Runs PII anonymization, local de-anonymization, and deterministic local detector checks for text and supported files. Use for redact/restore flows, file-firs...
Operate Todoist through a Python CLI backed by the Todoist REST API. Use when the task requires deterministic Todoist automation instead of chatty natural-la...
Generate reusable multi-step agent workflow blueprints. Use for trigger/action orchestration, deterministic workflow definitions, and automation handoff arti...
Deterministic end-to-end test skill for validating CLI publish lifecycle and verifying registry and metadata round-trips.
Performs deterministic end-to-end tests to validate ClawHub CLI publish lifecycle commands and verify registry metadata accuracy.
Convert Markdown text to beautiful Xiaohongshu (XHS) style card images with 5 themes, deterministic browser screenshot rules, auto-pagination, smart title ex...
Deterministically coordinates autonomous planning and execution across available skills under strict guardrails. Use only when the user explicitly activates this skill by name to run autonomously unti
Ship production code with AI agents through acceptance contracts, micro diffs, red green loops, and deterministic handoff checkpoints.
Transform OpenClaw cron jobs into Lobster workflows. Analyze, inspect, and validate job migrations. Use when converting automations to deterministic, approval-gated workflows with resume capabilities.
Build a cost-efficient LLM evaluation ensemble with sampling, tiebreakers, and deterministic validators. Learned from 600+ production runs judging local Olla...
Manage Apple Notes via deterministic local scripts (create, append, list, search, export, and edit). Use when a user asks OpenClaw to add a note, list notes, search notes, or manage note folders.
Lightweight helper to enforce TDD-style loops for non-deterministic agents.
Deterministic pipeline for streetwear and fashion images that captures user intent, enforces constraints, generates with Nano Banana Pro, critiques with Gemi...
Processes text input using a tool to return deterministic output, serving as a reference example for OpenClaw agent development.
Generate a deterministic, template-preserving 16-section SDS/MSDS package from 1 DOCX template, 1 prompt/rule file, and 1-3 source SDS/MSDS files, with DOCX/...
Compare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboards and model promotion decisions.
Anti-drift protocol script. Ensures parity between docs and system. Triggers: 'bom dia PROJECT' / 'good morning PROJECT' (load project context with health ch...
Autonomous engine that systematically evaluates and ranks agent skills across models using rubric grading, error taxonomy, and improvement feedback loops.
Production-safe change protocol for AI agents: preflight checks, risk scoring, rollback planning, HITL gates, and post-change validation. Use when users ask...
Evaluate agent quality and reliability with practical scorecards: accuracy, relevance, actionability, risk flags, tool-call failures, regression checks, and...
Prevent quality regressions after agent changes. Run targeted before/after checks for prompt, model, config, and tool updates; return pass rate, failure clus...
Use when creating or improving a skill for an AI agent, especially when the skill needs strong trigger wording, project-local context, references, scripts, t...
Use when: hardening OpenClaw cron/background workers (POSIX shells: bash/sh) against brittle quoting, cwd/env drift, and false pipeline failures (SIGPIPE, pi...