
Rewrite limitation passages so the paper keeps limitations without falling into count-based slot phrases (e.g., \"Two limitations…\") across many H3s.
module-planner
Use when a tutorial concept DAG exists and the run needs an ordered teaching plan with objectives and outputs.
post-merge-voice-gate
Post-merge paper-voice gate: inspect the reader-facing draft for planner-talk and axis-label artifacts, then route fixes to the actual source.
survey-seed-harvest
Identify survey/review papers in a retrieved set and extract taxonomy seeds into `outline/taxonomy.yml` (topics/subtopics/terminology).
survey-visuals
Draft non-prose visuals artifacts (timeline, figure specs) for a survey, grounded in evidence and using citation keys from `citations/ref.bib`.
table-filler
Fill `outline/tables_index.md` from `outline/table_schema.md` + evidence packs (NO PROSE in cells; citation-backed rows).