# agent-skills A collection of [Agent Skills]; structured markdown that extends LLM agent capabilities through a standardised format. [Agent Skills]: https://agentskills.io/ ## Available Skills Refer to [§ Token stats](#token-stats) for a detailed breakdown of each skill's token count, plus overall metadata usage. - [addressing-agent-comments](skills/addressing-agent-comments/SKILL.md): Finds `AGENT:` comments in code, gathers feedback, and carries out requested changes - [ast-grep](skills/ast-grep/SKILL.md): have the LLM write ast-grep rules to perform structural code search and analysis using the AST - [authoring-skills](skills/authoring-skills/SKILL.md): Creates well-structured Agent Skills following best practices. Use when writing new skills, reviewing existing skills, or when the user mentions skill authoring. - [creating-tasks-through-lunatask](skills/creating-tasks-through-lunatask/SKILL.md): Creates tasks in Lunatask for todos, reminders, deferred work, and handoffs. - [formatting-commits](skills/formatting-commits/SKILL.md): Creates commits strictly following Conventional Commits format via the `formatted-commit` CLI. - [frontend-accessibility](skills/frontend-accessibility/SKILL.md): Generates accessible HTML, React, and frontend code following WCAG 2.2 AA guidelines. Focuses on semantic HTML, keyboard accessibility, and screen reader compatibility. - [handling-customer-data](skills/handling-customer-data/SKILL.md): Handles customer data responsibly by answering questions about data without ever seeing the data directly. - [humanizer](skills/humanizer/SKILL.md): removes signs of AI-generated writing from text, making it sound more natural and human (initially copied from [blader/humanizer] then customised) - [invoking-subagents](skills/invoking-subagents/SKILL.md): Invokes ad-hoc subagents to read through lots of data and extract relevant information. Useful for exploring repositories, reading git logs, reviewing large diffs. - [managing-and-navigating-worktrees](skills/managing-and-navigating-worktrees/SKILL.md): Manages git worktrees and repos using the wt CLI. Use when cloning or creating new repos, adding worktrees, switching branches. - [querying-documentation](skills/querying-documentation/SKILL.md): Spawns focused agents to search specific language/framework documentation and answer moderately complex queries. - [resuming-work-through-lunatask](skills/resuming-work-through-lunatask/SKILL.md): Resumes previously deferred work from Lunatask. Use when user pastes a task note, shares a deep link, or references continuing earlier work. - [resolving-secrets](skills/resolving-secrets/SKILL.md): Wraps shell commands to resolve secret references in environment variables. - [reviewing-code](skills/reviewing-code/SKILL.md): Reviews code for correctness, security, reliability, performance, and quality. Use when asked to review code, a PR, a diff, or changes. - [scripting-with-go](skills/scripting-with-go/SKILL.md): Creates executable Go scripts with shebang-like behavior for long-lived automation. - [working-with-tmux](skills/working-with-tmux/SKILL.md): Lets the LLM create, manage, and capture output from tmux sessions/windows - [writing-roc-lang](skills/writing-roc-lang/SKILL.md): Writes Roc code with strong static types, helpful compiler errors, and functional programming. Covers both full applications and one-off scripts. [blader/humanizer]: https://github.com/blader/humanizer ## Installation If you're using [Amp], run `amp skill add https://git.secluded.site/agent-skills`. Otherwise, clone the repository, then install via `make` or manual symlinks. [Amp]: https://ampcode.com ```sh git clone https://git.secluded.site/agent-skills cd agent-skills ``` ### With Make Skills install to `~/.config/crush/skills/` by default. Override by setting `SKILL_DIR`. Tab completion works so you don't have to remember skill names or copy/paste. ```sh # List available skills make list # Install all skills to default dir make all # Install specific skills to Claude Code SKILL_DIR=$HOME/.claude/skills make authoring-skills formatting-commits # Remove a specific skill from Amp make uninstall-authoring-skills SKILL_DIR=$HOME/.config/agents/skills # Remove all skills from Codex make uninstall SKILL_DIR=$HOME/.codex/skills ``` ### With symlinks ```sh # Install all skills for s in skills/*/; do ln -s "$PWD/$s" ~/.config/crush/skills/; done # Install specific skills ln -s "$PWD/skills/authoring-skills" ~/.config/crush/skills/ # Remove a skill rm ~/.config/crush/skills/formatting-commits ``` ### Agent skill directories | Agent | Dir | | ----------------------- | -------------------------- | | Crush | `~/.config/crush/skills/` | | Amp | `~/.config/agents/skills/` | | Anthropic's Claude Code | `~/.claude/skills/` | | OpenAI's Codex | `~/.codex/skills/` | ## Updating ```sh cd ~/path/to/agent-skills git pull ``` Symlinked skills update automatically. ## Contributions Patch requests are in [amolith/llm-projects] on [pr.pico.sh]. You don't need a new account to contribute, you don't need to fork this repo, you don't need to fiddle with `git send-email`, you don't need to faff with your email client to get `git request-pull` working... You just need: - Git - SSH - An SSH key ```sh # Clone this repo, make your changes, and commit them # Create a new patch request with git format-patch origin/main --stdout | ssh pr.pico.sh pr create