Kartik-Doye/Ravengard-AI-Recruiter / .agents/skills/blueprint
blueprint
VerifiedDocuments observed or proposed software architecture with evidence-backed context, container, component, dynamic, data-flow, and deployment views. Use when the user needs architecture diagrams, onboarding material, trust boundaries, or a design view before a major change.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.2 KB |
| assets/template.html | other | 5.3 KB |
| references/diagram-guide.md | markdown | 3.2 KB |
| references/research.md | markdown | 3.1 KB |
| scripts/validate-mermaid | other | 3.4 KB |
scripts/validate-mermaid
View on GitHub#!/usr/bin/env python3
"""validate-mermaid: static syntax checks for .mmd diagram sources.
Catches the failures that break rendered architecture docs without
needing the mermaid toolchain: missing/unknown diagram type, unbalanced
brackets/quotes, tab indentation, duplicate node ids, empty labels.
Deterministic, read-only. It cannot prove the diagram RENDERS: for
that, render once with mermaid-cli when available and say so.
Usage: skills/blueprint/scripts/validate-mermaid <file.mmd>... [--json]
Exit 0 = all checks pass; 1 = findings; 2 = usage error.
"""
import json, re, sys
from pathlib import Path
KNOWN_TYPES = ("flowchart", "graph", "sequenceDiagram", "classDiagram",
"stateDiagram", "erDiagram", "journey", "gantt", "pie",
"mindmap", "timeline")
def check_file(path: Path):
findings = []
lines = path.read_text().splitlines()
if not lines:
return [{"check": "empty", "detail": "no content"}]
first = lines[0].strip()
if first.startswith("%%"):
first = next((l.strip() for l in lines if l.strip() and not l.startswith("%%")), "")
if not any(first.startswith(t) for t in KNOWN_TYPES):
findings.append({"check": "diagram-type", "detail":
f"first statement is not a known type: {first[:40]!r}"})
body = "\n".join(lines)
for opener, closer, name in (("{", "}", "braces"), ("[", "]", "square brackets"),
("(", ")", "parens"), ('"', '"', "quotes")):
if name != "quotes" and body.count(opener) != body.count(closer):
findings.append({"check": "balanced", "detail":
f"unbalanced {name}: {body.count(opener)} vs {body.count(closer)}"})
if name == "quotes" and body.count('"') % 2:
findings.append({"check": "balanced", "detail": "unbalanced quotes"})
for i, l in enumerate(lines, 1):
if "\t" in l:
findings.append({"check": "whitespace", "detail": f"tab on line {i}: mermaid prefers spaces"})
# duplicate node ids: word[ or word( or word{ at line starts
ids = re.findall(r"^\s*([A-Za-z_][A-Za-z0-9_]*)\s*(?:[\[\(\{])", body, re.M)
seen, dups = set(), set()
for i in ids:
if i in seen:
dups.add(i)
seen.add(i)
for d in sorted(dups):
findings.append({"check": "duplicate-node", "detail": f"node id defined twice: {d}"})
if re.search(r"[\[\(]\s*[\]\)]", body):
findings.append({"check": "empty-label", "detail": "node with empty label [] or ()"})
return findings
def main():
args = [a for a in sys.argv[1:] if a != "--json"]
if not args:
print("usage: validate-mermaid <file.mmd>... [--json]", file=sys.stderr)
return 2
all_findings = {}
for a in args:
p = Path(a)
if not p.is_file():
all_findings[str(p)] = [{"check": "missing", "detail": "file not found"}]
continue
f = check_file(p)
if f:
all_findings[str(p)] = f
if "--json" in sys.argv:
print(json.dumps({"files_checked": len(args), "findings": all_findings}, indent=2))
elif not all_findings:
print(f"validate-mermaid: {len(args)} file(s) pass static checks")
else:
for path, fs in all_findings.items():
for f in fs:
print(f"FAIL {path}: {f['check']}: {f['detail']}")
return 1 if all_findings else 0
if __name__ == "__main__":
sys.exit(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 |