3,748 tools found
Skill for adding an iOS App Clip to an Expo app: target setup, associated domains, AASA hosting, Smart App Banner, and TestFlight submission.
ADHX reads X/Twitter post links as structured JSON with post text, author details, engagement metrics, and long-form article content.
Skill for LLM-as-judge evaluation: direct scoring, pairwise comparison with position swaps, bias mitigation, rubrics and pipelines.
Run Gemini 3 to audit Linux kernel patches for memory bugs, Terraform plans for cost drift, and generate hardened K8s manifests.
Create plugin-packaged specialist subagents with validated names, detailed personas, read-only defaults, and optional companion routing skills.
Transforms raw agent evaluation runs into decision-ready reports with explicit outcome populations, denominators, latency data, and experiment conditions
Deterministically inject sandbox/tool/worker/checkpoint faults into an agent workflow and produce a recovered/contained/unrecoverable verdict.
Give an agent a persistent, searchable MCP memory bank (search/write/read/stats) that auto-syncs to plain Markdown files.
Authors and validates Agent QA tests, suites and hooks via MCP or CLI while preserving canonical IDs and schema contracts.
Skill for debugging and fixing failed Agent QA runs from MCP evidence: minimal patches, validated definitions, and a narrow verification rerun.
Triages failed Agent QA runs from MCP evidence into a fixed failure category with confidence, ownership and next action.
Plans safe recurring agent runs with cron, external schedulers, loops, or built-in clocks while avoiding tight LLM timers.
