Skip to content

aiskillstore/marketplace / skills/1102tools-dev/acquisition-policy-workflow

acquisition-policy-workflow

Verified

Trigger for: explaining current FAR, DFARS, or agency-supplement text; determining documented acquisition-policy status for an agency and FAR part; comparing codified text, RFO model text, and agency deviations; tracing acquisition rulemaking; finding procurement comment periods; analyzing public comments; refreshing prior policy analysis; or producing an Acquisition Policy Impact Brief. Use published federal sources and supplied policy documents without making legal or procurement-specific applicability determinations. Do not use for clause selection, market research execution, opportunities, pricing, grants, or cooperative agreements.

# Acquisition Policy Workflow current test evidence

Implementation test evidence is intentionally separated from the normative test specification.

## Current result

The canonical skill passed quick validation, nine-skill repository validation, and 10 deterministic workflow/record tests. The valid fixture passed policy-record validation, generated a four-page Acquisition Policy Impact Brief, and passed evidence-ID, status, hyperlink, fixed-table-geometry, ZIP, text-extraction, LibreOffice conversion, and all-page visual checks.

The fixture is synthetic and labeled for offline testing. Clean-client routing and live-source workflows remain open. Do not describe the standalone skill or agent as final `1.0.0` until the recorded matrix in `testing.md` passes.

## August 22 stabilization regression

The policy record advanced to schema `1.1` with structured `C###` conflicts and documented-clear, documented-conflict, and authorized-resolution finding states. An unresolved synthetic `$9 million` versus `$7.5 million` threshold conflict passed only when both source positions remained visible and resolution was reserved to an authorized official. The validator rejected both a controlling-value conclusion and an attempted authorized-resolution status without an official resolution record. Clean Codex and Claude replay remains required at the agent-package release layer.

## Required record

Record the exact client, version, model, invocation path, prompt, source fixtures or live identifiers, MCP versions, generated artifact, validator output, rendered pages, and limitations for every release run. Live source calls must be serialized and must not expose credentials.
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