Research & Search

v8 Skill

Guides the methodology for investigating V8 concepts, codebase structure, performance, memory, and architecture. MANDATORY to use whenever triaging bugs, investigating crashes, reading C++ files, analyzing compiler optimizations (Ignition, Maglev, TurboFan, Turboshaft), or doing static research on V8 subsystems. Essential for locating high-level design documents in the local docs/ directory before reading C++ code. Do not use for raw build commands or Git workflows.

zgiai Bundle

Summarize and distill existing content from pasted text, chat context, or already parsed attachment content into summaries, TL;DR, key points, action items, risks, conclusions, decisions, meeting notes, or requirements summaries. Use when the user asks for 总结, 摘要, 提炼重点, 归纳, 归纳需求点, 行动项, 风险, 结论, 会议纪要, summarize, summary, TL;DR, key points, action items, risks, conclusions, decisions, or meeting notes.

lu1sdv Bundle

Use when sink subagents encounter unseen languages or new technique categories that require fresh comprehensive research — not well-known sinks. Orchestrates parallel research swarms with structured JSON citations. Triggers: "comprehensive", "exhaustive", "most complete", "deep dive", "unseen language", "new technique category", "long horizon", "parallel research".

afadtc Bundle

DTC 用户洞察与市场探索引擎——VOC 深度挖掘、市场规模评估、用户画像、赛道分析、竞争格局映射。Use when user mentions: 市场调研, market research, 用户洞察, user insight, VOC, 用户画像, persona, 市场规模, TAM SAM SOM, 赛道分析, 品类分析, category analysis, 需求挖掘, 空白市场, 用户研究.

ahmedhamadto Skill

Queryable knowledge base of community-proven patterns and gotchas for technology combinations across the 15-domain Tech Stack Taxonomy. Use when evaluating stack choices, diagnosing production issues, asking how to correctly combine specific technologies, looking up best practices for a particular technology pattern, or feeding the Stack Compatibility Oracle.

cdeistopened Skill

Route any Amazon KDP self-publishing question to the right skill, framework, or transcript search. Use when someone asks about publishing on Amazon, wants niche research, needs keyword help, or says 'ask kdp.' This is the main concierge -- it figures out what the user needs and dispatches to the right specialist skill.

cdeistopened Skill

Generate pain-point-driven book outlines with 10 title/subtitle options and 8-chapter structures. Use after niche and keyword research is complete.

jerseycheese Skill

Close out the current chat with a tight summary and a sweep of the current project's durable context files — memory entries, status and task docs, plan files, and any project-specific reminders — so nothing important dies in the transcript. Trigger on /wrap-it-up, "wrap it up", "wrap up this chat", "close out this conversation", "end of chat", "summarize and clean up", or any end-of-session housekeeping request. Pairs with /handoff (which preps a new chat) — wrap-it-up is the backward-looking bookend.

microsoft Bundle

Use when asked to review code, review a branch, or do a code review. Spawns Breaker (correctness) and API Analyst (compatibility/conventions) sub-agents while the orchestrator reviews architecture, tests, performance, and security.

mopeyjellyfish Bundle

Research a topic with repo and current-source evidence. Use when findings should sharpen shaping, review, or planning.

questnova502 Bundle

Analyze market conditions, geographic opportunities, pricing, consumer behavior, and product validation across Google Maps, Facebook, Instagram, Booking.com, and TripAdvisor.

tamircohen28 Bundle

Use when you need to hand a decision back to the user as a plain-language summary plus a choice menu — after finishing work and needing the user to pick how to proceed, when told "waiting for your decision about X", or when the user says "display decision", "what's the decision on/about X", "show me my options for X", "let me choose", "walk me through the open decisions", "what are my action items", or gives a GitHub issue/PR number or URL to summarize and choose from.

wicttor Bundle

Perform local and external research to inform technical design decisions during planning.

together2329 Skill

External reference-database expert. Before authoring new RTL — or answering from assumed knowledge — consult the configured external DB for proven, authoritative references instead of reinventing. The DB is typically a prior-project / vendor RTL corpus (e.g. Andes peripherals: UART, SPI, I2C, GPIO, DMA, AHB bus matrix, bridges, timers), but it is NOT limited to RTL: it can hold spec excerpts, reference designs, datasheets, or any prior-art knowledge wired in by the deployment. Trigger on: external db, reference db, reference design, prior art, reuse, existing rtl, previous project, knowledge base, and common peripheral/bus families (uart, spi, i2c, gpio, dma, apb, ahb, bus matrix, bridge, timer, watchdog, rtc, fifo).

