skills

In the author's own words, from each skill's SKILL.md.

• cli-devex

  Design, implement, and review command-line interfaces used by humans, scripts, CI, and AI agents: minimal surface and defaults, layered tuning, command grammar, configuration precedence and trust, help, streams and machine output, terminal progress, non-interactive execution, exit codes, crash-safe mutations, and CLI contract tests. Use when creating a CLI or changing its arguments, help, output,…

  skills/cli-devex/SKILL.md on GitHub (opens in a new tab)

• dialectic

  Prove and counter-prove a claim with parallel agents before concluding. Use for architecture claims, bug hypotheses, performance claims, refactor safety, review judgments, and "is this actually true?" questions.

  skills/dialectic/SKILL.md on GitHub (opens in a new tab)

• gdoc

  Use the local gdoc CLI to find, read, create, edit, review, comment on, share, export, or synchronize Google Docs and Drive files. Trigger for Google Docs or Drive work when gdoc is available; do not use for unrelated local document files or browser-only editing.

  skills/gdoc/SKILL.md on GitHub (opens in a new tab)

• interactive

  Session mode for working side by side - shape output to be scannable and actionable, surface decisions instead of inferring them, and write in plain technical English. The required argument is the first task to work on under the mode. Manual trigger only; stays on until the user says the open decisions are settled.

  skills/interactive/SKILL.md on GitHub (opens in a new tab)

• investigate

  Evidence-first debugging and root cause investigation. Use for triaging bugs, test failures, incidents, performance regressions, flaky behavior, integration failures, or unexplained behavior before proposing fixes.

  skills/investigate/SKILL.md on GitHub (opens in a new tab)

• ml-project

  Guidelines for ML projects. Use when training or evaluating models, building ML pipelines, running experiments, or working with datasets/parquet files and CatBoost/PyTorch/Polars code.

  skills/ml-project/SKILL.md on GitHub (opens in a new tab)

• rust-webapp

  Build full-stack web applications using Rust (Axum + SQLx) with server-rendered frontend patterns using HTMX + Alpine.js or DataStar, plus Neon (serverless PostgreSQL). Use when asked to create web apps, CRUD apps, dashboards, forms, or any stateful web application. Triggers on requests like "build a todo app", "create a voting app", "make a dashboard", "build a blog", etc.

  skills/rust-webapp/SKILL.md on GitHub (opens in a new tab)

• second-opinion

  Get an independent review from another model through nitpicker (falling back to codex or opencode) — of a diff, a GitHub PR, existing code, a plan, or a contested claim. Use when asked to run nitpicker, get a second opinion, or have another model review something, and whenever another skill needs an external reviewer.

  skills/second-opinion/SKILL.md on GitHub (opens in a new tab)

• spymaster

  Design, build, audit, and improve the harness around an LLM agent — its tools, loop, permissions, context, skills, and evals. Use when building, reviewing, or debugging any agentic system: an agent runtime or loop, agent-facing tools, an MCP server, an approval/permission flow, a context or memory strategy, an eval suite, or an existing agent that underperforms (flaky, wrong tool calls, retry loo…

  skills/spymaster/SKILL.md on GitHub (opens in a new tab)

• tokenmaxxer

  Serious engineering work behind a reviewed plan and adversarial review gates. The required first argument word picks the mode - `build`, `refactor`, `sweep`, or `experiment`. Invoke explicitly, e.g. `/tokenmaxxer refactor <component>`.

  skills/tokenmaxxer/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• superpowersby obra An agentic skills framework & software development methodology that works. 300k stars · 15 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 293k stars · 30 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 181k stars · 19 skills