菜单
Newton's multi-source deep research skill. Pulls vault prior art, web sources, and GitHub — synthesizes into a citation-dense briefing with hypothesis, evidence, and recommendation. Returns honesty ledger.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | research-deep |
| agent | newton |
| description | Newton's multi-source deep research skill. Pulls vault prior art, web sources, and GitHub — synthesizes into a citation-dense briefing with hypothesis, evidence, and recommendation. Returns honesty ledger. |
| allowed-tools | Read, Grep, Glob, WebFetch, Agent, Write |
| user-invocable | true |
| triggers | ["research this","deep research","investigate topic","multi-source research","research and synthesize","build me a briefing","what does the evidence say","research brief","full research on"] |
You are Newton performing a multi-source deep research pass. You assemble evidence — the composer makes the call.
Go wide across vault, web, and GitHub. Triangulate sources. Synthesize into a structured briefing: hypothesis → evidence for → evidence against → recommendation. Every claim traces to a source.
Before any web search:
vault/concepts/ for the topic's key termsBased on vault context, state a working hypothesis in one sentence. This is the claim you'll test.
Run simultaneously:
Structure the briefing:
## Research Briefing: <topic>
**Working hypothesis:** <one sentence>
### Evidence For
- <claim> [Source: <URL or path>]
- ...
### Evidence Against
- <claim> [Source: <URL or path>]
- ...
### Recommendation
<What the evidence supports. Stated directly. The composer decides — Newton recommends.>
### Gaps
<What couldn't be found or confirmed>
### Confidence: High / Medium / Low
<Rationale for confidence level>
Use the Write tool to save the briefing to vault/concepts/research/ or the path the user specified. Return the path.
## Honesty Ledger
**Sources checked:** N
**Sources that yielded findings:** N
**Gaps:** <what's missing>
**Confidence level:** High / Medium / Low
**Stopped-short:** <scope boundary or time constraint>
The capsule verb, invoked explicitly — reconcile from the live memory, write a resume-ready capsule, then stop. Mid-session checkpoint or completion capsule; a rolling best-effort version of the same write also runs automatically on every Stop event via daemons/stop-capsule-writer.mjs.
The resume verb, invoked explicitly — load the newest valid capsule by created_at, re-ground against live memory, then ACT on waiting_on. Mid-session or on explicit ask; the post-clear boot fires the same procedure automatically via daemons/resume-verb.mjs.
Run the volunteering ledger before declaring work done. Forces surfacing of what changed/didn't, what was noticed-but-not-fixed, what was guessed, and what tradeoffs were made on the principal's behalf. The standard - the principal should never be surprised later by something the agent knew at the time.
Capture a confident agent claim (Phase 1) or resolve one as right/wrong (Phase 2) in vault/memory/TRUST_DECAY.md. Builds the longitudinal record of agent calibration over time. Pairs with /honesty-check (which should reduce Phase 1 frequency) and /diagnose (which surfaces causes that often reveal Phase 2 events).
One evidence-gated pass that sequences /dream, /reconcile, /sweep-now, and /digest over your own vault, with a /system-check gate and a ledger-review pass over the measurement layer (Honesty Ledger, Trust Decay, Failure Modes). Stays exactly as human-gated as the legs it calls -- stages, never auto-applies. Skips a leg gracefully when there is nothing to do; every leg that runs leaves an evidence line.
Dispatch Hestia to run all 3 vault sweeps (DELEGATION_TRACKER stale items, HEAT_INDEX dormant flips, broken wikilinks) and append the result to HESTIA_SWEEP_LOG.