1.3K skills · sorted by relevance
Design infrastructure for agents that run in isolated remote environments. Plan faster session startup, saved work states, shared sessions, authentication, and delivery of code changes and other results back to users.
Design structured summaries for long agent sessions that preserve goals, file changes, decisions, and next actions. Choose compression methods and timing, then test whether the agent can continue accurately without repeatedly retrieving information it already processed.
Use persistent virtual terminal sessions to keep directories and environment variables across commands, interact with Python or database consoles, and answer prompts. The skill explains sending input, reading responses, detecting prompts, and closing sessions when finished.
Review legal essays using IRAC: issue, rule, application, and conclusion. Get feedback on missed issues, rule accuracy, reasoning, and organization, plus recurring patterns across practice sessions, without rewritten essays or model answers.
Save established decisions, project facts, failed approaches, and system architecture to Atlas shared memory. The skill checks existing entries to avoid duplicates and creates self-contained records that other agents and future sessions can use.
Investigate unfamiliar codebases before fixing bugs, adding features, or refactoring. Follow relevant code paths, plan focused changes, and verify results, while recording useful discoveries in .notebook/ so later sessions can build on earlier investigation.
Automate browser work with a command-line tool for AI agents. Extract JavaScript-rendered content, fill forms, upload files, capture screenshots and network responses, and manage separate browser sessions for tasks involving multiple accounts or manual assistance.
Set up one mirrord-up.yaml file to debug several related services locally at the same time. Define each application’s command, Kubernetes target, environment settings, and traffic mode, then manage the sessions together with mirrord up.
Evaluates Claude Code conversations at session end and extracts reusable solutions, user corrections, and project conventions. It saves useful patterns as learned skills for future sessions, with configurable detection rules and a minimum conversation length.
Automate browser tasks with playwright-cli, including navigation, form filling, and data extraction. Test web applications, capture screenshots, reuse login sessions, and generate test code through command-line browser controls.
Keep a persistent record of project bugs and blockers in a local Markdown file. List issues by severity and category, inspect individual records, and save resolution notes so problems and their fixes remain available across sessions.
Create a handoff document that captures progress, decisions, failed approaches, and relevant files. Give a fresh agent the context needed to verify the current state and continue work across sessions.
Review Claude Code sessions using Braintrust traces, records of agent activity. Summarize tool, agent, and skill usage, inspect repeated actions, replay sessions, and track token consumption to understand failures and recurring work patterns.
Structure complex work that spans many sessions or iterations. Assess resources and obstacles, identify the current stage, choose one immediate achievable target, and set milestones for moving from preparation toward broader execution.
Diagnose and fix Claude Code plugin hook failures on Windows. Covers conflicts between WSL and Git Bash, path handling problems, and errors involving .sh arguments, using error messages and configuration files.
Find Claude Code sessions tracked by the Agent Monitor by project (cwd), model, status, or date, then rank the matches by cost or recency. Pulls the session list and the distinct cwd / facet values so filters use real values rather than guesses. Use when locating a session — "find my EstateWise sessions", "which Opus runs errored this week", "most expensive sessions in /repo".
The English summary is being prepared. Showing the original description.
Search a Claude Code session transcript for a string or regex pattern and show every matching message with surrounding context. Reads /api/sessions/:id/transcript and resolves sessions via /api/sessions?limit= from the Agent Monitor dashboard. Use when hunting for a specific message, prompt, tool call, or error inside a session's conversation.
The English summary is being prepared. Showing the original description.
Drive Codeman, the session manager this agent is running inside, over its HTTP API, from any agent CLI (Claude Code, Codex, Gemini CLI, OpenCode, Antigravity, Grok Build, DeepSeek Harness, OMP): list sessions, start worker sessions in any installed CLI, send them prompts, block until they finish (wait / wait-output / send-and-wait), read their output, and clean up; where available, message claude workers directly (Claude Code cross-session messaging). Use when asked to orchestrate or parallelize work across Codeman sessions, get a second opinion from another CLI or model, watch another session, or start and manage workers. Only usable inside a Codeman-managed session (CODEMAN_MUX=1); refuse to act otherwise.
The English summary is being prepared. Showing the original description.
Use claudraband CLI to control Claude Code sessions programmatically. Use when running, scripting, or automating Claude Code via the claudraband CLI — sending prompts, listing/resuming sessions, or working in interactive REPL mode. Triggers on any mention of claudraband, claudraband-cli, npx claudraband, bunx claudraband, or automating Claude Code sessions. Used when you need to ask yourself (Claude) a question
The English summary is being prepared. Showing the original description.
Fix OAuth PKCE "Session not found" or "No code verifier" errors in SPAs after redirect from external auth server. Use when: (1) OAuth callback fails with session/verifier not found despite flow starting correctly, (2) PKCE code_verifier stored in sessionStorage is missing after redirect back from auth server, (3) Error only happens in production or cross-origin redirects, not in local dev. Root cause: sessionStorage is lost when the browser opens a new tab, changes browsing context, or certain browsers clear it during cross-origin navigation. Fix: use localStorage instead (clean up after exchange).
The English summary is being prepared. Showing the original description.
Browserbase runs managed headless Chromium sessions in the cloud, so browser automation, AI agents and scraping jobs need no browser infrastructure of their own. Use when someone asks to "run Playwright in the cloud", "Browserbase session", "headless browsers at scale", "scrape with proxies and CAPTCHA solving", "persist a login across browser sessions", or "use Stagehand with Browserbase". Covers sessions, proxies, contexts, parallel runs and replays.
The English summary is being prepared. Showing the original description.
Reconstructs the workflow behind a past artifact by querying local ax session, recall, and commit history data. Use when a user asks "what made X work", "how was Y shipped/built", "extract workflow from <date|sha>", "workflow around <topic>", "recipe for this feature", or similar. It finds the anchor session or commit, inspects ax sessions, ax recall, and ax sessions show, and returns an ordered read-only narrative with decisions and evidence.
The English summary is being prepared. Showing the original description.
A multi-day digest of the user's own coding-agent sessions — sessions per day and project, most-edited files, and every lesson Cognee distilled into the knowledge graph in that window. Use only when the user explicitly asks for a weekly digest, a retro, a recap or report of their recent sessions, or asks for the `cognee-digest` skill by name. Not for questions about code or the current task.
The English summary is being prepared. Showing the original description.
Spawns full Claude Code peer sessions in separate terminal panes and git worktrees, real sessions rather than subagents, each with a directed task and contract brief, monitored and merged by the spawning lead. Detects the environment and uses herdr first, then tmux, then a native claude background agent. Use when work must persist or run beside the current session, needs a separate worktree or permission settings, should remain user-steerable in a visible pane, or when the user asks to spawn, hand off, or parallelize full sessions. Also spawns Codex peers into those panes. Excludes bounded consults and subagent-scale work.
The English summary is being prepared. Showing the original description.