菜单
Read the merged research-doc.md for an OKR. Returns structured findings (R-N anchors) for the PRD agent to cite.
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 | knowledge-research |
| description | Read the merged research-doc.md for an OKR. Returns structured findings (R-N anchors) for the PRD agent to cite. |
| version | 0.1.0 |
| purity | pure-data |
| runtime | research-runner |
| command | npx @maintainabilityai/research-runner@~0.1.64 skill-knowledge-research |
The PRD agent's bridge from Why → How. Reads the merged research artifact at okrs/<id>/why/research-doc.md and surfaces it in a parseable shape so FR-NN can cite R-N anchors.
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
okrId | string | yes | — | The OKR id whose why/ phase has merged. |
| Field | Type | Description |
|---|---|---|
ok | boolean | False if why/research-doc.md is absent. |
findings | { id: "R-N", title, supporting: string[], contradicting: string[], confidence: "HIGH" | "MEDIUM" | "LOW" }[] | Parsed from the synthesis prompt-pack's strict format. |
whitespace | string[] | The "Whitespace Analysis" section's bullets. |
references | string[] | The final References list. |
echo '{"okrId":"OKR-2026Q1-IMDB-001-celeb-api"}' \
| npx @maintainabilityai/research-runner@~0.1.64 skill-knowledge-research
Parses okrs/<id>/why/research-doc.md using the 10-section anchor scheme from prompt-packs/looking-glass/research/synthesis.md. CLI subcommand backend lands in B-PR1a.
{ok: false, reason: 'research-not-merged-yet'} when the file is missing — agent stops and notes the gating dependency.
Append one hash-chained audit event to okrs/<id>/audit/events/<run-id>.jsonl. Returns the new chain head.
Replay the hash chain over an existing audit JSONL; returns the chain head on success, the first integrity failure reason on failure.
Query the mesh's threat library for entries matching a concern (e.g. "identity", "data-licensing").
Academic paper search via arXiv. Returns ranked paper results per query envelope.
Aggregated architecture context for a scope — CALM nodes + ADRs + fitness functions + quality attributes. PURE data; the Architect persona is in the parent agent's prompt.
Aggregated quality context for a scope — quality attribute definitions + performance SLOs + reliability targets per BAR.