The Rookery: Storm Research skill

The Rookery documents a portable Storm Research skill for source-backed briefings using independent perspectives, explicit disagreements, and source-quality audits. It is an independent workflow inspired by STORM, not a distribution of Stanford STORM software.

Workflow level n/a Source Repository-documented Outcome Not empirically evaluated here

Evidence & verification

Source level

Repository-documented
Grounded in a maintainer repository/README. Availability, stars and forks do not establish research benefit or correctness.

Outcome verification

Not empirically evaluated here
A documented resource or intended workflow, not a demonstrated academic outcome. No empirical benefit is established by its inclusion.

Sources checked

2026-10-17 (UTC)

Primary repository documentation reviewed by an AI editorial agent. Descriptions are bounded to that text; no execution or demonstrated effectiveness inferred. README workflow and skills sections support catalog identity and research use; do not infer every catalog skill was evaluated. SKILL.md steps 1–9 directly support the framed baseline, separate lenses, source audit and fidelity-review description. These are prescribed mechanisms, not observed execution. STORM inspiration is explicitly disambiguated; bibliographic links are not identity aliases.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (2)

Research applicability

Useful as an AI-assisted evidence-review protocol for researchers comparing competing accounts across disciplines. Suitability for a systematic review or any particular field remains an editorial suggestion, not demonstrated coverage or methodological validation.

Getting started

Editorial, untested suggestion: read the Storm Research skill and its linked references, define a small public-source question, then use the README installation guidance for only the needed skill. Manually inspect every source claim and disclosed gap before reusing a briefing.

Maintenance

Dated documentation snapshot only; continued maintenance and availability not independently established.

License

README and skill declare MIT; license file and dependency terms not independently audited.

Workflow & human oversight

No fixed automation level is assigned. The documented agent workflow proposes and synthesizes evidence; researchers remain responsible for framing, source rights, disciplinary judgment and final use.

Workflow level is not an evidence score; higher is not better evidence.

Approach

The skill specifies a frozen question and sourced baseline, isolated lens executors, contradiction mapping, claim-level source audits, and a separate fidelity check. Unavailable source access or unverifiable isolation must be disclosed as degraded research, not hidden.

Limitations

README and Storm Research SKILL.md only; linked lens charter, analysis-methods and fidelity-check reference files were not reviewed. No installation, research run or behavioral evaluation was performed. The README says other skill packages await revalidation after an evaluation reset. Multi-agent separation depends on the host harness and does not establish independent scientific evidence. No accuracy or time-saving outcome is established.

Reproducibility

Exact retrieved bodies, source URLs, UTC retrieval timestamps and SHA-256 envelopes saved. No upstream code or claimed outcomes reproduced. HEAD was mutable; no commit version pinned.

Adoption requirements

A compatible Agent Skills host and permitted source access are needed; the documented isolated-lens mode requires verifiably clean executor contexts. Audit package instructions, permissions and model-provider data handling before use; do not upload confidential research material without authorization.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.