aiskillstore/marketplace / skills/1102tools-dev/govcon-growth-workflow
govcon-growth-workflow
VerifiedTrigger for: finding federal opportunities; capture and bid screening; competitor or incumbent intelligence; recompete pipelines; teaming partner research; agency, customer, or market intelligence; federal labor-rate or pricing context; or refreshing prior GovCon research. Always begin with the complete workflow menu and obtain the user's selection before research, preflight, file generation, web search, or MCP calls. Produce sourced chat findings or an optional validated GovCon Growth Brief without making a bid decision from public data alone.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.9 KB |
| agents/openai.yaml | config | 316 B |
| references/brief-specification.md | markdown | 1.1 KB |
| references/competitor-intelligence.md | markdown | 722 B |
| references/evidence-contract.md | markdown | 3.2 KB |
| references/evidence-limitations.md | markdown | 988 B |
| references/launch-menu-and-question-blocks.md | markdown | 1.8 KB |
| references/market-and-agency-intelligence.md | markdown | 743 B |
| references/opportunity-intelligence.md | markdown | 1.1 KB |
| references/pricing-context.md | markdown | 744 B |
| references/recompete-radar.md | markdown | 707 B |
| references/runtime-adaptation.md | markdown | 1.8 KB |
| references/teaming-due-diligence.md | markdown | 720 B |
| references/web-provider-policy.md | markdown | 7.4 KB |
| scripts/build_growth_brief.py | script | 11.5 KB |
| scripts/validate_growth_brief.py | script | 5.1 KB |
| scripts/validate_research_record.py | script | 18.4 KB |
| skill-report.json | config | 56.9 KB |
| test.md | markdown | 6.3 KB |
| testing.md | markdown | 4.4 KB |
scripts/build_growth_brief.py
View on GitHub#!/usr/bin/env python3
"""Build a structured GovCon Growth Brief from a validated research record."""
from __future__ import annotations
import argparse
import json
import subprocess
import sys
from pathlib import Path
from docx import Document
from docx.enum.style import WD_STYLE_TYPE
from docx.enum.table import WD_CELL_VERTICAL_ALIGNMENT, WD_TABLE_ALIGNMENT
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.oxml import OxmlElement
from docx.oxml.ns import qn
from docx.shared import Inches, Pt, RGBColor
NAVY = "17365D"
GREEN = "167D5A"
GRAY = "5B6573"
def shade(cell, fill: str) -> None:
props = cell._tc.get_or_add_tcPr()
element = OxmlElement("w:shd")
element.set(qn("w:fill"), fill)
props.append(element)
def set_cell_text(cell, value: object, *, bold: bool = False, color: str | None = None) -> None:
cell.text = ""
run = cell.paragraphs[0].add_run(str(value if value not in (None, "") else "Not provided"))
run.bold = bold
if color:
run.font.color.rgb = RGBColor.from_string(color)
cell.vertical_alignment = WD_CELL_VERTICAL_ALIGNMENT.CENTER
def configure(document: Document) -> None:
section = document.sections[0]
section.top_margin = Inches(0.75)
section.bottom_margin = Inches(0.7)
section.left_margin = Inches(0.8)
section.right_margin = Inches(0.8)
section.header_distance = Inches(0.35)
section.footer_distance = Inches(0.35)
normal = document.styles["Normal"]
normal.font.name = "Aptos"
normal.font.size = Pt(10.5)
normal.paragraph_format.space_after = Pt(6)
normal.paragraph_format.line_spacing = 1.08
for name, size, color in (("Title", 28, NAVY), ("Heading 1", 17, NAVY), ("Heading 2", 12.5, GREEN)):
style = document.styles[name]
style.font.name = "Aptos Display"
style.font.size = Pt(size)
style.font.bold = True
style.font.color.rgb = RGBColor.from_string(color)
style.paragraph_format.space_before = Pt(10)
style.paragraph_format.space_after = Pt(5)
if "Evidence ID" not in document.styles:
style = document.styles.add_style("Evidence ID", WD_STYLE_TYPE.CHARACTER)
style.font.name = "Aptos"
style.font.size = Pt(8.5)
style.font.bold = True
