← All digests
Added (2)
- Claude Code · first-party · fewer-permission-prompts — Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.
- Cursor · third-party · Auth0 — Auth0 skills for quickstarts, migration, MFA, and framework-specific SDK integrations for React, Next.js, Vue, Nuxt, Angular, Express, Fastify, FastAPI, Swift, Android, ASP.NET Core, React Native, and Expo.
Updated (10)
- Claude Code · first-party · builtin
description: Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR. → Research and plan a large-scale change, then execute it in parallel across 5\u201330 isolated worktree agents that each open a PR.
version: 2.1.112 → 2.1.118
- Claude Code · first-party · builtin
version: 2.1.112 → 2.1.118
- Claude Code · first-party · builtin
version: 2.1.112 → 2.1.118
- Claude Code · first-party · builtin
version: 2.1.112 → 2.1.118
- Claude Code · first-party · builtin
version: 2.1.112 → 2.1.118
- Claude Code · first-party · builtin
description: Use this skill to configure the Claude Code harness via settings.json. Automated behaviors ("from now on when X", "each time X", "whenever X", "before/after X") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions ("allow X", "add permission", "move permission to"), env vars ("set X=Y"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: "allow npm commands", "add bq permission to global settings", "move permission to user settings", "set DEBUG=true", "when claude stops show X". For simple settings like theme/model, use Config tool. → Use this skill to configure the Claude Code harness via settings.json. Automated behaviors ("from now on when X", "each time X", "whenever X", "before/after X") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions ("allow X", "add permission", "move permission to"), env vars ("set X=Y"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: "allow npm commands", "add bq permission to global settings", "move permission to user settings", "set DEBUG=true", "when claude stops show X". For simple settings like theme/model, suggest the /config command.
version: 2.1.112 → 2.1.118
- Claude Code · first-party · builtin
description: Reflective memory consolidation — review recent activity, synthesize learnings into typed memory files, and prune stale entries. → Reflective memory consolidation \u2014 review recent activity, synthesize learnings into typed memory files, and prune stale entries.
version: 2.1.112 → 2.1.118
- Claude Code · first-party · builtin
description: (none) → Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.
version: 2.1.112 → 2.1.118
- Claude Code · first-party · builtin
description: Create, update, list, or run scheduled remote agents (triggers) that execute on a cron schedule. → Create, update, list, or run scheduled remote agents (routines) ${H?"on a cron schedule or once at a specific time":"that execute on a cron schedule"}.
version: 2.1.112 → 2.1.118
- Claude Code · first-party · builtin
version: 2.1.112 → 2.1.118
Removed (1)
- Claude Code · first-party · less-permission-prompts