Research & Search

guhcostan Skill

Initialize OKF knowledge base files in the current project. Use when the user wants to start documenting their project for claude-mega-brain, or when the user says "init mega brain", "setup the knowledge base", "cria o okf", "inicializa o mega brain", "quero usar o mega brain", "criar a estrutura do knowledge base", or asks how to get started with the plugin.

guhcostan Skill

Create or update a single OKF concept file from raw input. Use when the user wants to document a specific table, metric, API, service, or concept in the knowledge base — even if they say "add this to the okf", "documenta essa tabela", "cria um conceito pra isso", "adiciona no knowledge base", "register this API", or pastes a schema/description and says to save it. If no OKF files exist yet, suggest /mega-brain:init first.

hansohn Skill

Research pricing comparables for a secondhand item using live eBay sold listings and active Facebook Marketplace listings. Use whenever the user wants to know what a used item is worth, find resale comps, check sold prices, price an item for sale on Facebook Marketplace or eBay, or build a pricing recommendation for resale. Trigger on phrases like "what's this worth", "price comps", "sold for", "resale value", "list price for". Always pull live data via browser automation — do not rely on training data for current market prices.

jackhendon Bundle

Structure notes from a user research session into a clean debrief with insights, quotes, and implications. Paste your raw notes in and get a formatted summary ready for Notion.

jassonbla Bundle

Analyze git commit history and summarize recent activity from a mission or project perspective. Use for commit summaries, daily or weekly progress reviews, author-specific work summaries, team activity reviews, release-note prep, or understanding what changed in a repository over a time window.

boom5426 Bundle

Use when the user wants a recent literature sweep for Awesome-Virtual-Cell, especially for latest papers, Nature-family journals, major labs, big groups, or a time-bounded update of what the README is missing.

castorini Bundle

Use when validating ragnarok generate outputs — checks TREC format compliance, citation integrity (valid indices, non-empty references), response length bounds, and JSONL structure. Wraps `ragnarok validate` plus custom assertions. Use after running generate or convert to verify output correctness.

chanuk0 Bundle

Verify a chosen topic against primary sources and turn a pile of links and notes into a one-page brief that later skills can build on. Use for "look into this link", "write this topic up", "research this properly", "check whether this is still open", "what do we actually know about this", or when handed an event, program, product, or announcement URL and asked to sort it out. Produces the input that blog-post and carousel-post consume. Finding a topic in the first place is topic-scout; drafting the actual post is blog-post or carousel-post.

chatlab Bundle

Query and analyze imported ChatLab chats with clb: find evidence, summarize topics, and compare activity or relationships. 查询和分析 ChatLab 已导入聊天记录：查找证据、总结话题、比较活跃度或关系。

kalpakprod Skill

Internal Wheel researcher for live quick and deep market passes. Use only from wheel after it has created a run and selected source routes; normalize every adapter result before it reaches the run record.

kevintsai1202 Bundle

Exports the local knowledge base (knowledge-base/, experience/) and ChromaDB vector data as JSONL, then backs it up to a dedicated private GitHub repository. Also supports cross-device restore from GitHub. Typically invoked by deep-memory after new knowledge-base or experience entries are written in a session, but can also be run directly by the user at any time to back up or restore.

kin0992 Skill

**UTILITY SKILL** - Generate a classic Git commit message from a staged diff. USE FOR: write commit message, generate commit message from diff, summarize staged changes, create commit text, compose git commit. DO NOT USE FOR: generating PR descriptions (use pr-title-description), writing changelog entries, conventional commits format. INVOKES: git diff --staged for reading staged changes. FOR SINGLE OPERATIONS: Use git commit -m directly for trivial one-liners.

kin0992 Skill

**UTILITY SKILL** - Generate a pull request title and description from a branch diff. USE FOR: write PR description, generate pull request title, summarize branch for reviewers, create PR body from commits, draft pull request. DO NOT USE FOR: writing commit messages (use commit-message skill), code review feedback, changelog generation. INVOKES: git log and git diff for reading branch changes, file reading for PR templates. FOR SINGLE OPERATIONS: Use git log --oneline directly for a quick branch summary.

nord342 Bundle

Process meeting notes, transcripts, or recordings into a clean recap, a tracked cross-meeting action list, and follow-ups. Activate whenever the user shares meeting notes, a call/Zoom/Teams/Granola/Fireflies transcript, a .vtt/.srt caption file, or raw bullets from a meeting, OR asks to "write up", "summarize", "recap", "take minutes from", or "pull action items from" a meeting. This skill defines the shared conventions (file layout, recap format, action ledger) used by /meeting-notes:recap, /meeting-notes:actions, and /meeting-notes:followup.

oliver-kriska Bundle

Clean up a scribe knowledge base — split bloated articles, expand or merge thin stubs, archive overgrown rolling files, and merge KB-self-named directories. Use when `scribe lint` reports content-quality warnings (bloated article, thin article, rolling file overgrown, directory named after the KB), or when the user asks to tidy, prune, split, archive, or de-clutter their KB / scriptorium.

pass-with-high-score Skill

High-autonomy "chef" for implementing new features from scratch. Handles code scanning, architectural research, technical specification, and full-stack implementation with a focus on "clean code" and project idiomatics. Use when the user says "cook this feature", "implement X", or "build Y".

