Hunt Research Sources
Run a wide research source hunt and return a ranked findings report. Use when the user asks to "hunt for sources", "go find sources on X", "scan the web for", "do a research sweep", "find the best sources", or compare many sources before deciding what matters. Produces a sourced report with accepted findings, rejected sources, conflicts, and gaps.
Install
$ agentstack add skill-ariaxhan-the-agent-library-hunt-research-sources ✓ 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 No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ 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-ariaxhan-the-agent-library-hunt-research-sources) 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
Hunt Research Sources
Go wide, kill noise, and bring back only findings that survive quality and novelty filters.
Use this for breadth. If the user gives one article or one URL, use a single-source extraction workflow instead.
1. Define the hunt
Clarify in your own notes:
- Topic
- Time sensitivity
- Source types worth prioritizing
- What counts as useful evidence
- Output path
Default output:
research/YYYY-MM-DD-hunt-topic.mdIf the project already has a research folder, use that.
2. Reconnaissance
Gather 8-15 candidate sources from relevant channels:
- Official docs or primary sources
- GitHub repos/issues/discussions
- Engineering blogs or postmortems
- Papers or technical reports
- Forums only when lived experience matters
- News only when the topic is current
Record source title, URL, date, and why it might matter.
3. Triage hard
Reject weak sources before deep reading:
- Marketing fluff
- Rewritten listicles
- Outdated material for fast-moving topics
- Paywalled/unreadable pages unless the user can provide them
- Sources that only repeat already-known claims
- Claims with no implementation detail, evidence, or examples
Aim to reject at least half.
4. Extract survivors
For each surviving source, capture:
- Main claim
- Concrete details: flags, numbers, configs, commands, caveats, examples
- Failure modes or tradeoffs
- Evidence strength
- What is new relative to the rest of the hunt
Avoid long quotes. Link everything.
5. Synthesize
Write the report:
# Hunt: |
## Summary
## Top Findings
### 1.
Source:
Why it matters:
Evidence:
Confidence:
## Conflicts
| Claim A | Claim B | Current read |
## Rejected Sources
| Source | Reason |
## Gaps
## Recommended Next Moves
6. Quality gate
Before finishing:
- Every major claim has a URL.
- Findings are ranked, not dumped.
- Rejections are logged.
- Conflicts are explicit.
- Gaps are named.
- The report says what decision it supports.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ariaxhan
- Source: ariaxhan/the-agent-library
- 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.