continuous-learning-v2
affaan-mInstinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
knowledge-synthesis
anthropicsCombines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.
web-search-plus
openclawUnified search skill with Intelligent Auto-Routing. Uses multi-signal analysis to automatically select between Serper (Google), Tavily (Research), Exa (Neural), You.com (RAG/Real-time), and SearXNG (Privacy/Self-hosted) with confidence scoring.
docstrange
openclawDocument extraction API by Nanonets. Convert PDFs and images to markdown, JSON, or CSV with confidence scoring. Use when you need to OCR documents, extract invoice fields, parse receipts, or convert tables to structured data.
provenance-audit
dadbodgeoffAI generation provenance and audit trail tracking. Records decision factors, data lineage, reasoning chains, confidence scoring, and cost tracking for AI-generated content.
scoring-engine
dadbodgeoffStatistical scoring with z-scores, percentiles, freshness decay, and cross-category normalization. Rank and compare items with confidence scoring.
learning-systems
Implicit feedback scoring, confidence decay, and anti-pattern detection. Use when understanding how the swarm plugin learns from outcomes, implementing learning loops, or debugging why patterns are being promoted or deprecated. Unique to opencode-swarm-plugin.
prioritization-calculator
a5c-aiAutomated calculation and scoring for product prioritization frameworks including RICE, ICE, MoSCoW, and custom weighted scoring. Normalizes scores, validates inputs, and generates priority rankings with confidence intervals.
continuous-learning-v2
sangrokjungInstinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
proof-of-work
MadAppGangProof artifact generation patterns for task validation. Covers screenshots, test results, deployments, and confidence scoring.
brainstorming
MadAppGangCollaborative ideation and planning with resilient multi-model exploration, consensus scoring, and adaptive confidence-based validation
pg-data
tyrchenGenerate safe, read-only PostgreSQL queries from natural language. Use when users need to query blog_small, ecommerce_medium, or saas_crm_large databases. Supports query generation, execution, and result analysis with confidence scoring.
continuous-learning-v2
xu-xiangInstinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
balls
gbasinDecomposed reasoning with explicit confidence scoring
rice
neurofooRICE prioritization scoring initiatives by Reach, Impact, Confidence, and Effort. Use for feature prioritization, roadmap planning, or when comparing initiatives objectively.
dag-output-validator
curiositechValidates agent outputs against expected schemas and quality criteria. Ensures outputs meet structural requirements and content standards. Activate on 'validate output', 'output validation', 'schema validation', 'check output', 'output quality'. NOT for confidence scoring (use dag-confidence-scorer) or hallucination detection (use dag-hallucination-detector).
dag-confidence-scorer
curiositechAssigns confidence scores to agent outputs based on multiple factors including source quality, consistency, and reasoning depth. Produces calibrated confidence estimates. Activate on 'confidence score', 'how confident', 'certainty level', 'output confidence', 'reliability score'. NOT for validation (use dag-output-validator) or hallucination detection (use dag-hallucination-detector).
dag-hallucination-detector
curiositechDetects fabricated content, false citations, and unverifiable claims in agent outputs. Uses source verification and consistency checking. Activate on 'detect hallucination', 'fact check', 'verify claims', 'check accuracy', 'find fabrications'. NOT for validation (use dag-output-validator) or confidence scoring (use dag-confidence-scorer).
scientific-data-extraction
jkitchinExtract structured data from scientific literature across multiple formats (PDF, HTML, images, plain text). Auto-detects scientific domain to recommend specialized tools for chemistry/materials when appropriate. Use this skill when: extracting numerical data from papers, digitizing graphs/plots, parsing tables from PDFs, extracting chemical properties or reactions, or converting unstructured scientific text to structured formats. Key capabilities: format detection and routing, domain-specific extraction (chemistry/materials), multi-method validation, table extraction, graph digitization, LLM-enhanced extraction with verification, confidence scoring.
Framework Detector
FortiumPartnersMulti-signal framework detection with confidence scoring for 6 major frameworks
confidence-scoring
laurigatesAssess quality of PRPs and work-orders using systematic confidence scoring. Use when evaluating readiness for execution or subagent delegation.
aireview
materialofairProfessional multi-agent AI code review with confidence scoring
pr-review
Mathews-TomPull request and code review with diff-based routing across five dimensions: code quality and guideline compliance, test coverage analysis, silent failure detection, type design and invariant analysis, and comment quality auditing. Classifies changed files and loads only relevant review methodologies. Produces severity-ranked findings (Critical, Important, Suggestion) with confidence scoring. Replaces pr-review-toolkit plugin. Trigger phrases: "review my PR", "review this code", "check my changes", "is this ready to merge", "audit this PR", "review before committing", "check code quality", "any issues with this code", "pre-merge review", "look over my changes", "code review". Use this skill when reviewing code before commit or merge, checking PR quality, or when the user asks for feedback on recent modifications.
security-review
joaquimscostaSecurity-focused code review identifying high-confidence exploitable vulnerabilities with two-axis severity/confidence scoring, OWASP 2025 alignment, and false positive filtering. Use when user runs /security-review, /review:security-review, requests a "security review", "security audit", "vulnerability scan", or mentions "find vulnerabilities", "check for exploits".
agent-skill-orchestrator
ericgandradeThis skill should be used when the user needs to solve a complex task and wants a detailed execution plan using the best available resources. Analyzes user requirements, discovers available plugins/agents/skills/MCPs, performs intelligent matching with confidence scoring, and creates strategic execution plans with alternatives. Works across all AI CLI platforms.
continuous-learning-v2
codelablyInstinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
detecting-ai-code
galihcittaUse when auditing code for AI authorship, reviewing acquisitions/contractors, verifying academic integrity, or during code review - provides systematic tiered framework for detecting fully AI-generated AND AI-assisted code patterns with confidence scoring
research-consolidator
mrelphThis skill should be used when the user asks to "consolidate research", "synthesize findings from multiple sources", "compare research from Claude and GPT", "merge research outputs", "combine AI research results", "create a research report from these sources", or has research from multiple AI models, web searches, or documents to combine into a unified analysis. Also triggered by mentions of cross-referencing findings, confidence scoring, or source attribution.
continuous-learning-v2
agent-arc-744Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
continuous-learning-v2
gocronxInstinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
loop-instinct-system
agent-arc-744Continuous learning instinct engine for trading bots. Manages named instincts with confidence scoring (0.0-1.0) that evolve based on trade outcomes. Integrates with LLM-based trading agents via tag injection.
Continuous Learning v2
yts806379An instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills, commands, or agents.
continuous-learning-v2
ERP-CORE-DEVInstinct-based pattern learning with confidence scoring and auto-evolution
Multi-Brain Score
fatih-developerConfidence scoring overlay for multi-brain decisions. Each perspective rates its own confidence (1–10) with justification. Consensus uses scores as weights, flags low-confidence areas, and surfaces uncertainty explicitly.
continuous-learning-v2
royaluniondesign-sysInstinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.