Skip to content

BdM-15/capture-insights / skills/capture-brief

capture-brief

Verified

Create or enrich a pursuit capture brief from USASpending bulk data, optional SAM live intel, and optional LLM narrative. Use when opening a recompete workspace, scaffolding admin paperwork, or when the user asks for a one-page pursuit snapshot with citations.

FileKindSize
SKILL.mdskill md1.2 KB
---
name: capture-brief
description: Create or enrich a pursuit capture brief from USASpending bulk data, optional SAM live intel, and optional LLM narrative. Use when opening a recompete workspace, scaffolding admin paperwork, or when the user asks for a one-page pursuit snapshot with citations.
metadata:
  title: Capture Brief
  category: pursuit-workspace
  status: active
  origin: capture-insights
  mcps:
    - usaspending-gov-mcp
    - sam-gov-mcp
  invoke: workspace,agent
  runtime: legacy
  supports_llm: true
  max_turns: 3
  output: pursuits/{slug}/01_capture/capture_brief.md
compatibility: Requires DuckDB USASpending bulk; SAM optional via MCP or REST
---

# Capture Brief

Atomic admin skill — one markdown brief per pursuit. Do not merge SAM scan or competitive snapshot here; chain via `pursuit-kickoff` if needed.

## Steps

1. Resolve pursuit slug from row (agency, recipient, award_key).
2. Pull USASpending relationships/flows for incumbent + agency (DuckDB first; live MCP optional).
3. Scaffold `capture_brief.md` with signals, timing, and citation blocks.
4. If enrich/LLM requested: add SAM hits + short narrative; cite sources only.

## Output contract

- Write only under `data/knowledge/pursuits/<slug>/`
- Never write to `global/` or `brain/`
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall