2.3K skills · sorted by relevance
Check opencode commands, HTTP server behavior, lifecycle events, and terminal startup with purpose-built scripts. Find stored sessions by ID, title, or scoped message searches, and export conversations as JSON for further inspection.
Store team conventions, troubleshooting notes, and project knowledge on a self-hosted Hindsight server. Retrieve relevant context before new tasks and draw on recorded experiences, including successful procedures, failed attempts, and individual preferences attributed to specific people.
Review open commitments in acc and record success or failure with supporting notes. Distinguish self-assessment from owner validation or observed real-world results, and keep commitments open when they are still waiting on an outcome.
Assess your Claude Code experience with a quick checklist or a deeper review across 10 feature areas. Receive a skill profile, identified gaps, and a personalized learning path with priorities, estimated study time, and practice exercises.
Add social-emotional learning—practicing emotional awareness, self-management, empathy, and collaboration—to subject lessons in OpenMAIC. It connects these goals to academic concepts through discussion, choices, feedback, retries, and reflection.
Turn work history into clear accomplishment statements for performance reviews, promotion cases, and weekly updates. Use Copilot CLI sessions, git commits, and GitHub pull requests to connect each action with its result and supporting evidence.
Design workflows that evaluate and refine AI outputs through self-review, separate generation and evaluation roles, tests, or weighted scoring criteria. Includes patterns for structured feedback, iteration limits, and stopping when quality stops improving.
Set up encrypted connections between devices with Tailscale and control access by user or device. The skill covers network routing, device name resolution, and self-hosting the coordination server with Headscale.
Connect NanoClaw to an existing Signal account through signal-cli, a command-line tool for Signal. Use personal chats, Note to Self, or group conversations to exchange messages with an AI assistant without registering a new number.
Prepare a graded Claude Managed Agent for recurring schedules, event triggers, or on-demand use. Validate timing, build deployment request data, optionally include self-evaluation for each run, and document the next steps in a roadmap.
Use an English working contract in Trae to address repeated failures or unverified completion. It separates execution, self-review, and acceptance, guiding agents through small checks and delivering results with evidence, residual risks, and confirmation needs.
Execute development subtasks under a supervising agent, starting with an implementation plan and impact analysis. Deliver code and a three-question self-review in a defined completion format for the supervisor to assess.
Turn completed research, analysis, reports, or plans from the current session into a self-contained HTML artifact. A renderer controls layout, typography, and color, using structured content and a choice of two visual styles.
Turn Matomo analytics into reports on organic traffic, landing pages, devices, countries, referrers, and search keywords. Use data from a self-hosted instance or Matomo Cloud to support reporting alongside GA4 or as an alternative.
Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.
Track machine learning experiments with SwanLab by recording training settings, metrics, and media such as images and audio. Learn to compare runs, inspect training charts, and connect existing training code to local, cloud, or self-hosted dashboards.
Helps decide whether to handle a task directly, create a subagent, or route it to an agent already familiar with the work. The choice depends on required background knowledge and whether plausible but incorrect results can be checked.
Assess your Claude Code knowledge through multiple-choice questions with immediate feedback. Choose a quick check or a comprehensive assessment to identify gaps and receive a prioritized learning path, with practice projects included in the comprehensive mode.
Understand SenseNova Team Harness, a workspace you host yourself for collaboration between people and local AI agents. Learn its core concepts, startup requirements, and workflow for assigning tasks, sharing input files, and reviewing versioned deliverables.
Review CI/CD pipelines, the workflows that build and release software, for unsafe code execution, exposed secrets, and excessive permissions. Combine automated scanning with manual checks to document reproducible findings and suggested fixes.
Revise an academic paper based on internal review comments. Reads review report or annotated manuscript, then applies revisions one by one with user approval. Trigger when user says "self revise" / "paper-selfrevise" / "内部修改" / "根据审稿意见修改".
The English summary is being prepared. Showing the original description.
Archive the current Cloudroom thread and release its runtime. Use only when the user explicitly asks to self-archive, archive yourself, or archive this thread.
The English summary is being prepared. Showing the original description.
[omh] Agent is stuck, looping, or drifting: capture a stuck, looping, drifting, or repeatedly failing agent run, diagnose the likely failure pattern, and prepare the smallest safe recovery action. Use when the user says: agent-debug, agent debug, agent debugging, agent introspection, agent self-debug, self-debug, self debugging, looping agent.
The English summary is being prepared. Showing the original description.
Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously. Use when building agents that get better over time, managing auto- memory, or designing self-correcting feedback loops.
The English summary is being prepared. Showing the original description.