KevinZai $ccc-research — Research domain hub
Load ONE skill. Get the entire research domain. 8 skills in one.
Sub-Skills
| # | Skill | Focus |
|---|---|---|
| 1 | deep-research | Multi-source research with parallel agents, citation tracking, synthesis |
| 2 | spec-interview | 5-7 structured questions to produce a complete spec before coding |
| 3 | cross-model-review | Code/decision review using multiple AI models for diverse perspectives |
| 4 | literature-review | Academic/technical literature review with source evaluation |
| 5 | competitive-analysis | Competing products/tools/libraries feature comparison |
| 6 | data-ingestion | Ingest and summarize large documents, codebases, or datasets |
| 7 | trend-analysis | Technology, market, or usage pattern trend analysis |
| 8 | large-context | Opus 5's native 1M window, reduction, chunk-and-synthesize, then Codex CLI for mechanical execution |
Research Surfaces
In addition to web search, research can use connected channels as surfaces:
- Telegram/Discord channels — community sentiment, ecosystem news, real-time signals
- Files API — ingest uploaded documents, codebases, or data files directly
- Cross-model review — route to multiple models for independent perspectives
No expressed intent? Present the top 3 sub-skills + "More…" as an AskUserQuestion picker (≤4 options).
Routing Matrix
| Your Intent | Route To |
|---|---|
| "Research X before building" | deep-research + competitive-analysis |
| "Define spec first" / "Interview me" | spec-interview |
| "Review this from multiple angles" | cross-model-review |
| "Literature review" / "Academic sources" | literature-review |
| "Compare these tools/libraries" | competitive-analysis |
| "Summarize this large document" | data-ingestion |
| "What are the trends in X?" | trend-analysis |
| "File too large for context" | large-context |
Protocol: Research Before Build
The recommended sequence for any non-trivial feature:
deep-research→ find existing solutions, prior art, best practicescompetitive-analysis→ evaluate optionsspec-interview→ define requirements before writing code- Hand off to implementation skills with research context
When to invoke this skill
Example 1
- user: research the best auth libraries for Next.js before I start building
- assistant: Loads ccc-research and routes to deep-research + competitive-analysis for multi-source comparison with citation tracking.
Example 2
- user: help me define the spec for this feature before coding
- assistant: Loads ccc-research and routes to spec-interview — 5-7 structured questions to generate a complete spec before implementation.
Example 3
- user: analyze this 500-page PDF of technical documentation
- assistant: Loads ccc-research and routes to data-ingestion for large document summarization and key insight extraction.
⚙️ Fable contract: plan before build · verifier ≠ worker · prove before alarm · loops need gates · leave durable state —
rules/fable-method.md
(On Codex, present these options as a numbered list and ask the user to reply with a number — AskUserQuestion is Claude-only.)