OpenParable
Skip to content
← Back to skills

Fep

Development
fep

Fep is an Agent Skill for development published in the fedify-dev/fedify repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Look up a Fediverse Enhancement Proposal (FEP) and explain how to implement it with Fedify. Use when the user asks about a specific FEP by ID (e.g., FEP-8fcf, FEP-1b12) or wants to implement a fediverse standard in their Fedify application.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/fedify-dev/fedify/blob/HEAD/claude-plugin/skills/fep/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/fep, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Look up the Fediverse Enhancement Proposal identified by “$ARGUMENTS” and explain how to implement it with Fedify.

Normalization

Normalise the identifier first: strip any leading FEP- or fep- prefix and lowercase the result to get the bare four-character hex id (e.g. 8fcf). Call that $ID in the steps below. If the result does not match ^[0-9a-f]{4}$, stop and ask the user to provide a valid FEP identifier.

Retrieval

If the fep MCP server is available, use mcp__fep__get_fep with id $ID to retrieve the proposal. Otherwise clone the proposals repo and read the file:

FEP_DIR="${TMPDIR:-${TEMP:-/tmp}}/fedify-fep-repo"
git clone https://codeberg.org/fediverse/fep.git "$FEP_DIR" 2>/dev/null \
  || git -C "$FEP_DIR" pull --ff-only
cat "$FEP_DIR/fep/$ID/fep-$ID.md"

Summary

Summarise: status, what problem it solves, and what extensions it defines (new JSON-LD terms, HTTP endpoints, or activity shapes).

Fedify implementation

Explain which Fedify APIs are relevant to the implementation: vocabulary types in @fedify/vocab, custom context handling, dispatcher or inbox listener patterns.