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.
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_whenfrontmatter — 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
- Glob all
.mdfiles, excluding skip dirs - For each file: check if frontmatter with
summaryandread_whenalready exists - If missing or incomplete: read the file content, infer a concise
summaryand 2-4read_whenkeywords from the actual content - Prepend the frontmatter block (or insert after existing
---if only partially present) - Write the updated file
Quality criteria
summaryis a single line, factual, specific — describes what the file actually coversread_whenkeywords 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
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
create-docs
Create or update .meridian/docs/ knowledge files for a module or directory. Produces reference docs with frontmatter for context routing.
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.
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.
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.
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.
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.
Didn't find tool you were looking for?