foryourhealth111-pixel/Vibe-Skills / bundled/skills/webthinker-deep-research
webthinker-deep-research
VerifiedDeep web research for VCO: multi-hop search+browse+extract with an auditable action trace and a structured report (WebThinker-style).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.0 KB |
| scripts/init_webthinker_run.py | script | 2.2 KB |
scripts/init_webthinker_run.py
View on GitHub#!/usr/bin/env python3
"""
Initialize an auditable "deep research run" folder.
This is intentionally minimal (stdlib only). It does NOT perform web search.
It scaffolds a workspace so the agent/user can:
- keep sources.json up to date
- append trace.jsonl for every action
- draft report.md continuously (think-search-and-draft)
"""
from __future__ import annotations
import argparse
import json
import re
from datetime import datetime
from pathlib import Path
def _slugify(text: str) -> str:
text = text.strip().lower()
text = re.sub(r"[^a-z0-9\u4e00-\u9fff]+", "-", text)
text = re.sub(r"-{2,}", "-", text).strip("-")
return text[:64] or "topic"
def main() -> int:
parser = argparse.ArgumentParser(description="Scaffold a WebThinker-style deep research run folder.")
parser.add_argument("--topic", required=True, help="Research topic/question (used for naming + header).")
parser.add_argument(
"--out",
default="outputs/webthinker",
help="Base output directory (default: outputs/webthinker).",
)
args = parser.parse_args()
now = datetime.now().strftime("%Y%m%d-%H%M%S")
slug = _slugify(args.topic)
run_dir = Path(args.out) / f"{now}-{slug}"
run_dir.mkdir(parents=True, exist_ok=False)
(run_dir / "trace.jsonl").write_text("", encoding="utf-8")
(run_dir / "sources.json").write_text(json.dumps({"topic": args.topic, "sources": []}, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
notes = f"""# Notes
- topic: {args.topic}
- created_at: {now}
## Working notes
"""
(run_dir / "notes.md").write_text(notes, encoding="utf-8")
report = f"""# Deep Research Report
**Topic:** {args.topic}
**Created:** {now}
## Executive summary
- (Write 3–6 bullets that can be validated by sources.json)
## Key questions
1. …
## Findings (evidence-linked)
### Finding 1
- Claim:
- Evidence: (link to sources.json entries)
- Confidence:
## Implications / trade-offs
## Next steps (verification plan)
- (Concrete next experiments / checks / code probes)
## Sources
See `sources.json`.
"""
(run_dir / "report.md").write_text(report, encoding="utf-8")
print(str(run_dir))
return 0
if __name__ == "__main__":
raise SystemExit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |