subsection-briefs
Build per-subsection writing briefs (NO PROSE) so later drafting is driven by evidence and checkable comparison axes (not outline placeholders).
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
Writing & research
13,979 results
novel-use
Top-level fiction writing and review workflow for using distilled novel styles without turning outlines, settings, rules, or procedures into lifeless prose.…
artifact-evaluation-prep
Prepare research artifact packages for evaluation or public release. Use for reproduction commands, environment checks, data packaging, and artifact forms.
experiment-report-writer
Write structured experiment reports from notes, configs, logs, metrics, tables, and figures. Use for result analysis, research updates, and presentation-ready…
architect
Research-backed evolution advice for your knowledge system. Analyzes health reports, friction patterns, and derivation history to propose specific changes with…
ask
Query the bundled research knowledge graph for methodology guidance. Routes questions through a 3-tier knowledge base — WHY (research claims), HOW (guidance…
study
Use this skill when the user wants to read, study, analyze, or deeply understand a research paper (PDF).
alterlab-pra-pr-writer
This skill should be used when the user asks about "press release", "media kit", "crisis communication", "PR writing", "public relations writing", "corporate…
alterlab-rma-abstract-writer
This skill should be used when the user asks about "writing an abstract", "abstract format", "structured abstract", "IMRAD abstract", "conference abstract",…
alterlab-rma-proposal-writer
This skill should be used when the user asks about "research proposal", "grant application", "funding proposal", "grant writing", "research justification",…
inbound-plan-work
Split a shared growth strategy or inbound branch artifact into one level of Paperclip backlog work items for inbound, content-led, or channel-led acquisition.…
bianchuihuo-2-0-longform
Edge Quenching 2.0 long-form creation workflow. Used for writing WeChat official account/Substack/long thread long-form articles around 2.0 themes such as AI, business, making money, one-person business, content monetization, market feedback, product hypotheses, and the business game. You must first read the local content management library and content benchmarking library nodes, expand surrounding nodes, and then assemble the logic chain; parallelism, listing synonymous sentence patterns, vague golden lines, and writing out of thin air without reading the library are prohibited.
cuihuo-judgment
Step 3 of the content creation pipeline: grind a judgment blank into shape—the trio (common-sense position → reversal → mechanism) plus nails. AI does differential diagnosis, writes prescriptions, asks follow-up questions to midwife it out, and challenges it from the opposing side. Not a single word of the judgment's body text is ghostwritten. Trigger: /cuihuo-judgment, "help me grind this judgment," "judgment shaping," "grind a judgment"
cuihuo-system
A system-learning tool for edge quenching. It is used to faithfully read through a book, a finite set of texts by one thinker, a school of thought, a set of theories, a book series, or a complex knowledge system: it does not require the user to presuppose a learning purpose; first freeze and completely read the finite source, reconstruct the original system's own structure, prepare the complete set of read-through lecture notes in one go, and then accompany the user through continuous reading; after the first pass ends, redraw the map, and select nodes to hand to /cuihuo-learning only according to real questions…
cuihuo-verification
A concept-flipping tool for edge quenching. It helps users see the metaphors, rules, confusions, and causal inversions hidden beneath a "taken-for-granted" concept, guiding users to complete the flip themselves. Two entry points: bring an old concept to test it, or bring an existing flip to deepen it. The flip must be spoken by the user themselves—AI…
claim-source-verification
Use when a manuscript's claims need to be checked against the sources cited for them, when literature search results must be verified before they enter a…
logline
This skill provides logline (hook) writing techniques for screenplays. Covers the four components (characters, conflict, setting, action), formulas for…
doc-sync
Check documentation consistency across README, man page, and help screen
deep-research
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review,…
lead-writer
Generate the opening lead section of long-form DR copy — the first 200-500 words that determine whether the prospect reads or bounces.
post
Use when writing a social post on a topic or a reply to someone's post — X/Twitter, LinkedIn, Bluesky, Threads — and the obvious take is not good enough.…
market-analysis
[Research] Use when you need to analyze market landscape: competitors, sizing (TAM/SAM/SOM), trends, SWOT, customer segments.
game-architect
Comprehensive game MVP interviewer and planner. Interviews you in progressive groups, researches genre conventions and reference games, then produces an…
oma-docs
Check documentation references, sync docs to code changes, and detect translation drift. Use for documentation maintenance in a repository.