cloudvoyant Bundle

Builds high-quality, literature-grounded, graduate-level interactive textbooks as diffbook MDX. Triggers on: "ed explore", "ed plan-syllabus", "ed plan-module", "ed create-lesson", "ed create-quiz", "ed create-project", "ed autodidact", "ed update", "ed doctor", "ed help", plus natural language like "build an interactive textbook", "create a course on", "study syllabus for", "graduate lesson on", "quiz me on", "course project for", "fix/repair a diffbook book", "unbork an ed book". Unified dispatcher — pass a subcommand as the first argument.

cloudvoyant Bundle

Pure technical exploration: research a problem space, compare technical approaches, compare repos, and generate decision-oriented proposals. No code is written. Triggers on: "explore new", "explore diff", "explore allow", "explore help", "technical exploration", "research approaches", "explore options", "compare repos", "how does X work".

jackchuka Skill

End-to-end workflow for taking a new tool idea from research to working MVP. Use when the user has an idea for a CLI tool, library, or small project and wants to go from concept to initial implementation. Triggers on "I have an idea for a tool", "build a new CLI", "create a new project", "kickoff new tool", "I want to build", "let's build a new", "新しいツールを作りたい", "CLIを作る".

jackchuka Skill

Summarize recent communication activity from Slack and meeting recordings. Use when the user wants to know what happened on Slack, review meeting action items, find mentions, or get a communication summary. Triggers on "summarize Slack", "meeting action items", "what was discussed", "activity summary", "search my mentions", "highlight of the day", "/activity-digest".

joneqian Skill

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear.

juicesharp Skill

Surgically fix ONE artifact (research, plan, or any doc) to clear the failing dimensions a grade panel flagged — reads the artifact plus its dimension verdicts, applies only the cited findings' feedback, and re-emits the artifact in place. Single-pass, no subagents, no self-review, no questions. Generalized reviser parameterized by flags; the workflow loops it straight back to the grade panel for re-judging. Use as a gate's revise stage.

juicesharp Skill

Decompose a research artifact into independent vertical slices — each a self-contained, separately-designable unit — and write a slice map to .rpiv/artifacts/slices/ with a machine-readable `slices:` frontmatter array. A research artifact is required (it is the cut's grounding); confirms the decomposition with you before writing. Also runs in RE-SLICE mode (`--slices <map> --slice-verdicts <v>…`) to STRUCTURALLY re-cut a slice map that failed the design-readiness gate — splitting epics, completing under-cited footings, redistributing frozen coverage units, breaking dependency cycles, renumbering — which a surgical reviser cannot do. Feeds a per-slice design fanout.

juicesharp Skill

Derive an executable acceptance inventory from the verbatim goal — the ID'd observable outcomes the finished work must exhibit, each with a runnable evidence command where one can be derived — and write it to .rpiv/artifacts/acceptance/ in one non-interactive pass. Authored BEFORE any plan exists so the standard of completion cannot inherit the plan's scope: the plan later addresses or explicitly defers each item, the grade panel's completeness dimension anchors on the inventory, and validate executes the evidence commands against the finished tree. Dispatched by the ship and build presets between research and planning.

juicesharp Skill

Merge N independent per-slice designs (plus the research they rest on) into ONE coherent phased plan in .rpiv/artifacts/plans/ — reconciling cross-slice overlaps, wiring inter-slice integration, and ordering phases by slice dependencies. Single-pass, no subagents, no self-review. The fan-in barrier of a fanout-and-synthesize flow — one phase per slice, plan-compatible so implement/validate consume it unchanged. For large slice maps it also runs hierarchically — as a per-cluster partial (`--as-subplan` turns designs into a subplan) and as the root merge (`--subplans` turns subplans into a plan) — so no single pass must hold every design at once. Use after a per-slice design fanout.

juicesharp Skill

Design ONE vertical slice from a slice map in isolation — its architecture decisions, file map, key interfaces, integration points, and success criteria — and write a per-slice design doc to .rpiv/artifacts/designs/. Single-pass, no research subagents, no self-review; asks the user only when a genuine design fork blocks the slice. Dispatched once per slice by a design fanout; the per-slice designs are later merged by synthesize. Use as a fanout unit, not standalone.

