メニュー
Research a topic relevant to SWARM AI safety and grow the vault with findings. Queries external sources, synthesizes into claim candidates, follows the extraction pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find papers on".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Find connections between claims and update topic maps. Requires semantic judgment to identify genuine evidence relationships. Use after /extract creates claims, when exploring connections, or when a topic map needs synthesis. Triggers on "/cross-link", "/cross-link [claim]", "find connections", "update topic maps", "connect these claims".
Extract structured claims from SWARM experiment runs, sweep results, and red-team reports. Comprehensive extraction is the default — every governance finding, adversarial pattern, and parameter sensitivity result gets extracted. Zero extraction from a domain-relevant run is a BUG. Triggers on "/extract", "/extract [file]", "extract findings", "mine this run", "process this experiment".
Explore and analyze the SWARM knowledge graph — detect orphan claims, find dense connection clusters, trace evidence chains, identify synthesis opportunities. Triggers on "/graph", "graph analysis", "find orphans", "what connects to X".
Surface the next highest-priority action from the SWARM synthesis pipeline queue and maintenance conditions. Recommends what to work on based on queue state, pending observations, stale claims, and research threads. Triggers on "/next", "what should I work on", "next action", "what's pending".
Run the full SWARM synthesis pipeline on one or more experiment runs — seed, extract, cross-link, update, validate in sequence. Triggers on "/pipeline", "/pipeline [run-folder]", "full pipeline", "process everything".
Capture methodology friction, process corrections, and operational learnings for the SWARM vault. Rule Zero — methodology notes are the spec; when something goes wrong, write it down so the system learns. Triggers on "/remember", "capture friction", "log this correction", "the system did X wrong".
| name | learn |
| description | Research a topic relevant to SWARM AI safety and grow the vault with findings. Queries external sources, synthesizes into claim candidates, follows the extraction pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find papers on". |
| user-invocable | true |
| allowed-tools | Read, Write, Glob, Bash, mcp__qmd__vector_search |
| context | fork |
Read vault/ops/derivation-manifest.md for research settings.
Default research depth: deep (AI safety domain, from config).
Target: $ARGUMENTS
Research a topic and grow the SWARM knowledge graph with findings.
Topics most likely to yield governance claims:
runs/research-[topic]-[date].md---
description: Research findings on [topic]
source_type: research
research_prompt: "[the query used]"
generated: YYYY-MM-DD
---
# [Topic] — research findings
[Synthesized findings from sources]
## Sources
- [Author et al. Year — title](url)
- ...
After creating the research file, run /extract [path-to-file] to process it into claims.
Research-sourced claims have lower initial confidence until validated by SWARM experiments:
confidence: low until replicated in SWARM runsconfidence: medium or high based on criteria