Agent Skills by Memect
Showing 23 vetted skills indexed across 1 GitHub repositories.
data-sensibility
Identifies data quality issues and pattern variations to guide extraction design.
cross-document-verification
Compare anchored facts across multiple documents and return a case-level verdict.
auto-model-selection
Identifies suitable worker LLMs for document-verification tasks using Context7 queries.
corner-case-management
Identifies and isolates edge-case documents using structured JSON registry rules.
version-control
Track changes to KC artifacts with filesystem-based versioning and changelogs.
work-decomposition
Split rulesets into TaskBoard tasks with sequencing and grouping.
compliance-judgment
Evaluate extracted entities against verification rules and return structured judgments.
evolution-loop
Diagnose, classify, patch, and revalidate AI skills and workflows.
skill-to-workflow
Distill validated verification skills into worker-LLM workflow blueprints.
bootstrap-workspace
Bootstrap a document verification workspace with Rules/, Samples/, and .env scaffolding.
skill-creator
Guides teams through creating and refining formal SKILL.md documents.
document-chunking
Chunk long documents into structured blocks with heading context.
entity-extraction
Extract domain-specific entities from documents using regex and LLM methods.
rule-graph
Map relationships between verification rules for impact analysis and conflict detection.
tree-processing
Build a cached JSON hierarchical tree indexing document structure for rule-based verification.
dashboard-reporting
Aggregate verification results and progress logs into a self-contained HTML dashboard.
rule-extraction
Extract atomic verification rules from regulatory text with source references.
pdf-review-dashboard
Generate a self-contained HTML dashboard comparing PDFs with verification results.
task-decomposition
Decompose verification rules into atomic sub-tasks with cost-aware methods.
quality-control
Monitor production verification results and trigger evolution loops on drift.
document-parsing
Parse PDFs and scans into Markdown with preserved headings and tables.
skill-authoring
Translate verification rules into Claude Code skills with SKILL.md structure.
confidence-system
Quantify and calibrate extraction and verification trustworthiness with multi-signal confidence scoring.