style.font.color.rgb = RGBColor.from_string(GREEN)
header = section.header.paragraphs[0]
header.text = "1102tools | GovCon Growth"
header.alignment = WD_ALIGN_PARAGRAPH.RIGHT
header.runs[0].font.size = Pt(8)
header.runs[0].font.color.rgb = RGBColor.from_string(GRAY)
footer = section.footer.paragraphs[0]
footer.alignment = WD_ALIGN_PARAGRAPH.CENTER
footer.add_run("Prepared as of the date shown | Page ").font.size = Pt(8)
field = OxmlElement("w:fldSimple")
field.set(qn("w:instr"), "PAGE")
footer._p.append(field)
def add_table(
document: Document,
headers: list[str],
rows: list[list[object]],
widths: list[float],
*,
repeat_header: bool = True,
):
table = document.add_table(rows=1, cols=len(headers))
table.style = "Table Grid"
table.alignment = WD_TABLE_ALIGNMENT.CENTER
table.autofit = False
for index, header in enumerate(headers):
set_cell_text(table.rows[0].cells[index], header, bold=True, color="FFFFFF")
shade(table.rows[0].cells[index], NAVY)
table.rows[0].cells[index].width = Inches(widths[index])
for row_index, row in enumerate(rows):
cells = table.add_row().cells
for index, value in enumerate(row):
set_cell_text(cells[index], value)
if row_index % 2:
shade(cells[index], "F4F6F8")
cells[index].width = Inches(widths[index])
for row in table.rows:
row._tr.get_or_add_trPr().append(OxmlElement("w:cantSplit"))
if repeat_header:
table.rows[0]._tr.get_or_add_trPr().append(OxmlElement("w:tblHeader"))
return table
def add_bullets(document: Document, items: list[object], empty: str) -> None:
if not items:
document.add_paragraph(empty)
return
for item in items:
if isinstance(item, dict):
text = item.get("text") or item.get("decision") or item.get("question") or json.dumps(item, sort_keys=True)
else:
text = str(item)
paragraph = document.add_paragraph(text, style="List Bullet")
paragraph.paragraph_format.keep_with_next = False
paragraph.paragraph_format.keep_together = True
paragraph.paragraph_format.space_after = Pt(4)
paragraph.paragraph_format.line_spacing = 1.05
def cite_ids(paragraph, ids: list[str]) -> None:
if ids:
paragraph.add_run(" [")
paragraph.add_run(", ".join(ids), style="Evidence ID")
paragraph.add_run("]")
def build(record: dict, output: Path) -> None:
document = Document()
configure(document)
as_of = record.get("scope", {}).get("as_of_date", "Not stated")
has_bid_decision = bool(record.get("validation", {}).get("bid_context_complete"))
label = "GovCon Growth Brief" if has_bid_decision else "Evidence Brief - No Bid Decision"
brand = document.add_paragraph()
brand.paragraph_format.space_before = Pt(115)
brand.alignment = WD_ALIGN_PARAGRAPH.CENTER
run = brand.add_run("1102tools")
run.bold = True
run.font.size = Pt(12)
run.font.color.rgb = RGBColor.from_string(GREEN)
title = document.add_paragraph(label, style="Title")
title.alignment = WD_ALIGN_PARAGRAPH.CENTER
subtitle = document.add_paragraph(record.get("question", "GovCon growth research"))
subtitle.alignment = WD_ALIGN_PARAGRAPH.CENTER
subtitle.runs[0].font.size = Pt(14)
meta = document.add_paragraph(f"As of {as_of}\nPrepared by: ____________________")
meta.alignment = WD_ALIGN_PARAGRAPH.CENTER
document.add_page_break()
headings = [
"Executive Summary",
"Business Question and Scope",
"Company Context and Missing Inputs",
"Evidence and Analysis",
"Assessment or Pipeline",
"Risks, Contrary Evidence, and Limitations",
"User Decision and Next Actions",
"Reproducible Search Log",
"Evidence Register",
]
document.add_heading(headings[0], level=1)
document.add_paragraph(record.get("validation", {}).get("executive_summary", "This brief organizes the approved public and internal evidence."))
if not has_bid_decision:
quote = document.add_paragraph(style="Intense Quote")
quote.add_run("Decision boundary: ").bold = True
quote.add_run("Internal company context is incomplete. This brief contains no bid or no-bid recommendation.")
