my-history-insight
A skill that analyzes past Claude Code session records to extract insights. Used for requests like "history analysis", "session analysis", "analyze my work patterns", "history insight", "/history-insight".
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Agents & models
25,496 results
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
harness-ceo
Coordinate Harness Anything work as the controller, commander, or executor through explicit delegation contracts, model-agnostic role selection, dispatch oversight, evidence acceptance, and continuous improvement. Use for Harness multi-agent collaboration, maintaining your own model matrix, or connecting a new model to an existing dispatch runtime.
to-spec
Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
openai-agents
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11…
creator-intelligence
Transform Claude Code into your personal Jarvis - an AI operating system that knows your projects, preferences, and workflows across sessions. Use this skill…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
context-budget-discipline
Hard context-budget discipline for long-running workflow hosts: evaluate a session reset at every lifecycle phase boundary, compact proactively at ~60-70% of…
laravel-ai-sdk
Use when integrating AI agents, tool calling, embeddings, structured output, or streaming in Laravel 13 via the `laravel/ai` package.
skill-creator
Alias for sentry-skills:skill-writer. Use when users explicitly ask for "skill-creator" or reference the legacy skill name. Redirects to the canonical skill…
create-canvas
Author, validate, and debug canvas extensions that the agent can open in the GitHub Copilot app's side panel. Use when creating, reviewing, or troubleshooting…
skill-creation-guide
Guide the user through authoring a new agent skill — when a skill is worth creating, the SKILL.md format, progressive disclosure, and common pitfalls. Also…
sketch
Open a Fabric.js-based SVG editor in the browser for collaborative visual prototyping. Codex writes and reads SVG through MCP tools while the user edits…
agentic-ecology-bioacoustics
Provides bioacoustic analysis capabilities for ecologists and researchers using the perch-hoplite Python package. A typical use case is to use agile modeling…
agentic-ecology-ui
Guidelines and templates for creating a generic web UI to visualize, rank, filter, and annotate vector databases. The UI has a hierarchical structure covering…
mujoco-python
Python simulation lifecycle (MjSpec, MjModel, MjData), simulation stepping (mj_step, mj_step1, mj_step2, mj_forward), named access (data.body, model.geom),…
issue-management
GitHub issue creation, labeling, milestones, agent assignment, and backlog prioritization for product management
self-improve
End-of-session retrospective that identifies improvements to agent config, tests, docs, and code. Use when asked to "self-improve", "reflect on session", "what…
fortify
Fortify existing code by splitting large functions, adding edge-case coverage, and backfilling unit tests. Use when user asks to "fortify", "harden",…
knowledge-gap
Post-task knowledge gap review and proposals for improving skills/rules
my
Inspect and optionally adjust the agent's runtime state. Use to check the current model or preset, context window and runtime limits, workspace and tool…
agentinbox
Use the local AgentInbox service to onboard the current runtime/session, manage shared sources and subscriptions, connect external providers such as GitHub…
install-bensz-skills
Use when you need to install all skills under pipelines/skills in this repository to the system level (by default installing to both Codex: ~/.codex/skills and Claude Code: ~/.claude/skills), so they can be discovered and invoked in any project/conversation. Use MD5 hashes for version control, installing only those with updates…
github
Interact with GitHub repositories, issues, pull requests, and code via the GitHub MCP server. This skill should be used when managing repositories,…