Research & Search

dabit3 Bundle

Index a codebase with GitNexus and serve an interactive knowledge graph via web UI + Cloudflare tunnel.

dabit3 Bundle

Public-records OSINT investigation framework — SEC EDGAR filings, USAspending contracts, Senate lobbying, OFAC sanctions, ICIJ offshore leaks, NYC property records (ACRIS), OpenCorporates registries, CourtListener court records, Wayback Machine archives, Wikipedia + Wikidata, GDELT news monitoring. Entity resolution across sources, cross-link analysis, timing correlation, evidence chains. Python stdlib only.

egohygiene Skill

Create, revise, split, or validate implementation-ready `.spec.md` files from ideas, requirements, architecture, research, or existing systems. Use when defining a durable scope contract with goals, non-goals, requirements, boundaries, interfaces, implementation phases, validation, acceptance criteria, and open questions.

griddynamics Bundle

To run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.

griddynamics Bundle

To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.

griddynamics Skill

Workflow for deep project research with grounded references, parallel exploration, etc.

clawlink-hq Skill

Fathom integration for AI agents via ClawLink — browser login, no API key setup. Connect Fathom through ClawLink's hosted setup to record, transcribe, and summarize video meeting notes. Use this skill when the user wants to work with Fathom (Communication) — connect Fathom, read or update Fathom data, or take actions in Fathom from chat instead of saying you cannot access it.

xjtulyc Skill

Use this Skill to structure research grant proposals: NSF/NIH Specific Aims, budget justification, ERC narrative sections, structured abstracts, and biosketch formatting.

xjtulyc Skill

Use this Skill for bibliometric analysis: author h-index, citation counts, co-authorship networks, co-citation analysis, bibliographic coupling, and VOSviewer-compatible output.

xjtulyc Skill

Use this Skill for statistical power analysis in psychological research: t-tests, ANOVA, correlation, regression, mediation, and simulation-based designs with Python.

xjtulyc Skill

Philosophy literature search: SEP web scraping, PhilPapers API, systematic review, citation tracing, and Chicago-style bibliography generation.

xjtulyc Skill

Use this Skill when the user needs to search academic literature, collect papers for a systematic review, or find the latest research on any topic. Covers cross-database search via OpenAlex API, Semantic Scholar API, and arXiv API, with deduplication, citation snowballing, BibTeX export, and annual trend visualization.

xjtulyc Skill

Use this Skill when conducting a systematic literature review following PRISMA 2020: PICO framework, database search strategy, title/abstract screening, full-text eligibility, data extraction, and GRADE evidence grading.

xjtulyc Skill

Use this Skill for operations research and optimization: LP/QP/MILP with cvxpy and OR-Tools, convex relaxation, sensitivity analysis, and Gurobi/GLPK solver interface.

jsgforever Bundle

This skill should be used when the user asks to "research code", "how does X work", "where is Y defined", "who calls Z", "trace code flow", "find usages", "review a PR", "explore this library", "understand the codebase", or needs deep code exploration. Handles both local codebase analysis (with LSP semantic navigation) and external GitHub/npm research using Octocode tools.

tuanductran Bundle

Help HR operations teams and digital HR leaders design, implement, and optimize employee self-service programs including ESS portals, HR chatbots, knowledge bases, and manager self-service tools. Use when asked to build an employee self-service portal, design an HR chatbot, create an HR knowledge base, reduce HR inquiry volume, or improve employee access to HR information.

dreamlab-ai Bundle

Generate Minecraft Java Edition worlds from real-world geographic data. Converts OpenStreetMap buildings, roads, water, and terrain into playable Minecraft worlds using the arnis Rust engine. Integrates with QGIS for geospatial analysis, Blender for 3D terrain preview, ImageMagick for elevation processing, and perplexity-research for location enrichment. Use when converting a real place (city, landmark, campus) into a Minecraft world, geocoding a location to a bounding box, fetching OSM features for an area, or building test/educational voxel worlds from geography. Triggers: "make a Minecraft world of <place>", "OSM to Minecraft", "arnis", "generate a voxel world from coordinates". NOT for fictional world-building with no geographic basis (use /game-dev), non-Minecraft engines, or live GIS analysis (use /qgis directly).

dreamlab-ai Bundle

Deep Research

dreamlab-ai Bundle

OpenAI Codex / GPT-6 Astra integration for Claude Code. Use when the user says "consult with openai", "talk to codex", "ask gpt-6", "get a second opinion from openai", "delegate to codex", "openai review", or "codex rescue". Provides code reviews, adversarial reviews, rescue operations (when Claude is stuck), and GPT-6 Astra task delegation with structured prompting. Runs the baked Codex CLI under the current profile; auth resolves from ~/.codex ([consultants.codex]) wired by the entrypoint. NOT for non-code tasks (research/content/design → dedicated skills), simple one-off edits Claude can finish alone, or DeepSeek reasoning (→ deepseek-reasoning). From openai/codex-plugin-cc.

conectlens Skill

Summarize a contract into obligations, deadlines, unusual terms, and lawyer questions. This is not legal advice and must be reviewed by a qualified lawyer.

conectlens Bundle

Use when planning mobile app features, roadmaps, or research-backed product decisions for apps/mobile.

conectlens Skill

Summarize a legal document, create a risk checklist, and prepare questions for counsel. This is not legal advice and must be reviewed by a qualified lawyer.

