agentleFS
Abwor9658Abwor9658/social-media-skills/AGENTS.md

social-media-skills

AGENTS.md2 starsChanged 8 months agoMITView on GitHub

This document defines the conventions and requirements for skills in this repository. Skills are grouped by layer in skills/ but have no required subdirectory structure beyond <skill-name>/SKILL.md. Every SKILL.md must begin with a YAML frontmatter block: Field constraints: A well-formed SKILL.md should include: Use conventional commits for all changes to this repository: Example commit messages: - feat: add hook-writer-sms skill - update: expand platform-strategy-sms with Bluesky guidance - fix: correct frontmatter version field in post-writer-sms - chore: update validate-skills.sh to…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this AGENTS.md into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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:

    Every SKILL.md must begin with a YAML frontmatter block:

    line 33
  2. Distinctive:

    If a skill grows beyond this limit, split guidance into focused sub-sections or extract repeated patterns into shared references

    line 62
  3. Distinctive:

    Use conventional commits for all changes to this repository:

    line 78
  4. Distinctive:

    Run the validation script before committing:

    line 96
  5. Distinctive:

    All checks must pass before merging to main.

    line 108

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

Agent Skills Specification

This document defines the conventions and requirements for skills in this repository.

Repository Structure

social-media-skills/
├── .claude-plugin/
│   └── marketplace.json       # Plugin manifest
├── skills/
│   ├── social-media-context-sms/
│   │   └── SKILL.md
│   ├── content-strategy-sms/
│   │   └── SKILL.md
│   └── <skill-name>/
│       └── SKILL.md
├── tools/
│   └── REGISTRY.md            # Tool integrations registry
├── AGENTS.md                  # This file
├── CLAUDE.md                  # Agent guidelines
├── LICENSE
├── README.md
└── validate-skills.sh         # Validation script

Skills are grouped by layer in skills/ but have no required subdirectory structure beyond <skill-name>/SKILL.md.

Skill Requirements

YAML Frontmatter

Every SKILL.md must begin with a YAML frontmatter block:

---
name: skill-name
description: One to three sentence description of what this skill does and when to use it.
metadata:
  version: "1.0.0"
---

Field constraints:

FieldTypeConstraints
namestring1–64 characters, kebab-case
descriptionstring1–1024 characters
metadata.versionstringsemver format (e.g. "1.0.0")

Naming Conventions

  • Lowercase only — no uppercase letters anywhere in skill names or directory names
  • Alphanumeric and hyphens only — no spaces, underscores, dots, or special characters
  • Kebab-case — words separated by single hyphens (e.g. hook-writer-sms, not hookwriter or hook_writer)
  • The name field in frontmatter must match the directory name exactly

File Size

  • Each SKILL.md must be under 500 lines
  • If a skill grows beyond this limit, split guidance into focused sub-sections or extract repeated patterns into shared references

Content Structure

A well-formed SKILL.md should include:

  1. YAML frontmatter (required)
  2. A brief purpose statement
  3. Inputs — what context or parameters the skill expects
  4. Steps — numbered or structured instructions the agent follows
  5. Outputs — what the skill produces
  6. Examples (optional but encouraged)
  7. See also — links to related skills

Git Workflow

Use conventional commits for all changes to this repository:

PrefixWhen to use
feat:Adding a new skill or significant new capability
fix:Correcting errors in skill instructions or metadata
update:Improving or expanding an existing skill
docs:Changes to README, AGENTS.md, CLAUDE.md, or other docs
chore:Tooling, config, or maintenance changes

Example commit messages:

  • feat: add hook-writer-sms skill
  • update: expand platform-strategy-sms with Bluesky guidance
  • fix: correct frontmatter version field in post-writer-sms
  • chore: update validate-skills.sh to check metadata.version

Validation

Run the validation script before committing:

./validate-skills.sh

The script checks:

  • YAML frontmatter exists with name and description
  • name is kebab-case and within 1–64 characters
  • description is within 1–1024 characters
  • File is under 500 lines

All checks must pass before merging to main.

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.