deep-research
Deep research expert for building comprehensive knowledge maps from first principles. Use when the user wants to deeply understand a topic — its origin, the…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
Writing & research
13,988 results
project-documentation
Create non-technical documentation for project features in the docs/ folder. Use when documenting completed features, writing feature documentation, explaining…
writing-sigma-rules
Author and maintain Sigma detection rules — structure, logsource taxonomy, detection logic with modifiers, false-positive filtering, backend conversion with…
writing-yara-rules
Author durable YARA detection rules — meta/strings/condition anatomy, string types and modifiers, structural conditions with file magic and offsets, the…
noise2blog
Turns rough notes, bullet points, voice transcripts, or tweet dumps into a polished, publication-ready blog post. Optionally enriches with Tavily research to…
product-update-logger
Tell the skill what your product shipped. It writes a polished dated entry to a living docs/changelog.md and produces a ready-to-use content package: tweet…
show-hn-writer
Draft a Show HN post backed by real HN performance data. Uses observed patterns from 250 top HN posts to maximise score.
content-linkedin
LinkedIn post generation with professional brand voice adaptation. Use when user wants to create a LinkedIn post, professional update, or LinkedIn content.
agent-survey-corpus
Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.
evidence-draft
Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence…
grad-paragraph
Write one survey-quality paragraph from evidence packs (tension → contrast → evaluation anchor → limitation).
research-pipeline-runner
Run a research Workflow end to end when the user requests a survey, brief, review, tutorial, or idea exploration; route an unbound goal, execute one eligible…
section-merger
Deterministically merge the final fingerprinted section snapshot into `output/DRAFT.md`, preserving outline order and inserting transitions only when…
literature-reader
Read, analyze, and summarize academic literature (PDF papers) to generate structured literature summary notes. Core capabilities: paper metadata extraction, research question identification, methodology analysis, experimental results analysis, personal evaluation generation, and cross-comparison of multiple papers. Supports Chinese and English papers, single-paper close reading, and batch literature reviews. When users provide PDF paper files and request literature reading, paper summarization, literature review, paper summary, paper close reading, paper...
nerdbot
Use when creating, repairing, querying, auditing, or migrating Obsidian-native git KBs with raw/wiki layers. NOT for docs sites or generic notes.
forge-novel-fusion
Fuse multiple distilled novel style profiles into one curated fiction style profile by taking selected strengths from each author style and rejecting weak or…
forge-novel-style
Distill an author's fiction prose style from user-provided novel samples into a reusable local style profile for later novel writing. Use when the user asks to…
use-novel-style
Write, continue, or revise fiction using a distilled novel author-style profile from novel_styles/{name}/style.json. Use when the user asks to write a…
focus-friendly
Make dense or complex information easier to understand, navigate, remember, and act on through clear layers, concrete examples, and visible progress. Use when…
storytelling-hooks
Use when writing any short-form video script, hook, opening line, or scroll-stopping content (TikTok, Reels, Shorts) for any niche or business — when the first…
baseline-selection-audit
Audit ML/AI experimental baselines for necessity, fairness, currency, and reviewer risk. Use when choosing baselines or checking SOTA comparisons.
deep-research
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when…
generar-prd-conversacional
Trigger: PRD, product requirements, definir producto, idear proyecto, armar spec de producto. Genera un PRD sección por sección conversando con el usuario —…
literature-search
Systematic literature review methodology including search strategy, screening, and synthesis. Use when conducting literature reviews or writing background…