legioncodeinc Bundle

Research a person, build a dossier on someone, vet a business partner, prep for a negotiation, verify what someone told you, or brief yourself before a meeting with a named individual. Fuses your entire Littlebird record of that person, every message thread, meeting, calendar invite, and screen sighting, into a dated relationship timeline with receipts, then reconciles it against external research. Use it for partner diligence, prospect research, negotiation prep, and claim verification. Not for employment screening.

legioncodeinc Bundle

Research a topic and get the delta, not another wall of reading. Trigger on 'research this topic', 'what do I already know about', 'catch me up on', 'synthesize what I have read', 'is what I think about this still true', 'deep dive on a topic', 'what did I miss on', 'brief me on'. Pulls what the user has already encountered on screen and in messages about the topic, layers a fresh external sweep over it, and returns a synthesis split into what they already had, what is new since then, where the sources disagree, what they appear to believe based on what they actually said, and what is still open. Every external claim carries a URL. Optional recurring mode watches a standing topic and reports only what is new.

hoetaek Bundle

Use to carry a LEAF sprout after Learn from ③ Example through a shipped result: validate one cheap instance against criteria, design the generator, run the critic, slice the task graph, draft or execute, and review. Use for documents, essays, articles, memos, research papers, proposals, reports, specs, study notes, presentations, prototypes, code, or mixed deliverables in a repo-local `.leaf/` workspace. Enter after ① Intent and ② Unknowns & Context pass in `learn`. Trigger on criteria, 와이어프레임, 설계, task graph, 작업 쪼개기, 초안 작성, 실행, 리뷰, or 검토 절차. For vague, early, or idea-stage work, use `learn` first.

skills-il Bundle

Verify a public claim against official Israeli data and return a sourced verdict. Use when checking a politician's statement, a viral WhatsApp or X message, a news headline, or any factual claim about Israeli inflation, prices, the state budget, government spending, exchange rates, Knesset votes, election results, housing prices, wages, unemployment, crime, or NGO and foreign-donation funding. The skill isolates the checkable assertion, routes it to the right official source (CBS, Bank of Israel, BudgetKey, Knesset, data.gov.il), pulls the figure, and labels the claim נכון, לא מדויק, מטעה, לא נכון, or לשיפוטכם with a full citation trail, or אין מספיק נתונים when no source confirms it. This matters because a hallucinated number is worse than no answer. Hebrew triggers: בדיקת עובדות, אימות טענה, פייק ניוז, האם זה נכון. Do NOT use for opinions, predictions, private personal facts, or writing articles from scratch.

skills-il Bundle

Navigate the Israeli education system including Bagrut (matriculation) exams, psychometric entrance test (PET), university admissions, and Ministry of Education school data. Use when user asks about Israeli schools, Bagrut requirements, psychometric exam, "psichometri", Israeli university admissions, sekhem calculation, Israeli education levels, Hebrew education terms, or school data from Ministry of Education. Covers K-12 system, exam structure, and higher education admissions. Do NOT use for non-Israeli education systems or post-graduate academic research.

microsoft Skill

Research and plan a large-scale change, then execute it in parallel across isolated agents that each open a PR.

moonlarry Bundle

Run a one-question-at-a-time innovation-gate interview before algorithm design, experiment planning, or paper drafting. Use to test whether a research problem extends the knowledge boundary, whether existing methods or direct transfer already solve it, and whether proposed components map to defensible subproblems and evidence. Always write paper/PAPER_IDEA_GRILL.md, including a conditional or not-ready diagnosis. Do not use for completed-experiment claim judgment, post-paper evidence auditing, manuscript review, or prose rewriting.

moonlarry Skill

Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.

nearform Skill

Summarize the user's recent workout history — sessions this week, current streak, planned-vs-actual hit rate, muscle-group balance, and progression trends. Reads the per-day logs in ~/workout-coach/logs/ (plus profile.md for targets). Use when the user asks "how am I doing", "show my stats", "what's my streak", "weekly summary", "am I making progress", or similar.

owl-listener Skill

Coordinate research operations across a program.

renky1025 Bundle

Knowledge base distilled from "Clean Code: A Handbook of Agile Software Craftsmanship" by Robert C. Martin (Uncle Bob). Use when applying Uncle Bob's frameworks for meaningful names, small functions, comments, formatting, objects vs data structures, error handling, boundaries, unit tests / TDD, class design (SRP), systems, concurrency, refactoring, and code smells; studying the book; or referencing its concepts during code review, cleanup, or TDD work.

rudrathegreat Skill

Compare astronomy papers across datasets, methods, assumptions, measurements, and conclusions.