Dag Research
Web research as a DAG: retrieve (multi-query search + tiered crawl) → multi-lens fanout → judged synthesis, one command, zero-loss corpus artifact. Trigger: research this / what is X and which is better / grounded answer from the web / 调研 / 查一下X怎么做 / 综合网上说法 / dag-research. Skip: you only need raw page content (fetch directly) / question answerable from the codebase (read code) / wide design decis…
Install
$ agentstack add skill-abysscn-oh-my-dag-dag-research ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ● Environment & secrets Used
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-abysscn-oh-my-dag-dag-research) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/dag-research — grounded web research pipeline
One research question → grounded, judged answer. The engine searches (multi-query), crawls the best sources (tier-reordered: academic/standards/gov/docs/repo first), fans out N analysis lenses over the shared corpus concurrently, then judges and synthesizes a final answer. Stdout = the answer; the artifact keeps lens champions plus the full corpus appendix (nothing silently dropped).
Usage
bun run dag-research "" \
[--council] # conductor auto-authors the lenses from the corpus
[--super] # aggregate search mode (wider retrieval)
[--k 8] # search hits to consider (default 8)
[--crawl 5] # bodies to fetch (default 5; 0 = search snippets only)
[--no-tier] # disable source-tier crawl reordering
[--lens-count N] [--conductor-model M] [--lens-model M] [--reason-model M]
[--out path] # artifact path (default /tmp/dag-research--.md)Requires a search/fetch backend (TAVILY_API_KEY or equivalent — see .env.example); without web keys the script explains what's missing and exits.
Discipline
- One question per run. A whole domain = several focused runs; long queries return
nothing — split into short terms.
- Read the artifact, not just stdout when the answer will drive a design decision:
lens champions often carry orthogonal caveats the synthesis compressed away.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: AbyssCN
- Source: AbyssCN/oh-my-dag
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.