agent-skills
A collection of Agent Skills; structured markdown that extends LLM agent capabilities through a standardised format.
Available Skills
Refer to § Token stats for a detailed breakdown of each skill's token count, plus overall metadata usage. I've used and tested them most with Crush, Amp, and Shelley, and to a lesser degree, Octofriend and Pi.
- addressing-agent-comments: Finds
CR:comments in code, gathers feedback, and carries out requested changes. - ast-grep: Writes ast-grep rules for structural code search and modification.
- auditing-repositories: Audits open source repositories for security, privacy, and unexpected behavior.
- authoring-skills: Creates and reviews Agent Skills following best practices. Covers skill structure, frontmatter, and progressive disclosure patterns.
- backing-up-with-keld: Writes and
manages keld configuration for restic backups. Covers TOML preset structure,
split preset composition (
home@cloud), config file discovery, environment variables, and systemd timer setup. - collaborating-through-pr-pico-sh:
Collaborates on git patches via pr.pico.sh, a minimal patchbin service.
Covers both contributing and reviewing patch requests using
git format-patchandgit am. - creating-tasks-through-lunatask: Creates tasks and handoffs in Lunatask via lune. Tasks are just tasks. Handoffs capture work to resume later across sessions without filling context windows.
- formatting-commits: Detects a project's commit style from recent history and formats messages accordingly. Supports Conventional Commits and kernel-style imperative commits.
- getting-a-code-review: Gets an external code review of changes, commits, PRs, or patches via CLI tools like Amp, CodeRabbit, or Kodus.
- frontend-accessibility: Strives to generate accessible HTML, React, and frontend code following WCAG 2.2 AA. Prioritizes semantic HTML over ARIA, keyboard navigation, and screen reader compatibility.
- handling-customer-data: Queries customer data responsibly—the agent answers questions about the data without ever seeing it directly.
- humanizer: Removes AI-generated patterns from text like promotional fluff, weasel words, and mechanical sentence structures. Based on Wikipedia's AI Cleanup research. Originally from blader/humanizer.
- ideating-with-bdd: Guides collaborative discovery of behaviour through structured conversation, iterating with the user to refine ideas into user stories and Gherkin scenarios. Works for any language or framework.
- initialising-and-updating-agents-md:
Analyses a codebase and creates or updates
AGENTS.mdto help future agents work effectively. Discovers commands, conventions, patterns, and gotchas from the project's source and config files. - invoking-subagents: Spawns subagents with restricted tool access for parallel tasks across repositories. Requires the Pi coding agent. Useful for summarizing git history or processing large diffs without filling the main context window.
- maintaining-aur-packages: Creates
and updates AUR packages following Arch packaging standards. Covers PKGBUILDs
for source,
-bin, and-gitpackage types, checksums withupdpkgsums, linting withnamcap, and.SRCINFOgeneration. - managing-and-navigating-worktrees: Manages git worktrees using wt with a bare repository structure. Each branch lives in its own sibling directory. Requires wt, git, and gum.
- monitoring-with-munin: Deploys and manages Munin monitoring across servers. Sets up munin-node on hosts, writes plugins, configures masters, and handles alerts.
- notifying-through-ntfy: Sends push notifications via ntfy.sh when requested, such as at the end of its turn.
- rebasing-with-git: Manages git rebase
workflows from simple rebases to the drop-and-repick integration branch
pattern. Assumes
upstreamremote for forks andrerereenabled. Supports worktrees includingwt-managed repos. - researching-with-rumilo: Dispatches AI research subagents via rumilo for web search and repository exploration. Research topics, look up library usage, or explore external codebases without filling the main context window.
- resuming-work-through-lunatask: Resumes deferred work from Lunatask handoff notes via lune.
- scripting-with-go: Creates executable Go scripts using a shell trick (not a true shebang). For automation and tooling outside of Go projects.
- testing-with-gocuke-and-gherkin: Drives BDD, red/green TDD, and property-based testing in Go projects using gocuke and Gherkin feature files.
- updating-llm-client-model-lists: Synchronizes model configurations across Zed, Crush, Octofriend, and Pi from Plexus' /v1/models endpoint.
- using-exe-dev: Guides working with exe.dev VMs, which provide Linux VMs with persistent disks, instant HTTPS, and built-in auth via SSH.
- using-jujutsu: Guides jujutsu (jj) workflows, covering commit selection, change creation, diff reading, and common pitfalls that trip up agents.
- working-with-tmux: Spawns and manages background processes via tmux. Creates windows, sends commands, and captures output without blocking the main session. Useful for servers and long tasks.
- writing-git-tags: Generates git tag annotations from commit history following Semantic Versioning and Conventional Commits via git-format.
- writing-roc-lang: Writes Roc code with strong static types, helpful compiler errors, and functional programming. Covers both full applications and one-off scripts.
- writing-rust: Writes idiomatic Rust with
strict quality gates:
cargo fmt,clippy -- -D warnings, and required tests. Enforcesthiserrorfor libs,anyhowfor apps, warns against common anti-patterns.
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.
git clone https://git.secluded.site/agent-skills
cd agent-skills
With Make
Skills install to ~/.config/agents/skills/ by default. Override by
setting SKILL_DIR. Tab completion works so you don't have to remember
skill names or copy/paste.
# 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=$HOME/.codex/skills
With symlinks
# Install all skills
for s in skills/*/; do ln -s "$PWD/$s" ~/.config/agents/skills/; done
# Install specific skills
ln -s "$PWD/skills/authoring-skills" ~/.config/agents/skills/
# Remove a skill
rm ~/.config/agents/skills/formatting-commits
Agent skill directories
| Agent | Dir |
|---|---|
| Crush, Octofriend, Shelley, Amp | ~/.config/agents/skills/ |
| Pi | ~/.pi/agent/skills/ |
| Anthropic's Claude Code | ~/.claude/skills/ |
| OpenAI's Codex | ~/.codex/skills/ |
Updating
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
# 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.
Token stats
Real token stats as reported by Synthetic.new's /messages/count_tokens endpoint with ./skill-stats.go.
=== addressing-code-review-comments ===
Token breakdown:
Name: 9 tokens
Description: 40 tokens
Body: 290 tokens (38 lines)
───────────────────────────────────────────────
Total: 339 tokens
=== ast-grep ===
Token breakdown:
Name: 7 tokens
Description: 76 tokens
Body: 2765 tokens (469 lines)
References:
rule_reference.md 2515 tokens
───────────────────────────────────────────────
Total: 5363 tokens
=== auditing-repositories ===
Token breakdown:
Name: 8 tokens
Description: 51 tokens
Body: 1046 tokens (156 lines)
References:
llm-security.md 427 tokens
───────────────────────────────────────────────
Total: 1532 tokens
=== authoring-skills ===
Token breakdown:
Name: 8 tokens
Description: 32 tokens
Body: 861 tokens (105 lines)
References:
checklist.md 301 tokens
patterns.md 880 tokens
process.md 311 tokens
specification.md 1441 tokens
───────────────────────────────────────────────
Total: 3834 tokens
=== backing-up-with-keld ===
Token breakdown:
Name: 9 tokens
Description: 39 tokens
Body: 1742 tokens (235 lines)
References:
config-examples.md 1415 tokens
installation.md 19 tokens
───────────────────────────────────────────────
Total: 3224 tokens
=== collaborating-through-pr-pico-sh ===
Token breakdown:
Name: 12 tokens
Description: 47 tokens
Body: 521 tokens (43 lines)
References:
contributing.md 162 tokens
jujutsu.md 516 tokens
reviewing.md 406 tokens
───────────────────────────────────────────────
Total: 1664 tokens
=== creating-tasks-through-lunatask ===
Token breakdown:
Name: 12 tokens
Description: 41 tokens
Body: 741 tokens (88 lines)
References:
cli.md 218 tokens
handoff.md 1035 tokens
installing-lune.md 65 tokens
───────────────────────────────────────────────
Total: 2112 tokens
=== formatting-commits ===
Token breakdown:
Name: 8 tokens
Description: 57 tokens
Body: 310 tokens (34 lines)
References:
conventional-commits.md 362 tokens
installing-git-format.md 22 tokens
kernel-style.md 526 tokens
───────────────────────────────────────────────
Total: 1285 tokens
=== frontend-accessibility ===
Token breakdown:
Name: 7 tokens
Description: 52 tokens
Body: 1080 tokens (148 lines)
References:
antipatterns.md 1341 tokens
patterns.md 2279 tokens
───────────────────────────────────────────────
Total: 4759 tokens
=== getting-a-code-review ===
Token breakdown:
Name: 8 tokens
Description: 98 tokens
Body: 412 tokens (54 lines)
───────────────────────────────────────────────
Total: 518 tokens
=== handling-customer-data ===
Token breakdown:
Name: 9 tokens
Description: 46 tokens
Body: 718 tokens (107 lines)
───────────────────────────────────────────────
Total: 773 tokens
=== humanizer ===
Token breakdown:
Name: 6 tokens
Description: 31 tokens
Body: 3274 tokens (462 lines)
───────────────────────────────────────────────
Total: 3311 tokens
=== ideating-with-bdd ===
Token breakdown:
Name: 9 tokens
Description: 133 tokens
Body: 1582 tokens (177 lines)
References:
gherkin-reference.md 984 tokens
───────────────────────────────────────────────
Total: 2708 tokens
=== initialising-and-updating-agents-md ===
Token breakdown:
Name: 12 tokens
Description: 59 tokens