sameergdogg Bundle

**Job Application Analyzer**: Analyzes job descriptions against the user's resumes and achievement history to provide tailored resume suggestions, a brief intro blurb, company research, and compatibility assessments. Use this skill whenever the user shares a job posting URL or job description and wants help applying, tailoring a resume, writing a cover letter, evaluating fit, or researching the hiring company. Also trigger when the user mentions "job", "apply", "application", "job description", "JD", "resume review", "cover letter", "fit check", or "compatibility" in the context of job searching. Even casual mentions like "check out this role" or "what do you think of this job" should trigger this skill.

sanoakr Skill

Build a reusable knowledge base of personas from Gmail history — one file per sender or department — and use those personas to answer questions and draft emails in the right style. Use this skill whenever the user wants to: - "build personas from my Gmail" - "create a contact knowledge base from email" - "who usually contacts me about X?" - "draft a reply to [person/department] in their style" - "what writing style does [department] use?" - "summarize how [person] communicates" - "create a self-persona from my sent emails" - "analyze my email communication patterns" The skill guides the full workflow: search → index → persona files → Q&A / email drafting. Trigger even when only part of this workflow is mentioned.

seokhoonj Skill

Summarize a Korean company's key financial accounts (revenue, operating and net income, total assets/liabilities/equity) from OpenDART. Holds no logic of its own -- it calls the opendart-client package's CLI (`opendart finance`) and shows the result to the user. Trigger phrases: 재무 요약, 재무제표, 주요계정, financials, 매출 영업이익, 재무 보여줘, 실적 어때.

serenorg Bundle

Research Analyst - virtual employee

seungyeop-lee Skill

Summarize ready issues and current in-progress state. Runs only on explicit invocation.

tdkn Skill

Use this skill when the user wants a reviewer-ready GitHub pull request body that follows the repository PR template, or a concise summary of branch changes for reviewers. Apply for informal asks like "write the PR", "improve the PR body", or "summarize this branch" even when they do not mention templates or GitHub explicitly.

terrylica Bundle

Research CKVD codebase for implementation details, patterns, or architecture questions. TRIGGERS - how does FCP work, understand data flow, find code, explore codebase, architecture questions.

the-focus-ai Bundle

This skill should be used when the user asks about "youtube", "my videos", "my channel", "youtube search", "video comments", "playlists", "list videos", "channel stats", "video details", "download video", "get transcript", "video subtitles", "summarize channel", "latest videos from channel", "video timestamp", "link to timestamp", or mentions YouTube operations. Provides YouTube Data API integration and yt-dlp for downloading videos, transcripts, and metadata from any channel. Includes workflow for comprehensive channel video summaries.

tianxiao1430-jpg Bundle

Advanced research skills using Z.AI Web Search Prime to synthesize technical information.

tmchow Bundle

yt-dlp. Use when the user wants to download, extract audio, pull subtitles, clip, or archive a YouTube or other streaming-site URL, or when yt-dlp hits 403, bot-check, or only-360p. Not for local-file edit/transcode, watch/summarize without saving, search, or generic downloads.

torpedod Bundle

Collects evidence from web sources (Crawl4AI) and local documents (Docling), applies quarantine classification, deduplication, and provenance tagging.

lesliexqing Bundle

Financial market analysis skill. Trigger when the user asks about any stock, sector, industry, market event, or macro trend — in any language or market. This includes single stock lookups ("how's NVDA doing"), sector analysis ("半导体板块趋势"), event impact analysis ("how do tariffs affect chip stocks"), and macro research ("is the AI capex cycle slowing"). Works for A-shares, Hong Kong, US, Japan, Europe, crypto, commodities. Even casual one-line questions should trigger this skill.

liamrjohnston Bundle

Add cached official-asset and product research preflight before reference selection and build authorization.

parallel-web Skill

DEFAULT for all research and web queries. Use for any lookup, research, investigation, or question needing current info. Fast and cost-effective. Only use parallel-deep-research if user explicitly requests 'deep' or 'exhaustive' research.

polyarch Skill

Consult Gemini as an independent expert with deep web research. Sends a question or task to Gemini CLI and returns a research-backed response.

phelps-sg Skill

Read and write notes in the shared Obsidian knowledge base

qepo17 Bundle

Turn an idea not yet represented by a Jira or GitHub ticket into an evidence-backed, outcome-oriented ticket draft. Research repository/docs first, clarify only material unknowns with a cumulative maximum of 10 questions, and publish only with explicit authorization. Optional preparation, not an execution prerequisite; reuse existing tickets rather than duplicate them.

quietdaemon Skill

Read and summarize the nightly self-review logs a reflection cron writes about your assistant's recent activity. Use when the user asks what the assistant 'noticed', for recent reflections / self-reviews, or whether any patterns showed up.

ray0907 Bundle

Internal guidance for composing Codex prompts for coding, review, diagnosis, and research tasks inside codex-rescue

gnurio Skill

Use this skill after /pmf-research-synthesis has identified the riskiest PMF dimension. Takes that dimension (or any business idea/strategy) and runs a structured assumption extraction, mapping, and experiment design sequence. Triggers include: 'validate my riskiest dimension', 'extract assumptions', 'what are the riskiest assumptions', 'run assumption mapping', 'design an experiment', 'pressure test this', 'what could go wrong with this', or any request to surface and test specific assumptions before committing resources. Runs a guided Extract → Map → Test workflow.