Menü
Format a research run's signals as a Markdown comment for the OKR anchor issue.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | format-research-issue-update |
| description | Format a research run's signals as a Markdown comment for the OKR anchor issue. |
| version | 0.1.0 |
| purity | pure-data |
| runtime | research-runner |
| command | npx @maintainabilityai/research-runner@~0.1.64 skill-format-research-issue-update |
Called by market-research-agent (and re-runs) to post a clean progress comment back to the OKR anchor issue. PURE markdown formatter — no LLM, no narrative writing.
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
topic | string | yes | — | One-line OKR-derived topic. |
runId | string | yes | — | Stable run id. |
rankedSources | RankedSource[] | yes | — | The dedupe-and-rank output. |
providerCounts | Record<string, number> | yes | — | Coverage signal. |
gapSignals | string[] | no | [] | Agent's gap analysis (e.g. low_source_diversity). |
meshContext | { platformId, barIds } | yes | — | For the issue header. |
| Field | Type | Description |
|---|---|---|
markdown | string | The formatted comment body, ready to POST as an issue comment. |
byteCount | integer | Size sanity check (issue comments cap around 65k chars). |
echo '{"topic":"...", "runId":"...", "rankedSources":[...], "providerCounts":{...}, "meshContext":{...}}' \
| npx @maintainabilityai/research-runner@~0.1.64 skill-format-research-issue-update
Pure JS string formatter. Backed by the existing research-runner issue-formatting helper. CLI subcommand backend lands in B-PR1a.
Never fails on valid JSON. Returns truncated markdown + a warning footer if byteCount > 60000.
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.