MCP App StoreMCP App StoreThis skill enables an agent to perform post-critical-path analysis on collections of durable verdicts. It focuses on mining validation history to find recurring patterns of evidence, specifically overweighting failures (NOT_PROVEN or FAIL) to identify gaps in the current rule set.
Use this skill when tasked to "learn from verdicts" or "mine validation history." It is designed for off-path continuous learning and evidence-based engineering.
Designed for agents following the AgentOps operating loop, likely compatible with Claude Code, Codex, and other advanced orchestrators using durable verdict systems.
This skill has not been reviewed by our automated audit pipeline yet.
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr
RPI — Full Lifecycle Orchestrator
Orchestrates a three-phase RPI lifecycle (discovery → implementation → validation) for autonomous agent workflows, including complexity classification, routing,
Beads BV — Graph-Aware Triage
Graph-based backlog triage using bv/br: rank priorities, find bottlenecks, and produce machine-readable recommendations for agents (robot mode).
cass Session Search
Mine past agent sessions for working prompts, decisions, rituals and recovery patterns (operational tooling).
PR Preparation & Validation
Systematically prepares pull requests by validating tests, analyzing commit patterns, and generating high-quality, structured PR bodies.
Operationalize
Distill research and learnings into durable automation rules.
Handoff: Durable Session Continuation
Writes compact session handoffs to ensure seamless continuation across agents or context resets.
Meta Skill Search Engine
A powerful search and load engine for AgentSkills across multiple corpora, enabling agents to discover and implement the right skill for a task.
CTX Link Check — Documentation Link Auditor
Scan project markdown for broken internal links, missing images, and unreachable external URLs; produce a clear report and suggested fixes before docs releases.
Skill Evolve
Iteratively improve an existing Agent Skill by observing real outputs, extracting recurring failure patterns, and applying small, verifiable fixes (OTF + JIT +
Fix (Workflow Orchestrator)
Orchestrates bug investigation and resolution workflows: diagnose, implement, test, and commit fixes with human checkpoints.
Humanizalo — Humanize AI Writing
Detects 40 AI writing ‘tells’ and rewrites text to inject a distinct human voice, with a 3-pass self-audit loop and 6‑dimension scoring.
E2E Check
Run end-to-end Playwright test suites or perform interactive browser walkthroughs to verify UI and user journeys for a project.
FDA Labeling Compliance Review
Automated checklist and structured workflow to assess FDA labeling compliance for foods, drugs, dietary supplements and medical devices; produces findings with
Property-Based Testing — Catalog & Best Practices
A practical guide and pattern catalog for property-based testing (PBT): when to use it, property catalog, libraries, and best-practice strategies across languag
GitHub PR Review
Review GitHub pull requests and post structured inline review comments that follow project guidelines and minimize duplicate feedback.
