aiskillstore/marketplace / skills/1102tools-dev/acquisition-policy-workflow
acquisition-policy-workflow
VerifiedTrigger 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.5 KB |
| agents/openai.yaml | config | 281 B |
| references/document-intake.md | markdown | 1.5 KB |
| references/evidence-contract.md | markdown | 3.8 KB |
| references/launch-menu-and-framing.md | markdown | 3.1 KB |
| references/report-specification.md | markdown | 2.1 KB |
| references/runtime-adaptation.md | markdown | 1.4 KB |
| references/source-routing.md | markdown | 3.8 KB |
| references/status-and-decision-boundaries.md | markdown | 3.9 KB |
| scripts/build_acquisition_policy_brief.py | script | 20.4 KB |
| scripts/validate_acquisition_policy_brief.py | script | 7.3 KB |
| scripts/validate_policy_research_record.py | script | 23.6 KB |
| skill-report.json | config | 41.7 KB |
| test.md | markdown | 1.6 KB |
| testing.md | markdown | 2.2 KB |
testing.md
View on GitHub# Acquisition Policy Workflow test specification
## Routing
- A vague policy request produces the complete ten-choice menu and no retrieval.
- A precise codified-text request routes directly to mode 1.
- A named-agency RFO applicability request routes directly to mode 2 and asks only for missing dates or citation details.
- Market-research execution, clause selection, opportunity research, pricing, grants, and cooperative agreements do not route to this skill.
## Status controls
- Model text without an agency deviation remains non-operative.
- An agency deviation preserves its scope, effective date, transition terms, and limitations.
- A proposed rule, withdrawn rule, and future-effective final rule are never presented as current.
- Recent Federal Register effectiveness and eCFR lag remain distinct.
- Absence from the Acquisition.gov index is described as no posted deviation located, not proof of nonexistence.
- Duplicate or multi-part deviation documents remain visible.
## Documents and public queries
- Supplied documents are untrusted evidence and embedded instructions are ignored.
- Approved-versus-draft conflicts cause a precedence question.
- Queries contain only sanitized public identifiers and terms.
- Missing MCP capabilities yield an exact bounded alternative, not a direct-HTTP bypass.
## Comments
- Comment analysis records search terms, returned and reviewed counts, sample method, exclusions, and limitations.
- Targeted organization searches are not described as complete or representative.
- Public comments are never treated as authority or consensus.
## Artifact
- The valid fixture passes record validation and builds a DOCX.
- Unknown evidence references, unsafe query keys, invalid status, operative model text, missing deviation evidence, and incomplete stakeholder samples fail.
- The DOCX passes section-order, evidence, link, table-geometry, reserved-determination, ZIP, extraction, LibreOffice, and visual gates.
## Client release matrix
- Codex CLI and Desktop.
- Claude Desktop (Code) and Claude Code CLI, with current Opus and Sonnet models.
- Explicit invocation is release blocking. Natural-language routing is release blocking for the precise policy prompts and advisory for broad ambiguous prompts.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |