agentleFS
automagik-devautomagik-dev/genie/skills/genie-hacks/SKILL.md

genie-hacks

Skill351 starsChanged 8 months agoApache-2.0View on GitHub

Browse, search, and contribute community hacks — real-world patterns for provider switching, teams, skills, hooks, cost optimization, and more.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Registry: read references/catalog.md (relative to this skill directory) before answering any list, search, show or help request.

    line 14
  2. Very specific:

    Contribute mechanics: read references/contributing.md when running contribute.

    line 15
  3. Very specific:

    Keep output concise: tables for list, the full format only for show.

    line 28
  4. Very specific:

    Submit: only after the confirmed preview, following references/contributing.md: preflight GitHub access, fork or use the GitHub connector, …

    line 34
  5. Very specific:

    If gh is missing or unauthenticated, or any GitHub step fails, save the formatted hack to ~/.genie/cache/pending-hacks/<hack-id>.md and …

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Genie Hacks

Browse real-world Genie patterns contributed by the community: search by problem, explore by category, or contribute your own. No subcommand means list.

Data

  • Registry: read references/catalog.md (relative to this skill directory) before answering any list, search, show or help request. It holds every hack (problem, solution, code, benefit, when to use) and the category table. Never invent a hack that is not in it.
  • Contribute mechanics: read references/contributing.md when running contribute; it has the exact fork, branch and PR commands and the offline fallback.
  • Published page: https://docs.automagik.dev/genie/hacks (source genie/hacks.mdx in automagik-dev/docs).

Commands

CommandBehavior
listTable of all hacks (ID, title, category), then the count and a contribute nudge.
search <keyword>Case-insensitive match over title, problem, solution and code; per match show ID, title, category and a problem snippet. No matches: suggest broader terms or list.
show <hack-id>Full entry. Unknown ID: suggest the closest IDs.
help <problem>The top three relevant hacks with a one-line why and a quick tip each; prefer a loose match to "no matches".
contributeGuided submission that opens a PR to automagik-dev/docs.

Keep output concise: tables for list, the full format only for show.

Contribute

  1. Gather title, problem, solution with code, category (one from the catalog's table), benefit and when-to-use, one question at a time.
  2. Preview the hack in the catalog template and confirm: yes submits, edit re-prompts that field, cancel aborts.
  3. Submit only after the confirmed preview, following references/contributing.md: preflight GitHub access, fork or use the GitHub connector, branch hack/<slug>, append under the category heading in genie/hacks.mdx, commit hack: <title>, open the PR against dev, never main.
  4. Report the PR URL and what happens next.

If gh is missing or unauthenticated, or any GitHub step fails, save the formatted hack to ~/.genie/cache/pending-hacks/<hack-id>.md and relay the manual steps; never lose the write-up.

Rules

  • Hack IDs are lowercase kebab-case and unique; check existing IDs first.
  • Hacks are realistic and tested, never aspirational.
  • Catalog code uses the live v5 CLI (genie --help is the source of truth); v4-era entries carry a note with the live replacement.
  • Community discussion: https://discord.gg/automagik

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.