git:20260801.0de5ac7 to git:20261013.fbe187d

79 added, 48 removed. Audit A to A.

---

name: ccc-research

- context: fork

- description: "complete research ecosystem — 8 skills in one. Deep multi-source research, spec interviews, cross-model review, competitive analysis, trend analysis, and large…"

+ description: "Research before you build: cited multi-source research, spec interviews, cross-model review, literature reviews, competitive and trend analysis, and large-document or large-codebase ingestion. Use when the user wants options compared, prior art found, a spec defined, or something too big summarized."

allowed-tools:

- Read

+ - Write

+ - Bash

+ - Glob

+ - Grep

+ - WebSearch

+ - WebFetch

+ - Agent

+ - Skill

- AskUserQuestion

+ model: inherit

+ effort: high

---

- # /ccc-research — Research domain hub

+ # /ccc-research — research, routed

- > Load ONE skill. Get the entire research domain. 8 skills in one.

+ **CC Commander** · /ccc-research · a cited answer, a comparison or a spec before any code is written.

- ## Sub-Skills

+ Research sub-skills (`deep-research`, `spec-interview`, `cross-model-review`, `literature-review`, `competitive-analysis`, `data-ingestion`, `trend-analysis`, `large-context`) ship with the Commander CLI toolkit. Invoke one with the Skill tool when it is listed in this session; otherwise apply the method in [references/routing.md](references/routing.md). The user's selected model is preserved.

- | # | 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 |

+ Codex: ask pickers as plain-text questions, run parallel lanes as separate `codex exec` calls, and write the report to a file.

- ## Research Surfaces

+ ## When to use / when not to

- 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

+ - Use before a non-trivial build, for "which library/tool/vendor", "what are the trends in X", "interview me for a spec", "review this decision from several angles", or an input too large to read in one pass.

+ - Use `/ccc-brainstorm` for open-ended ideation, `/ccc-debate` for a structured for/against verdict on one decision, `/ccc-plan` once the spec exists, `/ccc-data` for data pipelines and analytics.

- > **No expressed intent?** Present the top 3 sub-skills + "More…" as an AskUserQuestion picker (≤4 options).

+ ## What happens

- ## Routing Matrix

+ ### 1. Route by intent, or ask

- | 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` |

+ An argument or a clear intent routes straight to the sub-skill in [references/routing.md](references/routing.md). "Research X before building" runs the research-before-build sequence in step 4.

- ## Protocol: Research Before Build

+ Otherwise ask with AskUserQuestion (header "Research"), recommended first:

- The recommended sequence for any non-trivial feature:

- 1. `deep-research` → find existing solutions, prior art, best practices

- 2. `competitive-analysis` → evaluate options

- 3. `spec-interview` → define requirements before writing code

- 4. Hand off to implementation skills with research context

+ - 🟢 Deep research — parallel sources, citations, a synthesized report

+ - Compare options — `competitive-analysis` feature and trade-off table

+ - Spec interview — 5 to 7 questions, then a written spec

+ - More — cross-model review, literature review, trends, or ingest something large (a follow-up picker)

- ## When to invoke this skill

+ ### 2. Fix the question

- **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.

+ Restate the question in one sentence, the depth (overview, detailed, exhaustive), sources to include or exclude, and the output (brief, report, table). Ask only for what changes the result.

- **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.

+ ### 3. Gather and synthesize

- **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.

+ - **Deep research**: when `/deep-research` is listed in this session, invoke it with the Skill tool (`/deep-research <question>`); it fans out search, fact-checks and returns a cited report. Otherwise split the question into 3 to 5 independent sub-questions and run them as parallel Agent calls (each returns findings with source URLs and dates, never raw page dumps), using WebSearch and WebFetch. Synthesize in the lead context.

+ - **Cross-model review**: Claude and the Codex CLI only. Run an independent Claude reviewer through the Agent tool, and Codex when installed:

+ ```bash

+ codex review --uncommitted # code changes in the working tree

+ codex exec --json -m gpt-6-astra --sandbox read-only "$(cat review-prompt.md)" < /dev/null # a document or decision

+ ```

+ Reviewers never see each other's output. Report agreements, single-reviewer findings and contradictions separately.

+ - **Large inputs** (`data-ingestion`, `large-context`): measure first, since current Claude models have a 1M-token window:

+ ```bash

+ find "<path>" -type f -not -path '*/node_modules/*' -not -path '*/.git/*' -exec cat {} + | wc -c | awk '{print int($1/4)" est. tokens"}'

+ ```

+ Under roughly 800K estimated tokens, read it directly. Above that, reduce (filter with `rg -l`, drop generated and vendored files), then chunk on semantic boundaries with one subagent per chunk returning conclusions only. Mechanical work over a large surface goes to `codex exec -m gpt-6.1-sol` inside an isolated worktree, with the diff reviewed before merge. State what was dropped.

+ - **Other surfaces**: connected channels (opt-in connectors such as Discord or Telegram) for community sentiment, and user-uploaded files, only when the user points to them. They are absent by default.

+ ### 4. Research before build (non-trivial features)

+ 1. `deep-research` — existing solutions, prior art, practice

+ 2. `competitive-analysis` — evaluate the options

+ 3. `spec-interview` — requirements before code

+ 4. Hand off to `/ccc-plan` or `/ccc-build` with the report path as context

+ ### 5. Write the deliverable

+ Write the report or spec to a file the user chooses (default `./research/<slug>-<YYYY-MM-DD>.md`) with Write. Every factual claim carries a source link and access date; every comparison states its criteria.

+ ## Done when

+ - The deliverable exists (`test -s <file> && echo ok` printed `ok`) and its path is reported.

+ - Every load-bearing claim has a source URL, and at least the top recommendation was checked against a second independent source or a fresh-context verifier (Agent) asked to refute it.

+ - Cross-model review: each reviewer's output was received in this turn, or the user is told which reviewer could not run (for example, Codex not installed).

+ ## Guardrails

+ - Route models to Anthropic and the Codex CLI only; never to a local or other third-party model.

+ - Never present an unsourced claim as fact; label inference and gaps.

+ - Never post, message, or publish research output; it stays a local file unless the user authorizes sharing in this conversation.

+ - Never send the user's private code or documents to an external service other than the Codex CLI they already use, and only after they choose cross-model review.

+ - Subagents return conclusions, not raw content.

+ ## See also

+ - `/ccc-debate` — structured verdict on one decision

+ - `/ccc-brainstorm` — divergent ideation

+ - `/ccc-plan` — turn the spec into an implementation plan

+ - `/ccc-orchestrate` — plan on Claude, execute on Codex, verify on Claude

---

> ⚙️ **Fable contract:** plan before build · verifier ≠ worker · prove before alarm · loops need gates · leave durable state — `rules/fable-method.md`