document.add_heading(headings[1], level=1)
document.add_paragraph(record.get("question", "Not provided"))
add_table(document, ["Scope field", "Value"], [[key.replace("_", " ").title(), value] for key, value in record.get("scope", {}).items()], [2.1, 4.8])
document.add_heading(headings[2], level=1)
add_bullets(document, record.get("user_context", []), "No internal company context was supplied.")
document.add_heading("Assumptions", level=2)
add_bullets(document, record.get("assumptions", []), "No working assumption was recorded.")
missing = record.get("validation", {}).get("missing_bid_context", [])
document.add_heading("Missing bid-screen context", level=2)
add_bullets(document, missing, "None recorded.")
document.add_heading(headings[3], level=1)
for finding in record.get("findings", []):
p = document.add_paragraph(finding.get("text", ""), style="List Bullet")
cite_ids(p, finding.get("evidence_ids", []))
if not record.get("findings"):
document.add_paragraph("No approved finding was recorded.")
for index, check in enumerate(record.get("validation", {}).get("numeric_checks", [])):
total = sum(float(value) for value in check.get("components", []))
locator = f"validation.numeric_checks[{index}]"
calculation_ids = [
item.get("id")
for item in record.get("evidence", [])
if isinstance(item, dict)
and item.get("source_class") == "calculation"
and item.get("locator") == locator
]
if len(calculation_ids) != 1:
raise ValueError(
f"numeric check {index} requires exactly one calculation evidence item whose locator is {locator}"
)
paragraph = document.add_paragraph(f"{check.get('label', 'Calculated total')}: {total:,.2f}")
cite_ids(paragraph, calculation_ids)
document.add_heading(headings[4], level=1)
document.add_paragraph(record.get("validation", {}).get("assessment", "No final assessment was approved."))
pipeline = record.get("validation", {}).get("pipeline", [])
if pipeline:
add_table(document, ["Candidate", "Signal", "Timing", "Confidence", "Next validation"], [[p.get("candidate", ""), p.get("signal", ""), p.get("timing", ""), p.get("confidence", ""), p.get("next_validation", "")] for p in pipeline], [1.5, 1.8, 1.1, 0.8, 1.7])
document.add_heading(headings[5], level=1)
add_bullets(document, record.get("conflicts", []), "No source conflict was recorded.")
add_bullets(document, record.get("unresolved_questions", []), "No unresolved question was recorded.")
for inference in record.get("inferences", []):
p = document.add_paragraph("Inference: " + inference.get("text", inference.get("reasoning", "")), style="List Bullet")
cite_ids(p, inference.get("evidence_ids", []))
document.add_heading(headings[6], level=1)
add_bullets(document, record.get("user_decisions", []), "No user decision was recorded.")
add_bullets(document, record.get("validation", {}).get("next_actions", []), "No next action was recorded.")
document.add_heading(headings[7], level=1)
queries = record.get("queries", [])
if queries:
add_table(document, ["Source / operation", "Sanitized parameters", "Retrieved", "Coverage and limits"], [[q.get("operation", q.get("source", "")), json.dumps(q.get("parameters", {}), sort_keys=True), q.get("retrieved_at", ""), f"{q.get('count', 'n/a')}; {q.get('limitations', '')}"] for q in queries], [1.5, 2.35, 1.25, 2.0])
else:
document.add_paragraph("No external query was made.")
document.add_heading(headings[8], level=1)
# LibreOffice can position a repeated header above the printable area on a
# later page of a long fixed-width table. Keep the header on the first page
# only so every continued evidence row remains fully visible after PDF
# conversion.
add_table(
document,
["ID", "Class", "Source", "Fact", "Limitations"],
[[
e.get("id", ""),
e.get("source_class", ""),
f"{e.get('title', '')}\n{e.get('locator', '')}",
e.get("fact", ""),
e.get("limitations", ""),
] for e in record.get("evidence", [])],
[0.55, 0.85, 1.55, 2.5, 1.65],
repeat_header=False,
)
output.parent.mkdir(parents=True, exist_ok=True)
document.save(output)
def main() -> int:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("record", type=Path)
parser.add_argument("output", type=Path)
args = parser.parse_args()
validator = Path(__file__).with_name("validate_research_record.py")
result = subprocess.run([sys.executable, str(validator), str(args.record)], check=False)
if result.returncode:
return result.returncode
build(json.loads(args.record.read_text(encoding="utf-8")), args.output)
print(args.output)
return 0
if __name__ == "__main__":
raise SystemExit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |