By Emrick DonadeiUpdated 2026-06-26grill-skill
According to AlphaMoat, as of the latest data month, Grill Skill has 107 downloads and 0 stars — ranked #56,395 of 63,926 Claude skills overall, and #9,911 of 10,757 in AI Agent.
Use when the user wants to create caliper evals for a skill, iterate on a skill using evals, or run the full create → test → improve cycle for a skill they want to measure.
A skill where the agent logs it's own findings for self-improvement
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express...
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co...
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Present multiple clarifying questions as an interactive Telegram form using inline buttons. Use when the agent needs to ask the user 2 or more clarifying questions before proceeding with a task, and wants to present them all at once in a structured form layout with selectable options and an "Other" free-text escape hatch. Triggers when: gathering multi-faceted requirements, onboarding flows, preference collection, or any scenario requiring structured multi-question input from the user via Telegram.
Use when the user wants to run, design, or interpret caliper evals, write an `.eval.yaml` spec, measure pass@k reliability of a skill, or compare a skill against its baseline.
Data month: — · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.