Skip to content
cccskills
FreePublished on GitHub

deep-research

Deep multi-source research synthesis — web, academic, patent, and internal KB cross-referencing

The English summary is being prepared. Showing the original description.

garochee33/DSH
See how to install

Files included (1)

  • SKILL.md2.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Deep Research Skill v2.0

Purpose

Conduct thorough multi-source research across web, academic databases, patent systems, and internal Trinity KB, then synthesize findings into actionable intelligence.

Capabilities

  • Multi-source parallel search (Tavily, arXiv, PubMed, Semantic Scholar, Wikipedia, OEIS)
  • Patent landscape analysis
  • Competitive intelligence gathering
  • Academic literature review and citation mapping
  • Internal KB cross-referencing for existing knowledge
  • Executive summary generation with confidence scores

Research Protocol

  1. Scope: Define research question, constraints, and target depth
  2. Search: Fan out to 3+ sources in parallel
  3. Filter: Rank by relevance, recency, and authority
  4. Synthesize: Cross-reference findings, identify patterns and contradictions
  5. Report: Structured output with citations, confidence levels, and knowledge gaps

Agents

  • Researcher (primary): Deep web and academic search
  • Oracle: Internal KB and data intelligence
  • Prophet: Strategic pattern recognition

Tools

  • deep_web_search (Tavily), research_topic
  • patent_search, arxiv_search, pubmed_search, semantic_scholar_search
  • wikipedia_lookup, wolfram_alpha_query
  • search_vault (internal KB)

Quality Gates

  • Minimum 3 independent sources for any factual claim
  • All citations must include URL/DOI
  • Confidence scoring: HIGH (3+ corroborating sources), MEDIUM (2), LOW (1)
  • Research reports must include "Knowledge Gaps" section

Protocol

  1. Assess — Understand the specific requirement and context
  2. Plan — Determine the approach based on the guidance above
  3. Execute — Apply the deep research methodology
  4. Verify — Validate the output against expected standards
  5. Report — Document results and any issues encountered

Integration

This skill is available via:

  • invoke_skill("deep-research") in the agent kernel
  • POST /api/skills/invoke with skillId: "deep-research"
  • Semantic search via GET /api/skills/search?q=deep+research

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

ai-sdk

Free

Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

The English summary is being prepared. Showing the original description.

garochee33/DSH4Updated Oct 12, 2026

algorithms

Free

Algorithm design and analysis skill for DSH; use when working on optimization, data structures, or computational procedures.

The English summary is being prepared. Showing the original description.

garochee33/DSH4Updated Oct 12, 2026

api-gateway-designer

Free

Design and implement scalable API gateways, RESTful APIs, GraphQL endpoints, WebSocket handlers, and microservice communication patterns. Use when creating API routes, designing endpoints, implementing middleware, or setting up service mesh architectures.

The English summary is being prepared. Showing the original description.

garochee33/DSH4Updated Oct 12, 2026

best-of-n

Free

Implement a task N ways in parallel and pick the best. Spawns multiple subagents in isolated worktrees, evaluates all candidates, and applies the winner. Use when asked to "best of n", "try multiple approaches", "parallel implementations", "/best-of-n", or "/bon".

The English summary is being prepared. Showing the original description.

garochee33/DSH4Updated Oct 12, 2026

check

Free

Check your work with a verification subagent. Spawns a verifier that reviews diffs, runs builds and tests, and evaluates correctness. Use when asked to "check work", "verify changes", "self-verify", "/check", "/verify", "/check-work", or "/self-verify".

The English summary is being prepared. Showing the original description.

garochee33/DSH4Updated Oct 12, 2026

ci-cd-architect

Free

CI/CD pipeline design, GitHub Actions workflows, deployment automation, infrastructure as code, and release management. Use when setting up CI/CD, automating deployments, configuring build pipelines, or managing releases.

The English summary is being prepared. Showing the original description.

garochee33/DSH4Updated Oct 12, 2026

See all skills by garochee33

Report a problem with this skill