Research

Cross-reference compound IDs across 50+ databases (ChEMBL, DrugBank, PubChem, ChEBI, PDB, KEGG) via UniChem REST API. Resolve InChIKeys to source IDs, find structurally related compounds by connectivity, batch-translate between naming systems. No auth required.

Analyze learning management and training pathway systems for prerequisite mapping, competency-based progression, adaptive sequencing, and credential stacking. Evaluates LMS platforms, SCORM/xAPI compliance, completion prediction models, learning outcome measurement against Bloom's taxonomy, ROI tracking, and workforce development program effectiveness.

Draft a professional Hebrew letter for an Israeli traffic-ticket appeal — בקשה לביטול דו"ח or בקשה להישפט. Respectful tone, factual claims only, evidence list, requested remedy. Saves draft to ~/.openclaw/workspace/traffic-law-appeal-il/output/. Never sends or files.

Track cryptocurrency futures, options, and perpetual swaps with funding rates, open interest, liquidations, and comprehensive derivatives market analysis. Use when monitoring derivatives markets, analyzing funding rates, tracking open interest, finding liquidation levels, or researching options flow. Trigger with phrases like "funding rate", "open interest", "perpetual swap", "futures basis", "liquidation levels", "options flow", "put call ratio", "derivatives analysis", or "BTC perps".

Evaluate physical therapy personalization and adaptive treatment systems. Analyzes exercise recommendation algorithms (rules-based, collaborative filtering, protocol-driven), contraindication enforcement and safety checks, difficulty progression logic (multi-parameter advancement with regression pathways), patient compliance prediction models, home exercise program (HEP) generation and delivery workflows, video/image exercise library quality and accessibility, and outcome-driven treatment pla...

Evaluate therapy outcome measurement systems for rehabilitation and physical therapy. Analyzes functional improvement scoring (MCID, MDC, risk-adjusted residuals), treatment effectiveness comparison by therapist, diagnosis, and facility with case-mix adjustment, discharge readiness prediction (plateau detection, visit utilization trending), patient satisfaction correlation with clinical outcomes, and quality reporting compliance (CMS MIPS, CARF accreditation) using FOTO, AM-PAC, OPTIMAL, DASH...

Use when researching, specifying, designing, or QAing a Swiss FOI / Öffentlichkeitsgesetz / LTrans / transparency-law request builder, including “MuckRock for Switzerland” or FragDenStaat-style tools. Covers federal BGÖ/LTrans and cantonal workflows, authority discovery, deadlines, fees, EDÖB/FDPIC mediation, privacy/source protection, benchmarking, and product spec output.

Identifies the real underlying study design used in a medical or biomedical paper, distinguishes primary and secondary design components when papers are hybrid, and converts the paper into an evidence-aware design label suitable for literature appraisal, evidence grading, and downstream review workflows. Always identify the actual design from what the study did, not from how the authors describe it. Never fabricate references, metadata, or study features.

Control Spotify — play music, search the catalog, manage playlists and library, inspect devices and playback state. Loads when the user asks to play/pause/queue music, search tracks/albums/artists, manage playlists, or check what's playing. Assumes the Hermes Spotify toolset is enabled and `hermes auth spotify` has been run.

Music and audio file analysis agent. Produces reproducible Python/Shell analysis pipelines (librosa, pyloudnorm, essentia, madmom, mutagen, ffprobe) for BPM/key/time-signature detection, LUFS/True Peak loudness measurement, spectral balance, dynamic range (LRA/PLR/PSR), structural segmentation, mastering QC, and reference-track comparison. Verifies distribution-platform compliance (Spotify/Apple Music/YouTube/Tidal/Amazon Music/EBU R128). Effort baseline: xhigh; stems and batch >50 files expe...

Detect shell-company signals from live government registry data — single director, no accounts ever filed, overseas registered-office concentration, no employees, nominee address patterns. Pulls live unmodified registry records and scores the shell-probability. Use this skill when the user asks to "detect shell company", "is this a shell", "AML check", "flag suspicious entity", "money-laundering screening", "sanctions evasion indicator", or is doing compliance / investigation / fraud-research...

Automates academic research using the SerpAPI Google Scholar endpoint. Extracts citation graphs, h-index data, and co-author networks for literature reviews. Supports BibTeX export and cross-references with Semantic Scholar API.

Audit content gaps and decay using Ahrefs MCP data: missing topics, thin coverage, outdated content, and decaying pages. Use this skill when planning a content roadmap, refreshing a stale catalog, building topical authority, or identifying which existing pages need update versus replacement. Triggers on content gap, content audit, content refresh, content roadmap, decaying content, content decay, topical authority, what topics should we cover, where is competitor content stronger. Also trigge...

Detect AI-generated content using pure text analysis (no external API calls). Analyzes sentence uniformity, vocabulary diversity, repetition patterns, hedging language, paragraph uniformity, and personal experience signals. Returns a 0-100 confidence score plus flagged passages. Use when user says "AI content check", "AI detection", "AI written", "content authenticity", "AI content", "detect AI".

Use when searching academic papers, looking up citations, finding authors, or getting paper recommendations using the Semantic Scholar API. Triggers on queries about research papers, academic search, citation analysis, or literature discovery.

Access the Semantic Scholar Graph API to search papers and retrieve paper/author/citation data when you need literature discovery or citation graph exploration.

Use when the user is dealing with a leader — a CEO, political figure, boss, business partner, negotiating counterparty — whose self-presentation is larger-than-life in a way that feels like armor over insecurity: everything is the biggest/greatest/best, name plastered on everything, monuments and ornament everywhere, "I alone can fix it" framing. Helps the user tell armor from genuine stature, predict which kinds of criticism will land vs. harden the leader, and recognize early warning signs ...

Literature search and citation management for medical research. Searches PubMed, Semantic Scholar, and bioRxiv/medRxiv with verified citations. Anti-hallucination — every reference verified via API before inclusion. Generates BibTeX entries.

Scientific-methodology skills for the SciTeX ecosystem — publication-quality figures, statistics, experiment reproducibility. Distinct from `general/` (which covers package engineering) and per-package skills (which cover package-specific APIs). Load when authoring analysis scripts, preparing figures for manuscripts, or checking scientific rigour of ecosystem output.

Simulates a strict SCI peer-review workflow; trigger when a user uploads or pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–12) plus experimental-logic vulnerability checks and revision suggestions.

Structure individual scenes using Scene-Sequel framework with goal-conflict-disaster beats

Audit legal information systems that explain rights to the public, evaluating plain-language accuracy, jurisdiction-specific content correctness, reading level appropriateness targeting 5th-8th grade, multilingual support, WCAG accessibility compliance, and content update workflows when laws change. Use when reviewing legal aid websites, self-help law portals, court information systems, tenant rights platforms, or government benefits explainers.

White-box security audit. Blue-teamer and lead red-teamer run in parallel isolation for an independent first pass — neither sees the other's output during reconnaissance. A synthesis step categorizes findings into four prescriptive buckets (anchoring-suppressed, convergent, blue-flagged-unverified, divergent), producing a unified target list. Focused red-teamers then deep-dive each target. Iterates when exploit chains are discovered. Heavy and thorough by design.

Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state. Universal interceptor with domain auto-detection, 2-phase classification + evaluation, and triple-verdict output (veracity / fit / actionability). Anti-girouette guardrail that distinguishes drift from pivot — preserves human decisional authority. Manual invocation only (no hooks, no enforcement). Activate when an input may affect strategic-frame.md,...