01-package-scaffolding/overlay-generator/SKILL.md
Generate client-specific overlay files (metadata, permissions, manifests) from a canonical SKILL.md source for different AI agent clients. Use when publishing a skill to multiple ecosystems (Copilot, OpenCode, Codex, Gemini CLI), converting between overlay formats, or validating overlay consistency. Do not use when creating skills for a single client only or when editing skill content (edit SKILL.md first, then regenerate overlays).
npx skillsauth add chelch5/skilllibrary overlay-generatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generates client-specific overlays from a canonical SKILL.md source. Each AI client has different metadata requirements — this skill produces the right format while keeping content authoritative in one place.
SKILL.md (canonical source of truth)
│
├── metadata.json (Copilot overlay)
├── permissions.yaml (OpenCode overlay)
├── openai.yaml (Codex overlay)
└── manifest.json (Universal cross-client index)
Extract: name, description, license, compatibility.clients, and all metadata fields.
For each compatible client, generate the appropriate overlay format:
Copilot (metadata.json):
{
"name": "<name>",
"version": "1.0.0",
"description": "<description>",
"main": "SKILL.md",
"license": "<license>"
}
OpenCode (permissions.yaml):
name: <name>
description: "<description>"
permissions:
read: ["src/**/*", "tests/**/*", "docs/**/*"]
write: ["src/**/*", "tests/**/*"]
Codex (openai.yaml):
name: <name>
description: "<description>"
schema_version: "1.0"
capabilities: [file_read, file_write, shell_execute]
# All overlays must reference the same name and description
grep -h "name" metadata.json permissions.yaml openai.yaml 2>/dev/null | sort -u
# Validate JSON/YAML syntax
cat metadata.json | jq . 2>/dev/null
for skill_dir in */; do
if [ -f "$skill_dir/SKILL.md" ]; then
# Generate overlays for each skill
fi
done
Per skill:
skill-name/
├── SKILL.md # Canonical source (unchanged)
├── metadata.json # Copilot overlay (if compatible)
├── permissions.yaml # OpenCode overlay (if compatible)
└── openai.yaml # Codex overlay (if compatible)
At library root: skills-manifest.json indexing all skills and their overlays.
testing
Manages context window budgets, loading strategies, and compaction techniques for AI-assisted coding sessions. Trigger on 'context window', 'what to load', 'context management', 'context overflow', 'token budget'. DO NOT USE for loading specific project docs into agent context (use project-context) or prompt wording and optimization (use prompt-crafting).
development
Implements authentication, session, token, and authorization patterns for the current stack. Trigger on 'add auth', 'JWT', 'OAuth', 'login endpoint', 'session management', 'API key auth'. DO NOT USE for OWASP hardening checklists (use security-hardening), threat modeling (use security-threat-model), or secret rotation/storage (use security-best-practices).
tools
Defines request/response shapes, versioning, validation, and compatibility rules for API-first work. Trigger on 'design API', 'OpenAPI spec', 'REST schema', 'API versioning', 'generate client SDK'. DO NOT USE for GraphQL schemas, gRPC/protobuf definitions (use stack-standards), auth endpoint logic (use auth-patterns), or external API client wrappers (use external-api-client).
development
Create a repo-local ticket system with an index, machine-readable manifest, board, and individual ticket files. Use when a repo needs task decomposition that autonomous agents can follow without re-planning the whole project each session. Do not use for executing tickets (use ticket-execution) or quick fixes that don't warrant formal tickets.