/Geek-skills-deep-research

name: deep-research
version: 8.1.2
description: >
  Use this skill when the user wants an evidence-based research memo, literature
  review, market/policy/technical landscape, or a multi-source decision brief
  with citations, trade-offs, and a clear conclusion. Best for tasks that need
  synthesis across multiple external sources, iterative follow-up research, or
  a reusable written artifact. Do not use for quick factual lookups,
  single-source summaries, simple Q&A, summarizing one document the user
  already provided, plan-only requests where the user explicitly defers the
  actual research, or when the user wants a short answer with no need for
  cited evidence (a short but evidence-backed conclusion is still a brief
  memo, which this skill covers). Chinese trigger examples: "帮我调研",
  "深度研究", "综述报告", "技术选型分析", "竞品研究", "政策分析".
compatibility: Requires web search plus file read/write. Shell/scripts and subagents are optional accelerators, not hard requirements.
metadata:
  version: "8.1.2"
  owner: "enterprise-research"
  category: "research"
  maturity: "production-candidate"
  outputs: "workspace/research-plan.md workspace/research-notes/*.md workspace/registry.md workspace/draft.md workspace/evaluation.md workspace/run-summary.json"

Deep Research V8.1

This skill is for **evidence-rich research outputs**, not for every question that happens to mention “analysis”.

The V8 shift is simple:

• **Single-agent first.** Start with one lead agent and only fan out when parallel work will clearly help.
• **Thin harness, fat skill.** Put reusable judgment and workflow here; keep deterministic checks in scripts.
• **Context organization over prompt stuffing.** Load the minimum active context bundle, then pull in references only when needed.
• **Eval and observability built in.** A good report is not enough; the run must also be diagnosable and improvable.

What this skill should produce

Choose the lightest artifact that satisfies the task.

| Output type | Use when | Typical length | Required artifacts | |---|---|---:|---| | **Brief memo** | user wants a concise answer with evidence | 800-1800 words | `research-plan.md`, `registry.md`, `draft.md`, `run-summary.json` | | **Full report** | user asks for comprehensive analysis / literature review / decision document | 2500-6000 words | all core artifacts + `evaluation.md` | | **Delta update** | user says “continue”, “second round”, “what changed”, “deepen round 2” | 600-1800 words | prior round handoff (`references/handoff-format.md`) + new notes + delta draft |

If the user did **not** ask for a long report, default to **Brief memo**.

When NOT to use this skill

Do **not** activate for:

• quick fact lookups or simple definitions
• summarizing a single provided article/PDF/page
• short comparisons the model can answer directly from 1-2 sources
• brainstorming without evidence requirements
• tasks where the user explicitly wants a short answer, not a report

If in doubt, ask yourself: **Does this task need a reusable evidence artifact and multi-source synthesis?** If not, do something simpler.

Org-policy boundary

This skill does **not** replace system policies, enterprise guardrails, or repo-level instructions. Put these outside the skill:

• data handling / PII / compliance rules
• approval requirements for external access or irreversible actions
• org-wide style and review policy
• environment-specific permissions

Keep those in system prompts, AGENTS/CLAUDE/OpenAI config, or the harness. This skill owns the **workflow**, not the company’s permanent red lines.

Active context bundle

At activation time, keep the active bundle small.

**Always load first** 1. This `SKILL.md` 2. `references/methodology.md` 3. `references/report-assembly.md` 4. `references/research-notes-format.md`

**Load on demand**

• `references/subagent-prompt.md` only if you actually dispatch subagents
• `references/handoff-format.md` only when a delta update continues a prior round
• `references/evaluator-prompt.md` only if you run the evaluator
• `references/quality-gates.md` before finalization
• `references/observability.md` when emitting metrics or diagnosing regressions
• `references/tension-discovery.md` only for contested / decision-heavy topics
• `references/landscape-scan.md` only when literature or ecosystem mapping matters

**After compaction or context reset** Reload only:

• `research-plan.md`
• active task notes
• `registry.md`
• unresolved issues list
• the one reference file for the current phase

Do **not** reload the whole skill tree unless the run drifted badly.

Workflow

P0 — Scope, route, and choose the lightest mode

Create `workspace/research-plan.md` with:

• research question
• intended audience
• freshness requirement
• geography / market / jurisdiction
• output type (brief / full / delta)
• stakes: low / medium / high
• why this skill is justified

Then choose the orchestration mode:

| Mode | Default choice | |---|---| | **Single-agent** | default for most tasks | | **Lead + subagents** | only when there are 3+ separable research threads or obvious parallel value | | **Delta update** | when continuing prior research |

**Do not fan out just because subagents exist.**

P0.5 — Optional modules (not mandatory by default)

Use optional modules only when they earn their keep:

• **Tension discovery** (`references/tension-discovery.md`): use for contested, hype-heavy, or decision topics where mainstream framing may be wrong.
• **Landscape scan** (`references/landscape-scan.md`): use when the domain is unfamiliar, broad, or literature-heavy. For non-academic topics, this can be an ecosystem/standards/vendor scan rather than arXiv.
• **Reverse search**: use when costs, failure modes, counter-evidence, or operational constraints are missing.

P1 — Plan the evidence work

Break the task into 1-5 research threads. Each thread needs:

• one crisp objective
• starting queries
• what “done” looks like
• what evidence would