amolith/llm-projects # After potential feedback, submit a revision to an existing patch request with git format-patch origin/main --stdout | ssh pr.pico.sh pr add {prID} # List patch requests ssh pr.pico.sh pr ls amolith/llm-projects ``` See "How do Patch Requests work?" on [pr.pico.sh]'s home page for a more complete example workflow. [amolith/llm-projects]: https://pr.pico.sh/r/amolith/llm-projects [pr.pico.sh]: https://pr.pico.sh ## Token stats Real token stats as reported by [Synthetic.new]'s [/messages/count_tokens] endpoint with [./skill-stats.go](./skill-stats.go). [Synthetic.new]: https://synthetic.new [/messages/count_tokens]: https://dev.synthetic.new/docs/anthropic/messages/count-tokens ``` === addressing-agent-comments === Token breakdown: Name: 22 tokens Description: 96 tokens Body: 706 tokens (40 lines) ─────────────────────────────────────────────── Total: 824 tokens === ast-grep === Token breakdown: Name: 18 tokens Description: 198 tokens Body: 7503 tokens (469 lines) References: rule_reference.md 6814 tokens ─────────────────────────────────────────────── Total: 14533 tokens ⚠️ Body exceeds recommended 5000 token budget! === authoring-skills === Token breakdown: Name: 20 tokens Description: 86 tokens Body: 2000 tokens (102 lines) References: checklist.md 806 tokens patterns.md 2415 tokens process.md 833 tokens specification.md 3890 tokens ─────────────────────────────────────────────── Total: 10050 tokens === creating-tasks-through-lunatask === Token breakdown: Name: 30 tokens Description: 108 tokens Body: 1927 tokens (88 lines) References: cli.md 589 tokens handoff.md 2769 tokens installing-lune.md 176 tokens ─────────────────────────────────────────────── Total: 5599 tokens === formatting-commits === Token breakdown: Name: 22 tokens Description: 98 tokens Body: 965 tokens (43 lines) References: installing-formatted-commit.md 296 tokens ─────────────────────────────────────────────── Total: 1381 tokens === frontend-accessibility === Token breakdown: Name: 20 tokens Description: 140 tokens Body: 2891 tokens (148 lines) References: antipatterns.md 3638 tokens patterns.md 6233 tokens ─────────────────────────────────────────────── Total: 12922 tokens === handling-customer-data === Token breakdown: Name: 22 tokens Description: 123 tokens Body: 1983 tokens (107 lines) ─────────────────────────────────────────────── Total: 2128 tokens === humanizer === Token breakdown: Name: 15 tokens Description: 84 tokens Body: 8536 tokens (462 lines) ─────────────────────────────────────────────── Total: 8635 tokens ⚠️ Body exceeds recommended 5000 token budget! === invoking-subagents === Token breakdown: Name: 20 tokens Description: 113 tokens Body: 796 tokens (13 lines) References: installing-synu.md 140 tokens ─────────────────────────────────────────────── Total: 1069 tokens === managing-and-navigating-worktrees === Token breakdown: Name: 32 tokens Description: 110 tokens Body: 1912 tokens (96 lines) ─────────────────────────────────────────────── Total: 2054 tokens === querying-documentation === Token breakdown: Name: 22 tokens Description: 132 tokens Body: 796 tokens (22 lines) References: dependencies.md 108 tokens ─────────────────────────────────────────────── Total: 1058 tokens === resolving-secrets === Token breakdown: Name: 20 tokens Description: 120 tokens Body: 259 tokens (10 lines) References: installing-opx.md 125 tokens ─────────────────────────────────────────────── Total: 524 tokens === resuming-work-through-lunatask === Token breakdown: Name: 30 tokens Description: 113 tokens Body: 1241 tokens (42 lines) References: cli.md 528 tokens installing-lune.md 176 tokens ─────────────────────────────────────────────── Total: 2088 tokens === reviewing-code === Token breakdown: Name: 18 tokens Description: 125 tokens Body: 1880 tokens (121 lines) ─────────────────────────────────────────────── Total: 2023 tokens === scripting-with-go === Token breakdown: Name: 20 tokens Description: 120 tokens Body: 1968 tokens (138 lines) ─────────────────────────────────────────────── Total: 2108 tokens === working-with-tmux === Token breakdown: Name: 22 tokens Description: 84 tokens Body: 1465 tokens (87 lines) ─────────────────────────────────────────────── Total: 1571 tokens === writing-roc-lang === Token breakdown: Name: 22 tokens Description: 142 tokens Body: 1846 tokens (117 lines) References: builtins-llms.md 67881 tokens llms.md 11324 tokens scripting.md 1722 tokens ─────────────────────────────────────────────── Total: 82937 tokens ============================================================ SUMMARY ============================================================ Skills: 17 Metadata: 2367 tokens Combined bodies: 38674 tokens Overall: 151504 tokens Validation errors: 0 Largest skills (by total tokens): 1. writing-roc-lang 82937 tokens 2. ast-grep 14533 tokens 3. frontend-accessibility 12922 tokens 4. authoring-skills 10050 tokens 5. humanizer 8635 tokens ``` --- Some other tools if these interested you - [wt](https://git.secluded.site/wt) - CLI for managing git worktrees - [formatted-commit](https://git.secluded.site/formatted-commit) - CLI that turns LLM input into well-formatted Conventional Commits - [garble](https://git.secluded.site/garble) - transform stdin with an LLM (fix typos, translate, reformat) - [lune](https://git.secluded.site/lune) - CLI and MCP server for [Lunatask.app](https://lunatask.app)