Loading...
Loading...
Found 6,049 Skills
Convergence loop that iteratively improves work until quality thresholds are met. Scores, diagnoses specific weaknesses, rewrites, re-scores, and repeats until all dimensions reach 8/10 or diminishing returns are detected. Use when you want to refine or iterate on work, after the analyst gives a REVISE verdict, or when output quality is below your bar. Part of the architect-system loop. Outputs to system/refinery-log.md.
Automate Amara tasks via Rube MCP (Composio). Always search tools first for current schemas.
Create a structured problem statement document for a feature, bugfix, or project. Use when starting a project, adding a feature, or fixing a bug and you need to clearly define the problem, context, desired outcome, and success criteria. Accepts input from Jira tickets (via MCP), document links, or text descriptions.
Generate Excalidraw diagrams. Use when creating flowcharts, ER diagrams, sequence diagrams, block diagrams, or any .excalidraw files.
Use jira CLI for Jira operations including issue management, project queries, transitions, and JQL search
tRPC router architecture, procedure design, and Vertical Slice Architecture patterns. Use when building tRPC APIs, designing procedures, or structuring backend slices.
View a plan's tasks and progress, regardless of output format.
Self-improvement and learning skill that helps Claude learn from user interactions, corrections, and preferences
Orchestrate the full paper pipeline end-to-end. Manage state propagation between phases (literature → plan → code → experiments → figures → tables → writing → review), support checkpointing and resumption. Use for assembling a complete paper from components.
Improve an existing skill in diegocanepa/agent-skills based on conversation learnings and submit the changes via a Pull Request.
Researches how the industry solves a defined issue, collects references from engineering blogs, open-source projects, and technical articles, then produces a design document with industry baseline, research summary, design goals, non-goals, and proposed design. Use when an issue definition exists in docs/issues/ and a concrete design is needed before implementation begins.
Guide for creating event-driven hooks for Claude Code. Use when automating responses to tool calls, lifecycle events, or implementing custom validations.