claude-code-best-practices
Comprehensive guide for optimizing Claude Code workflows and effectiveness. Use when writing or improving CLAUDE.md files, managing context windows, crafting…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,710 results
wallet-setup
This skill should be used when setting up a 1Sat wallet programmatically, creating a new wallet instance, configuring local + remote storage, managing the…
codex-agent-setup
Explicit-only installer for the Sigma Auth Siggy Codex custom agent. Use ONLY when the user explicitly asks to install, update, check, uninstall, or set up the…
nuke-implement
Use when a task should be implemented by delegated subagents rather than the session's own hands — "nuke implement", "implement this with agents", "build this…
scaffold-skill
Write, update, validate, and package agent skills inside an existing or new repository. Use when the user asks to scaffold a skill in a repo, write a SKILL.md,…
synapse
Pattern detection and automatic skill recommendation system. Activates when analyzing Cortex memory files, detecting recurring work patterns, or determining if…
agent-skill-review
Review Codex, Claude, OpenAI, or other agent skill directories as reusable capability packages. Use when asked to audit, review, improve, score, rewrite,…
claude-context-improver
Audit and improve the Claude Code context layer — CLAUDE.md guidance files, .claude/rules/ path-scoped rules, and companion code_map.md navigation maps —…
gemini-companion
Coordinate Gemini CLI companion workflows for staged review, focused task execution, follow-up analysis, and clear continuation boundaries. Use this skill when…
goudi
Ground an ambitious proposal into the smallest verifiable first move with stop rules — pressure-test feasibility, avoid over-grand designs, make a bold…
skill-session-review
Analyze how an existing agent skill was used in past Claude Code, Grok, Codex, and Oh My Pi conversations. Use when the user asks to analyze a certain skill's usage, this skill…
trellis-plan-review
Independent review of Trellis task planning artifacts. Treats the selected task and its recursive current or archived children as one review scope, verifies…
zotero-synth
Search, browse, and analyze Zotero libraries via zotero-mcp to summarize papers, generate topic or collection literature reviews, synthesize evidence with…
famou-artifact-generator
Interactively guide the user through the complete process of a FaMou evolution task: first produce `problem.md`through a structured clarification loop, then implement and verify the three input materials for the FaMou experiment (`init.py`、`evaluator.py`、`prompt.md`). Trigger when the user mentions any of the following situations: define/clarify/create a FaMou task, help me write…
famou-experiment-manager
Workflow skill for managing famou evolution experiment tasks. When the user mentions "submit experiment", "check experiment status", "delete experiment", "get experiment results", "famou experiment", "upload experiment", "config.yaml experiment", or needs to use famou-ctl to manage experiment tasks, this skill must be used. Even if the user only says "submit" or "run experiment", as long as the context involves famou…
chop
Chop is volatility farming on Robinhood Chain (4663). Any token can be wrapped into a "log" (chTOKEN); every wrap, unwrap, buy and sell of a log pays a fee…
active-storage
This skill should be used when the user asks about "file uploads", "Active Storage", "attachments", "has_one_attached", "has_many_attached", "image variants",…
rails-caching
Rails caching strategies including fragment caching, low-level caching with Rails.cache, cache keys, and conditional GET. Use when the user asks about caching…
plan-with-baz
Plan a feature or change end-to-end using Baz indexed search across your org's repos. Explores the relevant repos with Baz's MCP tools and produces a…
speed-dating
Scaffold and maintain projects using the speed dating method, one self-contained kebab-case folder per project with a short CLAUDE.md, numbered source-of-truth…
goalify
Use when the user asks to set goal, run autonomously, autopilot, run to Ready, auto-run to completion, self-driven execution, goalify it, or explicitly wants to plan the current spec / work-in-progress into `/goal` tasks and dispatch them.
claude-remote
Manage **remote-control** Claude Code sessions (i.e. `claude --remote-control`, NOT regular local sessions) running in Terminal.app — start, stop, list, or…
gemini-agent
Delegate coding, review, diagnosis, planning, and structured output tasks to an independent Gemini session via Gemini CLI. Use cases include `gemini -p` non-interactive execution,`gemini -r latest` continuing the most recent session,`gemini -r "<session-id>"` resuming a specified session, and requiring `--output-format…
invariants
The ordering and evidence rules the whole bencium-loop loop rests on, stated once with their reasons and their real enforcement status. Referenced by every…