Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Research · rlaope | DecimalAI

researchby rlaope

Research

rlaope/ulw-research

Source rlaope/oh-my-hermes ↗License MIT

[omh] Web research with citation discipline on top of native search - every claim carries a live URL and unfetched claims stay not observed; for a decision-ready brief use research-brief, and for ongoing Scout/Analyst/Briefer coordination use research-department.

SkillScore50Maintained

Automatic

Research pack

Last verified 8/27/2026

What it changes

Passed 8 of 16 test cases with the skill, and 4 of 16 without it.

Without skill27%

With skill50%

Checks it passed that the model alone missed

Contains a verified-claims ledger with an annex for unresolved claims.
Provides repository version pins or commit references for Redis and KeyDB.
Includes pinned commit permalinks or version tags for studied repositories.

and 6 more in the full report

5 fixed6 passed either way11 still failing0 broke

Pass-rate lift: +23 pp
Tokens: +68%
Agent turns: 0%
Response time: +16%

Model gemini-3.6-flashMeasured 8/27/2026v411 of 22 cases passed with skill · 16 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/rlaope-ulw-research/SKILL.md https://app.decimal.ai/s/rlaope-ulw-research/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add rlaope-ulw-research, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/rlaope-ulw-research/ and pins it in .decimal/skills.lock

decimalai skills add rlaope-ulw-research

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/rlaope-ulw-research/SKILL.md https://app.decimal.ai/s/rlaope-ulw-research/SKILL.md

Raw file: /s/rlaope-ulw-research/SKILL.md ↗ · machine-readable summary at /s/rlaope-ulw-research.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

Before drafting our system spec, I need a deep research breakdown comparing open-source queue engines like Celery, BullMQ, and Temporal. Please examine their internal mechanisms, tradeoffs, and licenses, referencing specific commits or version tags where relevant. Give me a decision-oriented dossier listing key evaluation criteria, recommended versus rejected options with rationales, potential risks, and a clear distinction between confirmed facts and open uncertainties.

What was checked, without and with the skill
Checked	Without skill	With skill
Includes pinned version tag or commit references for each studied queue engine.	Missed	Passed
Contains a verified-claims ledger with an annex for unresolved claims.	Missed	Passed
Includes a plan-feed block listing decision drivers, viable options, and rejected candidates.	Missed	Passed

case-01 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md146 linessingle file

Research

This is a Hermes-native research workflow skill.

Why This Exists

research exists to make Hermes a careful research engine: it routes research demands to source-backed evidence gathering - from live web citations to studied reference implementations - verifies contested claims, and distills decision-grounding output so planning starts from evidence instead of guesses.

Do Not Use When

The user asks for a full plan-to-PR delivery cycle; use ultrawork (its delivery_boundary capability) or a planning workflow after research instead.
The request is purely local repo inspection with no external, current, citation, or source-comparison need.
The study target is this repository itself rather than external references; use codebase-onboarding.
The user needs coding execution, review, CI, or merge evidence rather than research synthesis.
The requested output is a typed candidate list or acquisition status without factual synthesis; use source-finder.
The user needs a market, customer, or pricing decision brief with evidence-versus-inference treatment; use research-brief.
The user asks for recurring monitoring, a source inbox, or Scout/Analyst/Briefer operations; use research-department.
Correctness is a bounded, versioned official or upstream guidance question; use best-practice-research.

Examples

Good example:

Prompt: 딥리서치로 다른 오픈소스 구현들을 깊게 보고 스펙 잡기 전에 근거를 만들어줘.
Expected behavior: Run the Hermes research lane at depth: decompose axes, study the most relevant reference implementations with pinned refs, verify contested claims, then distill a decision-grounding dossier for the planning step.
Why: The user explicitly asked for deep pre-spec grounding built on other open-source implementations.

Bad example:

Prompt: 이 레포 코드 구조만 파악해줘.
Expected behavior: Route to codebase-onboarding because the study target is this repository, not external sources or reference implementations.
Why: Local repo orientation needs no external evidence gathering or claim verification.

Completion Checklist

The research question, source boundaries, recency assumptions, and confidence level are named.
Observed sources, inference, synthesis, and unresolved retrieval gaps are separated.
Follow-up planning or handoff uses the research summary without calling it execution evidence.

Recovery Notes

Track record

Benchmark

8 / 16

test cases passed, vs 4 / 16 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/25/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

rlaope / oh-my-hermes

skills/ulw-research/SKILL.md

View on GitHub ↗

License MITImported 8/25/2026Version v4

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Research

Why This Exists

Do Not Use When

Examples

Completion Checklist

Recovery Notes

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills