Recently added

Detect dangling DNS records and subdomain-takeover risks across AWS, GCP, and Azure by driving the findmytakeover tool.

Agent skill for long-context work: decompose tasks that exceed the context window with filtering, chunking, recursive sub-agents and verification, based on the Recursive Language Models research.

Zero-dependency, spec-driven agentic SDLC: durable specs, context-fit plans, re-anchored workers, adversarial cross-model review, and receipts. Compatible with Codex, Claude Code, and Factory Droid.

masterplan orchestrator

masterplan orchestrator

Brainstorm, plan, execute, resume, import, lint, and retrospect long-running coding-agent work with durable run bundles and strict context control.

Synthetic single-plugin fixture proving the packaging pipeline makes no assumption about Catalyst's specific inventory (CTL-1461 Phase 7).

Linear backlog grooming — orphan, stale, and duplicate ticket detection

Frontmatter validation, reference auditing, and directory reorganization tools for Catalyst plugin developers: keep skill and agent frontmatter consistent, find broken references, and safely reorganize directory structures.

Pre-phase-agent (wave-based) orchestration workflow preserved as a documented fallback: oneshot, orchestrate, god, setup-orchestrate. Superseded by catalyst-dev's execution-core/phase-agent pipeline. Requires catalyst-dev (shared backing scripts).

Setup, maintenance, and compounding upkeep of the Catalyst framework and the thoughts/ knowledge base: framework diagnostics/repair (setup-catalyst), terminal launcher config (setup-warp), and research-doc curation (research-curate). Future home for the compound-engineering retro/learning loop.

Complete development workflow: research → plan → implement → validate → ship. Includes research agents, planning tools, handoff system, Linear integration, and PM commands.

Reusable AI agent skills for Claude Code, Gemini CLI, and other AI coding tools

Persistent context network for coding projects. Tracks tasks, dependencies, and decisions across sessions.

Persistent context network for coding projects. Tracks tasks, dependencies, and decisions across sessions.

Build and run web apps, websites, agents, databases and background workers on Uniac, the cloud platform for AI agents.

Convert PDF, Word, PowerPoint, Excel and office docs to Markdown locally. No API key. Files never leave your machine.

Example Agent Plugin demonstrating the Agent Plugins v1.0.0 package format: Python skills plus a containerized FastMCP server exposed over Streamable HTTP.

Deploy websites, APIs, and services to xhostd from your coding agent. Create apps, push code, deploy previews or production, inspect status, and manage channels, environment, storage, and domains.

Design and create apps with Autograph App Builder.

Agent skills I use day-to-day with GitHub Copilot CLI and other coding agents.

BuzzAssist canvas and media plugin for Codex.

Continuous memory for agent CLIs. Extracts, summarizes, and compresses conversations into tiered daily logs. Codex layer observed against a real codex-cli 0.150.1 install (#443, #444, #460, #463, #465): marketplace discovery, install, hook firing, per-turn capture, and session extraction all hold up against a real Codex transcript.

Terminal workspace and multiplexer for interactive CLI sessions. Use when managing terminal sessions, running interactive REPLs, debugging, automating terminal workflows, or when user mentions zellij, floating panes, or session layouts. Simpler alternative to tmux.

Convert game walkthroughs and guides from plain text into structured, interlinked Obsidian markdown pages. Use when the user wants to convert a walkthrough, FAQ, guide, or reference document into Obsidian vault pages. Triggers on mentions of converting walkthroughs, guides, or FAQs to Obsidian, or splitting a large text file into Obsidian pages.

uv — Astral's fast Python package & project manager, one binary replacing pip/pipx/pyenv/poetry/virtualenv. Use when managing Python projects with pyproject.toml + uv.lock (uv init/add/sync/lock/run), running PEP 723 inline-dependency scripts, running one-off tools with uvx, installing/pinning Python versions (uv python), migrating from pip (uv pip), building/publishing packages, or configuring indexes/resolution/cache. Includes `(uv 0.X+)` version annotations. The uv CLI, not ruff/ty.

Invoke deep sequential thinking for complex problem-solving. Use when the user says 'use ultrathink', 'ultrathink', or when tackling problems that require careful step-by-step reasoning, planning, hypothesis generation, or multi-step analysis.

ty — Astral's extremely fast (Rust) Python type checker and language server, in 0.0.x beta. Use when running or configuring `ty check`, reading ty diagnostics, setting rule levels in `[tool.ty]`/`ty.toml`, writing `# ty: ignore[rule]` suppressions, debugging environment or module-resolution failures, wiring ty into CI (exit codes, `--output-format github`), or migrating from mypy/pyright. Pinned to ty 0.0.72. The type checker — NOT ruff (lint/format) or uv (packaging).

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output. Use when debugging applications, running interactive REPLs (Python, gdb, ipdb, psql, mysql, node), automating terminal workflows, or when user mentions tmux, debugging, or interactive shells.

Run a Socratic teaching loop that quizzes you on a coding session until you've confirmed mastery of every concept. Use when you want to learn or lock in a Claude Code session, understand a transcript/PR/design decision, be quizzed on recent work, or prepare to teach someone else — or when the user runs `/teach` or asks to be taught or quizzed on a topic. Sources sessions from ~/.claude/projects/ and tracks a per-concept checklist until every item is confirmed.

Write content using stored writing styles from the writing-styles/ collection. Use when the user wants to write in a specific voice, apply a stored style, list available writing styles, or evaluate text against a style rubric.

Extract and document writing styles from source texts into reusable style guides. Use when analyzing an author's voice, creating a style guide from a book or document, capturing writing patterns for replication, or building a writing style rubric.

Configure the Claude Code status line with VCS-aware scripts showing git branch, jj change ID, bookmarks, context usage, and costs. Use when setting up a statusline, customizing the status bar, or adding VCS info to the status line.

MCP server exposing SQLite database tools (query, execute, list_tables, describe_table, create_table). Read-only by default; writes are opt-in via --allow-writes or MCP_SQLITE_ALLOW_WRITES=true. Use when inspecting, querying, or (when enabled) modifying SQLite databases.

Review and ensure skills maintain high quality standards. Use when creating new skills, updating existing skills, or auditing skill quality. Checks for progressive disclosure, mental model shift, appropriate scope, and documentation clarity.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

MCP server exposing a single sequentialthinking tool for dynamic, reflective, step-by-step problem-solving. Use when a task needs structured reasoning, planning, hypothesis generation, branching to explore alternatives, or revising earlier steps while keeping a running chain of thoughts.

ruff — Astral's one fast (Rust) binary that is both a Python linter (`ruff check`) and a Black-compatible formatter (`ruff format`). Use when linting or formatting Python, configuring `[tool.ruff]`/`ruff.toml`, choosing rules with `select`/`extend-select`/`ignore`, looking up codes like F401/E501/B008, applying fixes (`--fix`, `--unsafe-fixes`), suppressing (`# noqa`, `# ruff: ignore[...]`), or enabling preview rules. Includes `(ruff 0.X+)` + preview annotations. Not uv or ty.

Fast, gitignore-aware recursive content search with the `ripgrep` (`rg`) command-line tool — a smarter, faster `grep`. Use when searching code or text for a regex across a directory tree, filtering by file type or glob, listing/counting matches, doing search-and-replace previews, or gitignore-aware code search. Triggers on mentions of ripgrep or rg. The rg CLI tool, distinct from the file-search/fuzzy-search MCP servers.

React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code for optimal performance. 62 rules across 8 categories covering waterfalls, bundle size, server-side, re-renders, and rendering.

pytest — Python testing framework and idioms beyond unittest. Use when writing, running, or configuring pytest tests — plain `assert` (rewritten), DI `@pytest.fixture` (scopes/autouse/yield/conftest), `@pytest.mark.parametrize`, `skip`/`skipif`/`xfail` + markers, `raises`/`warns`/`approx`, fixtures (`tmp_path`/`monkeypatch`/`capsys`/`caplog`), the CLI (`-k`/`-m`/`-x`/`--lf`/`--pdb`), config (`pyproject.toml`/`pytest.ini`). Includes `(pytest N.M+)` annotations. Not unittest, tox, or coverage.

Datadog CLI (pup) for observability, monitoring, logs, APM, security, and infrastructure. Use when querying Datadog metrics, searching logs, managing monitors, investigating incidents, or performing Datadog API operations.

psql — PostgreSQL's interactive terminal client and SQL script runner. Use when connecting to or inspecting a Postgres DB from a terminal, running SQL scripts or one-off queries in shells/CI/agents (`-c`/`-f`/`-qAtX`/`--csv`), using meta-commands (the `\d` family, `\copy`, `\watch`, `\gexec`, `\if` scripting, `\pset`/`\x`, variables), `.psqlrc`, or fixing connection/auth issues. Includes `(pgNN+)` annotations. The psql client only — SQL syntax -> postgres-sql, server admin -> postgres-admin.

The PostgreSQL SQL dialect & data types that set Postgres apart from generic SQL. Use when writing or debugging Postgres-specific SQL — upsert (`ON CONFLICT`), `RETURNING`, `MERGE`, CTEs, window frames, `GROUPING SETS`, `LATERAL`, generated/identity columns, partitioning, `jsonb`/jsonpath/SQL-JSON (`JSON_TABLE`), arrays, ranges, composite/enum/domain types, `uuidv7()`. Includes `(pgNN+)` annotations. Dialect & types — client -> psql, tuning -> postgres-performance, config -> postgres-admin.

PostgreSQL query & performance tuning. Use when a query is slow, reading an `EXPLAIN [ANALYZE]` plan (scan/join nodes, estimate skew), choosing an index type/columns (btree/GIN/GiST/SP-GiST/BRIN/hash; partial/expression/covering), fixing planner estimates with statistics, diagnosing MVCC bloat/VACUUM/autovacuum lag, or tuning planner GUCs (`random_page_cost`, `work_mem`). Includes `(pgNN+)` annotations. Tuning only — client -> psql, SQL -> postgres-sql, config -> postgres-admin.

PostgreSQL extension management and the bundled `contrib` catalog. Use when running `CREATE/ALTER/DROP EXTENSION`, listing extensions (`\dx`), or choosing which contrib module enables a feature — FDWs (`postgres_fdw`, `dblink`), trigram search (`pg_trgm`), crypto/UUIDs (`pgcrypto`), types (`hstore`/`ltree`/`citext`), query stats (`pg_stat_statements`, `auto_explain`), forensics (`pageinspect`, `amcheck`). Covers trusted extensions & `shared_preload_libraries`. Includes `(pgNN+)` annotations.

PostgreSQL server administration & operations. Use when configuring a server (`postgresql.conf`, `ALTER SYSTEM`, GUCs), managing roles/privileges (`GRANT`/`REVOKE`), authentication (`pg_hba.conf`, scram-sha-256), backup/restore (`pg_dump`, `pg_basebackup`, incremental, PITR), replication (streaming, logical, slots, failover), `pg_upgrade`, or monitoring (`pg_stat_activity`/`pg_stat_io`). Includes `(pgNN+)` annotations. Server ops — client psql, SQL postgres-sql, tuning postgres-performance.

Browser automation with Playwright for Python. Use when testing websites, taking screenshots, filling forms, scraping web content, or automating browser interactions. Triggers on browser, web testing, screenshots, selenium, puppeteer, or playwright.

oxlint — the extremely fast (Rust) JavaScript/TypeScript linter from the oxc project, an ESLint alternative that needs no config to start. Use when linting JS/TS/JSX/Vue, writing `.oxlintrc.json`, selecting rules via `plugins` + `categories` (correctness, suspicious, pedantic, perf, style, restriction, nursery), running `--fix`/`--fix-suggestions`/`--fix-dangerously`, suppressing with `// oxlint-disable`, or migrating from ESLint. The linter — not oxfmt, ESLint/Biome, or ruff.

oxfmt — the fast Rust formatter from the oxc project, a Prettier-compatible alternative formatting JS/TS/JSX plus JSON, CSS, YAML, TOML, GraphQL, Markdown and Vue. Use when formatting or checking with oxfmt, configuring `.oxfmtrc.json`, migrating off Prettier/Biome (`--migrate`), or enabling built-in `sortImports`/`sortPackageJson`/`sortTailwindcss`. Note: bare `oxfmt` REWRITES FILES IN PLACE. The formatter — not oxlint, Prettier/Biome, or ruff format.