Body: 850 tokens (63 lines)
───────────────────────────────────────────────
Total: 921 tokens
=== invoking-subagents ===
Token breakdown:
Name: 8 tokens
Description: 42 tokens
Body: 450 tokens (20 lines)
───────────────────────────────────────────────
Total: 500 tokens
=== maintaining-aur-packages ===
Token breakdown:
Name: 9 tokens
Description: 58 tokens
Body: 1439 tokens (103 lines)
References:
build-patterns.md 1120 tokens
───────────────────────────────────────────────
Total: 2626 tokens
=== managing-and-navigating-worktrees ===
Token breakdown:
Name: 11 tokens
Description: 60 tokens
Body: 703 tokens (96 lines)
───────────────────────────────────────────────
Total: 774 tokens
=== monitoring-with-munin ===
Token breakdown:
Name: 10 tokens
Description: 62 tokens
Body: 1801 tokens (222 lines)
References:
writing-plugins.md 1151 tokens
───────────────────────────────────────────────
Total: 3024 tokens
=== notifying-through-ntfy ===
Token breakdown:
Name: 10 tokens
Description: 37 tokens
Body: 1052 tokens (89 lines)
References:
ht.md 383 tokens
httpie.md 385 tokens
nodejs.md 541 tokens
python.md 517 tokens
wget.md 430 tokens
───────────────────────────────────────────────
Total: 3355 tokens
=== rebasing-with-git ===
Token breakdown:
Name: 8 tokens
Description: 71 tokens
Body: 2317 tokens (232 lines)
───────────────────────────────────────────────
Total: 2396 tokens
=== researching-with-rumilo ===
Token breakdown:
Name: 10 tokens
Description: 60 tokens
Body: 1217 tokens (112 lines)
───────────────────────────────────────────────
Total: 1287 tokens
=== resuming-work-through-lunatask ===
Token breakdown:
Name: 12 tokens
Description: 44 tokens
Body: 466 tokens (42 lines)
References:
cli.md 195 tokens
installing-lune.md 65 tokens
───────────────────────────────────────────────
Total: 782 tokens
=== scripting-with-go ===
Token breakdown:
Name: 8 tokens
Description: 46 tokens
Body: 727 tokens (138 lines)
───────────────────────────────────────────────
Total: 781 tokens
=== testing-with-gocuke-and-gherkin ===
Token breakdown:
Name: 14 tokens
Description: 77 tokens
Body: 633 tokens (67 lines)
References:
bdd-practices.md 261 tokens
gocuke-api.md 1427 tokens
───────────────────────────────────────────────
Total: 2412 tokens
=== updating-llm-client-model-lists ===
Token breakdown:
Name: 13 tokens
Description: 51 tokens
Body: 997 tokens (126 lines)
───────────────────────────────────────────────
Total: 1061 tokens
=== using-exe-dev ===
Token breakdown:
Name: 8 tokens
Description: 32 tokens
Body: 380 tokens (45 lines)
───────────────────────────────────────────────
Total: 420 tokens
=== using-jujutsu ===
Token breakdown:
Name: 9 tokens
Description: 55 tokens
Body: 735 tokens (92 lines)
───────────────────────────────────────────────
Total: 799 tokens
=== working-with-tmux ===
Token breakdown:
Name: 8 tokens
Description: 32 tokens
Body: 909 tokens (128 lines)
───────────────────────────────────────────────
Total: 949 tokens
=== writing-git-tags ===
Token breakdown:
Name: 7 tokens
Description: 38 tokens
Body: 821 tokens (107 lines)
References:
installing-git-format.md 22 tokens
───────────────────────────────────────────────
Total: 888 tokens
=== writing-roc-lang ===
Token breakdown:
Name: 8 tokens
Description: 53 tokens
Body: 693 tokens (117 lines)
References:
builtins-llms.md 25216 tokens
llms.md 4253 tokens
scripting.md 614 tokens
───────────────────────────────────────────────
Total: 30837 tokens
=== writing-rust ===
Token breakdown:
Name: 7 tokens
Description: 45 tokens
Body: 1324 tokens (139 lines)
References:
idioms.md 1708 tokens
───────────────────────────────────────────────
Total: 3084 tokens
============================================================
SUMMARY
============================================================
Skills: 31
Metadata: 1949 tokens
Combined bodies: 32856 tokens
Overall: 88318 tokens
Validation errors: 0
Largest skills (by total tokens):
1. writing-roc-lang 30837 tokens
2. ast-grep 5363 tokens
3. frontend-accessibility 4759 tokens
4. authoring-skills 3834 tokens
5. notifying-through-ntfy 3355 tokens
Some other tools if these interested you
- wt - CLI for managing git worktrees
- git-format - CLI that turns LLM input into well-formatted conventional commits and tags
- garble - transform stdin with an LLM (fix typos, translate, reformat)
- lune - CLI and MCP server for Lunatask.app