agentleFS
Beskars-CodeBeskars-Code/Skills/skills/rules/SKILL.md

rules

Skill0 starsChanged 5 days agoMITView on GitHub

Never invoke directly. Holds the rule files that AGENTS.md and other skills link to; open one only when AGENTS.md or a skill names it. Ships as a skill so the rules install with npx skills.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Not a user skill: never recommend /rules.

    line 10

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

Pack rules

Not a user skill: never recommend /rules. This folder exists so npx skills installs the rules next to every other skill (../rules/...). Root-level skills/*.md files are not installed.

Read when

The Rules section and the Read when table in AGENTS.md are the source for when to open each file.

One file for each AGENTS.md rule that needs more than its bold line:

  • keep-it-simple.md: least code for the result, subtract first, light to read, a folder per concern instead of utils dumps
  • strong-foundation.md: a strong first iteration with a seam (a named extension point where a new variant plugs in) on each area of modularity, scaled to the work and the context
  • no-unrequested-tests.md: no test unless the user accepted it
  • main-context.md: keep judgment in the main context, hand noisy work to a subagent

Journeys, listed in /ask-gabriel: journeys/ holds one file per journey, each following one piece of billing work through the skills and rules.

Topic files, named in the Read when table:

  • code-quality.md: code quality rules (quality:* cite keys), named principles, mechanical rules, reuse env vars, naming
  • code-quality-examples.md: good and bad snippets for code-quality.md
  • code-structure.md: code structure rules (structure:* cite keys), services, primitives (one-job helpers), folders, cheap reads, authority (the server enforces), the Structure card
  • code-structure-examples.md: good and bad shapes for code-structure.md
  • planning.md: reads before planning, grill first, the Before/After change diagram, and the in-chat execution context (authority order, context template, optional persistence)
  • execution.md: Git sync only, verification scope, ready-ticket preflight, handoffs and evidence, remediation, recovery and completion
  • user-experience.md: every UI and UX rule (ux:* cite keys), React and UI, docs/design.md as the app UX source of truth, copy, locale, quality floor
  • writing-style.md: no em dash, plain language and plain (Classic) principle names, asking the user (the ask bar, Questions and Locked-in templates), the final report, and the Unslop rules for chat replies
  • testing.md: when an accepted test is worth writing, the authoring gate, junk patterns, the retention bar, what a good test looks like, the test proposal, the test comment, and the handoff
  • shipping.md: branch safety, scoped pre-push/required checks, remote CI reporting, the create tool, and the branch-and-push process
  • shipping-templates.md: ship questions and announcements, the PR Change diagram rule, and the PR title and body template
  • tooling.md: harness-first discovery, browser permissions/fallbacks, focused checks and terminal evidence
  • dev-server-logs.md: accessible service output, OS-aware log-only viewers, remote fallback, visibility evidence and lifecycle
  • pr-lifecycle.md: parent-owned watching, latest-head readiness, cleanup and intent-aware takeover
  • principles.md: steering vocabulary for a design, verification, or delegation judgment. One-line rule, when to open it, and a pointer to the file that owns the detail

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.