publish-skills

When to use this skill

Use when the user wants to publish extracted or promoted skills to a Prism skill registry. Invoked as /publish-skills (Claude Code) or @publish-skills (Cursor), optionally with flags: --all (publish everything regardless of delta state) or --registry NAME (target a named registry).

Prerequisites

• Skills must exist in _analysis/extracted_skills_codebase/ (created by /extract-skills (Claude Code) or @extract-skills (Cursor), or prism promote) and/or _analysis/extracted_skills_history/ (created by /run-history-pipeline (Claude Code) or @run-history-pipeline (Cursor))
• Each skill directory must contain both plugin.json and SKILL.md
• A registry must be configured in ~/.prism/registries.json (or legacy ~/.prism/config.json)
• The REGISTRY_TOKEN environment variable or per-registry token in registries.json must be available

Flags

Instructions

Step 1 -- Resolve target registry

Resolve the target registry from ~/.prism/registries.json (with fallback to legacy ~/.prism/config.json). If --registry NAME was specified, use that name; otherwise use the default registry.

python3 -c "
import json, os, sys
reg_path = os.path.expanduser('~/.prism/registries.json')
try:
    with open(reg_path) as f:
        data = json.load(f)
except (FileNotFoundError, json.JSONDecodeError):
    data = {'registries': [], 'default': None}
# Fall back to config.json migration
if not data.get('registries'):
    cfg_path = os.path.expanduser('~/.prism/config.json')
    try:
        with open(cfg_path) as f:
            cfg = json.load(f)
        url = cfg.get('registry_url', '')
        if url:
            print(json.dumps({'name': 'default', 'url': url, 'token': '', 'writable': True}))
            sys.exit(0)
    except: pass
    print('NOT_CONFIGURED')
    sys.exit(0)
# Resolve target: --registry NAME or default
target_name = None  # <-- set to registry name if --registry flag was provided
if target_name is None:
    target_name = data.get('default')
if not target_name:
    print('NO_DEFAULT')
    sys.exit(0)
for reg in data['registries']:
    if reg['name'] == target_name:
        if not reg.get('writable', True):
            print('READ_ONLY:' + target_name)
            sys.exit(0)
        print(json.dumps(reg))
        sys.exit(0)
print('NOT_FOUND:' + str(target_name))
"