benbrastmckie Skill

Research blockers and spawn new tasks to overcome them, updating parent task dependencies

benbrastmckie Bundle

Create phased implementation plans from research findings. Invoke when a task needs an implementation plan.

benbrastmckie Skill

Autonomous state machine that drives a task through its full lifecycle (research -> plan -> implement -> complete) without user confirmation between phases. Invoke for /orchestrate command.

benbrastmckie Bundle

Route commands to appropriate workflows based on task type and status. Invoke when executing /task, /research, /plan, /implement commands.

benbrastmckie Skill

Grant proposal research and drafting with funder analysis. Invoke for grant tasks.

benbrastmckie Skill

Market sizing research with TAM/SAM/SOM framework

coco-research Skill

Create or update a structured change log for a product or platform. Use when someone asks to "create a change log", "log this change", "what changed", "update the change log", "release notes", or "changelog". Reads project memory (CLAUDE.local.md Recent Changes) and meeting notes to build chronological change records. Supports init (backfill from memory), update (append new entries), and release (summarize for a version).

eugenelim Bundle

Use when implementing or resuming a non-trivial repository change: a feature, behavior-changing fix, refactor, migration, framework or dependency upgrade, schema or API change, performance work, infrastructure or build-system change, reversion, or an existing build spec under `docs/specs/`. Also use for bare continuation commands ('resume', 'continue', 'keep going', 'pick up where I left off', 'let's get going') when conversation or workspace context identifies active build work. Do not use for shaping, research, strategy, product planning, design exploration, monitoring or status-only work, review-only, explanation-only, specification-authoring-only, spike-only or throwaway exploration, or trivial edits that are cosmetic, tightly local, behavior-preserving, and have obvious verification.

eugenelim Bundle

Decompose a research question into the sub-questions a thorough answer must address. Builds the outline that `/source-map` then populates and `/desk-research` then synthesises against. Grounded in STORM's outline stage (multi-perspective topic decomposition) and PRISMA's PICO framework (Population, Intervention, Comparison, Outcome — the systematic-review decomposition). Produces `<topic-slug>-outline.md` listing each sub-question with a brief rationale. Depth cues — `quickly`, `top three`, `briefly`, `summary only` for the must-answer few; `comprehensively`, `exhaustively`, `in depth`, `extensive` to chase second-order sub-questions.

eugenelim Bundle

Evidence-grounded research with selectable depth and discipline. Use for any look-up, find-out, fact-check, or comprehensive investigation, including prior art and best practice surveys. Carries a mode parameter (quick / standard / applied / deep) with `quick` as default — casual phrasings (`look up`, `find out`, `quick check`) stay quick; academic phrasings (`research with citations`, `evidence-grounded`, `go deep`, `comprehensively`) bias standard or deep; practitioner phrasings (`applied patterns for`, `best practice for`, `prior art on`, `grey literature`) bias applied. Quick mode is inline, ≤5 fetches, no artifact. Standard mode produces `<topic-slug>-survey.md` with GRADE-style confidence per finding from peer-reviewed and primary sources. Applied mode produces `<topic-slug>-survey.md` calibrated for practitioner grey literature with a discipline-aware confidence overlay. Deep mode additionally auto-runs `/devils-advocate`, producing `<topic-slug>-counterpoints.md`.

eugenelim Bundle

Adversarially review a research artifact (`<topic-slug>-survey.md`) or a user-supplied claim. Searches for counter-evidence, names the strongest objections, and routes each to a verdict — either a confidence-rating downgrade or a do-not-resolve verdict for an irreducible tension where both sides are well-evidenced under different conditions. Grounded in ACH (evidence-against column — the discipline that catches premature closure) and GIJN investigative-journalism practice ("what does the other side say"). Auto-invoked by `/desk-research` deep mode against `<topic-slug>-survey.md`; runs standalone against any user-supplied claim. Produces `<topic-slug>-counterpoints.md` linking back to the source artifact. Depth cues — `quickly`, `top three`, `briefly`, `summary only` for the strongest objections; `comprehensively`, `exhaustively`, `in depth`, `extensive` for the full set.

eugenelim Bundle

Reconstruct the rationale for a past decision by walking time-ordered artifacts (commits, PRs, design docs, chat logs, internal memos). Self-contained — does not invoke `/source-map` or other research-pack skills, because the source surface is time-ordered and internal, and authority is established by an artifact's place in the history rather than by external curation. Produces `<topic-slug>-archaeology.md` with chronology, the rationale chain, the alternatives that were considered and rejected, and a revival check flagging rejected alternatives whose original rejection rationale no longer holds. Depth cues — `quickly`, `top three`, `briefly`, `summary only` for the main rationale chain; `comprehensively`, `exhaustively`, `in depth`, `extensive` for branch alternatives and dead ends.

eugenelim Bundle

Use when a strategist needs to scan the macro environment before setting strategy or evaluating market entry. Triggers on "run a PESTLE", "I need to understand the macro environment", "political economic social analysis", "macro scan", "what external forces affect us". Produces a committed macro-environment artifact. Do NOT use as a substitute for current intelligence — PESTLE organizes and prioritizes information you supply; it does not generate market research.

eugenelim Bundle

Orient to the current desk-research project at a glance — reads overview.md and surfaces phase, working hypothesis, stop-signal verdict, and what to do next. Triggers on 'where are we on the X research', 'status of the Y investigation', 'resume the Z project', 'what phase is the research in', 'where did we leave off on the research', or any return-to-a-named-research-project phrasing. Read-only: never advances phase, never modifies any file.