Deep Research
Conduct systematic source-backed research with scoped questions, triangulation, contradiction handling, and citation-ready synthesis.
Install
$ agentstack add skill-rylaispirit-rylai-codex-hermes-skills-deep-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 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-rylaispirit-rylai-codex-hermes-skills-deep-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
> Rylai Codex-Hermes Edition | Original portable workflow by Rylai
Runtime Compatibility
- Codex: install under
~/.agents/skills/deep-researchand useagents/openai.yamlfor UI metadata. - Hermes: install under
~/.hermes/skills/deep-researchor expose the bundle throughskills.external_dirs. - Resolve bundled files relative to this skill directory; do not depend on paths from another runtime.
- Map capabilities to the current runtime: Codex image generation uses
image_gen; Hermes usesimage_generate. - Verify binaries, packages, credentials, network access, and tool availability before execution.
Portable Deep Research
Produce a source-backed answer to a question that genuinely needs multi-source research.
Workflow
- Define the research question, scope, date boundary, audience, and decision the report should support.
- Break the question into independent sub-questions and identify preferred primary sources.
- Search broadly, then open and inspect the most relevant sources.
- Use parallel research agents only when the runtime exposes delegation and the subtasks are independent.
- Build an evidence table containing claim, source, date, confidence, and contradiction notes.
- Triangulate important claims and explain disagreements instead of silently selecting one source.
- Synthesize the answer with citations attached to the claims they support.
- State unresolved gaps, stale evidence, and inference separately from verified fact.
Boundaries
- Ask a clarification question only when ambiguity materially changes the research result.
- Never invent a citation, quote, URL, statistic, publication date, or source conclusion.
- For current topics, verify freshness at execution time.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Rylaispirit
- Source: Rylaispirit/rylai-codex-hermes-skills
- 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.