research-practitionerlisted

Practitioner-grounded deep research that extends the standard /research engine with structural enforcement against shallow vendor-flavored synthesis. Use this skill whenever the user says "/research-deep", "deep research", "not just docs", "find practitioners", "what experts who shipped X learned", "deeper research", or asks any research question where prior research output was rejected as superficial. Also trigger automatically when the topic is a fast-moving technical domain (AI agents, LLM infrastructure, novel architectures) where documentation-deep answers reliably mislead and only practitioner experience reports carry signal. Trigger especially when the user is visibly frustrated with a previous shallow research output, when they explicitly ask for named experts/practitioners, when they say "I need to actually understand X", or when the user mentions wanting to build / ship / operate something rather than just compare options. The skill enforces tier-tagged claims, verbatim primary-source quotes, mandat
OpenBioHack/openbiohack · ★ 0 · AI & Automation · score 75

Install: claude install-skill OpenBioHack/openbiohack

# Research-Practitioner Protocol This skill extends the standard `/research` skill (see `~/.claude/skills/research/SKILL.md`) with additional structural enforcement designed to prevent a recurring failure mode: sub-agents reading aggregator pages for 4-12 minutes and returning confident-sounding synthesis dressed as expertise. **Anchor incident**: a five-pass research project on agent infrastructure for B2B ops automation produced rising confidence theater (60% → 65% → 86% → 84%) while the user, a domain practitioner, repeatedly caught the research agents missing entire harness categories (OpenClaw, Hermes Agent), category-erroring Claude as a model rather than a platform, and parroting vendor capability claims without verifying against source code. Each pass was 4-12 minutes of aggregator skimming. The confidence numbers were performance, not estimates. The standard `/research` skill already does most of the right things (18-step protocol, tier classification, banned probability words, pre-mortem, steel-man, anti-escalation rule). This skill adds the layers that specifically address documentation-deep failure: practitioner experience as a non-negotiable input, verbatim primary-source quotes, mechanism-before-marketing, three-pass adversarial iteration, mandatory output sections that make gaps visible, and Norton-safe markdown. ## Relationship to the standard `/research` skill This skill **inherits** the entire standard `/research` protocol. Run all 18 steps of the stand