561 skills · sorted by relevance
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
The English summary is being prepared. Showing the original description.
[32] ANALYZE. Ensure every critical claim has verifiable evidence with confidence levels. Each fact must have source + confidence percentage. If confidence <85%, enter Loop150 to find more sources. Use for critical decisions, factual claims, legal/compliance work, or any situation where unverified claims are dangerous.
The English summary is being prepared. Showing the original description.
Turns untargeted LC-MS/MS features (m/z, RT, MS/MS) into confidence-stratified metabolite annotations using spectral-library matching (matchms), in-silico tools (SIRIUS/CSI:FingerID, MetFrag) and molecular networking, and assigns a defensible MSI/Schymanski confidence level to each. Use when naming detected features, scoring MS/MS against a reference library, running SIRIUS, or deciding what confidence level an evidence set actually supports. For upstream feature extraction see metabolomics/xcms-preprocessing and metabolomics/msdial-preprocessing; for downstream enrichment that must respect these levels see metabolomics/pathway-mapping; for lipid-specific structural annotation see metabolomics/lipidomics.
The English summary is being prepared. Showing the original description.
Validates agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).
The English summary is being prepared. Showing the original description.
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
The English summary is being prepared. Showing the original description.
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
The English summary is being prepared. Showing the original description.
[32] ANALYZE. Ensure every critical claim has verifiable evidence with confidence levels. Each fact must have source + confidence percentage. If confidence <85%, enter Loop150 to find more sources. Use for critical decisions, factual claims, legal/compliance work, or any situation where unverified claims are dangerous.
The English summary is being prepared. Showing the original description.
Research a topic across multiple web sources, break it into focused questions, and read key pages in depth. Produce a report with source links, confidence levels, practical findings, and clear distinctions between facts and estimates.
Turn Claude Code session patterns into reusable behavior rules with confidence scores. Keep project-specific lessons separate, review and share learned rules, and combine related patterns into skills, commands, or agents.
Cross-reference public records to investigate companies, contracts, sanctions, property, and litigation. Match names across sources, label confidence levels, and build structured findings linked to original records, with optional statistical analysis of event timing.
Retrieve a country's resilience score, a measure of preparedness and recovery capacity, on a 0–100 scale. Review six domain scores, three broader components, recent trends, the 30-day change, and a confidence range for the result.
Guide market prediction workflows with LSTM, Transformer, and N-BEATS models using neural-trader commands and result storage. It explicitly identifies version 2.8.11 outputs as placeholders, so they cannot be treated as fitted models or evidence of prediction accuracy.
Apply simple code changes across files without calling an LLM, using agent-booster's local transformation engine. The skill checks a confidence score before saving results and records outcomes for cost tracking and future routing decisions.
Investigate failed Agent QA runs using recorded steps, logs, and saved evidence. Classify each failure, explain confidence and supporting findings, and identify the likely area to fix and the next action.
Route a goal through acc's scored-memory workflow, which uses evaluated stored information. Handle returned reasoning frames, submit proposals with confidence estimates, and present final answers with reference IDs before recording the eventual outcome.
Analyze Donald Trump’s negotiations, public messaging, and decisions using frameworks drawn from public records. Compare possible next moves with probabilities, confidence levels, and unknown factors, or switch to roleplay to simulate his responses in a given situation.
Examine recorded calls and voicemails for signs of AI-generated speech. Extract acoustic features, classify samples with machine learning, and prepare reports with confidence scores and sound visualizations to support voice impersonation investigations.
Build threat actor profiles from public reports, social media, code repositories, and other intelligence sources. Correlates indicators, maps related infrastructure and attack techniques, and produces structured dossiers with confidence assessments about who may be responsible.
Collect indicators of compromise, technical clues such as suspicious domains and file hashes, from incident evidence. Add context and confidence scores, then prepare them for detection, blocking, and structured sharing with partners.
Investigate suspicious IP addresses, domains, URLs, file hashes, and email artifacts using multiple threat intelligence sources. Assess confidence that each indicator is malicious, check links to known campaigns, and document evidence for blocking, monitoring, or allowing it.
Investigate repository behavior, architecture, or possible causes without changing files. Trace relevant code and supporting material, then rank explanations by evidence and confidence, with concrete file references and clear distinctions between observations, conclusions, and unresolved questions.
Checks factual claims in articles and reports against current sources or independently queried original data. Applies corrections, assigns one of six confidence levels to each claim, and produces a sourced report with an overall pass or fail assessment.
Turn search results from chat, email, documents, and other sources into a coherent answer. Merge duplicate information, retain source references, highlight conflicting accounts, and reflect source freshness and authority when expressing confidence in the findings.
Turns user corrections and recurring mistakes into actionable rules with confidence scores. It records when each rule applies and why it matters, so relevant lessons can be retrieved before similar work begins.