Agent skill

add-frontmatter

Scan all .md files in the project and add or fix YAML frontmatter (summary + read_when) so they can be discovered by context routers like Reflex.

Stars 146
Forks 13

Install this agent skill to your Project

npx add-skill https://github.com/markmdev/meridian/tree/main/skills/add-frontmatter

SKILL.md

Add Frontmatter

Scan every .md file in the project and ensure it has the required frontmatter so Reflex can discover and route it.

Required frontmatter format

---
summary: One-line description of what this file covers
read_when:
  - keyword or phrase that signals this file is relevant
  - another keyword
---

What to skip

  • Files already having correct summary + read_when frontmatter — leave them alone
  • Files that have frontmatter with any other keys (e.g. name, description, title) — do not replace or merge, leave them alone
  • node_modules/, .git/, dist/, build/, vendor/, __pycache__/
  • .claude/ — agents, skills, commands, hooks all use their own frontmatter schemas
  • Files that are purely generated output, changelogs, or boilerplate with no reusable knowledge (e.g. CHANGELOG.md, LICENSE)

Process

  1. Glob all .md files, excluding skip dirs
  2. For each file: check if frontmatter with summary and read_when already exists
  3. If missing or incomplete: read the file content, infer a concise summary and 2-4 read_when keywords from the actual content
  4. Prepend the frontmatter block (or insert after existing --- if only partially present)
  5. Write the updated file

Quality criteria

  • summary is a single line, factual, specific — describes what the file actually covers
  • read_when keywords match how someone would describe a task that needs this file (e.g. "setting up auth", "debugging routing", "OpenClaw plugin")
  • Don't invent knowledge not in the file — infer from actual content only

Expand your agent's capabilities with these related and highly-rated skills.

markmdev/meridian

create-docs

Create or update .meridian/docs/ knowledge files for a module or directory. Produces reference docs with frontmatter for context routing.

146 13
Explore
markmdev/meridian

planning

Interview-driven planning methodology that produces implementation-ready plans. Always use this skill INSTEAD of EnterPlanMode — it provides structured interviewing (20-40 clarifying questions), exhaustive parallel codebase exploration (5-15 Explore agents), verbatim requirements capture, and automated plan validation via plan-reviewer (must score 9+). Use for new features, refactoring, architecture changes, migrations, or any non-trivial implementation work.

146 13
Explore
markmdev/meridian

ux-states-audit

Audit UI code for missing loading states, empty states, and error states. Every async operation and data-driven UI must handle all three. Finds gaps and implements the missing states using the app's existing patterns.

146 13
Explore
markmdev/meridian

error-audit

Audit code for silent error swallowing, fallbacks to degraded alternatives, backwards compatibility shims, and UI that fails to show errors to the user. Finds and fixes all occurrences in the specified scope.

146 13
Explore
markmdev/meridian

observability-audit

Audit code for observability gaps — debug logs left in, errors caught without being logged, missing context on log entries, untracked slow operations. Uses the app's existing observability tooling exclusively.

146 13
Explore
davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results