Loading...
Loading...
Found 6,225 Skills
Diagnose ClickHouse issues by analyzing system.part_log (part creation, merges, mutations, downloads, removals, moves). Use for too many parts / micro-batch inserts, merge backlog or slow merges, mutation storms (ALTER DELETE/UPDATE), unusual replication DownloadPart churn, unexpected RemovePart spikes, or ZooKeeper/Keeper znode growth correlated with part activity.
PostgreSQL-specific development assistant focusing on unique PostgreSQL features, advanced data types, and PostgreSQL-exclusive capabilities. Covers JSONB operations, array types, custom types, range/geometric types, full-text search, window functions, and PostgreSQL extensions ecosystem.
Manus-style file planning system for organizing and tracking progress of complex tasks. Creates three files: task_plan.md, findings.md, and progress.md. Use when users request planning, decomposition, or organization of multi-step projects, research tasks, or work requiring more than 5 tool calls. Supports automatic session recovery after /clear. Trigger words: task planning, project planning, create plan, decompose task, multi-step planning, progress tracking, file planning, help me plan, decompose project
Test APIs and services with Vitest in Encore.ts.
MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.
Intelligent agent for validating ERPNext/Frappe code against best practices and common pitfalls. Use when reviewing generated code, checking for errors before deployment, or validating code quality. Triggers: review this code, check my script, validate before deployment, is this correct, find bugs, check for errors, will this work.
Create beautiful infographics with pre-designed templates. Best for KPI cards, timelines, roadmaps, step-by-step processes, A vs B comparisons, SWOT analysis, funnels, org trees, pie/bar charts. Use when you need quick visual impact with 4-8 items. Simple YAML-like syntax. NOT for complex data analysis (use vega) or technical flowcharts (use mermaid).
Review SQL and query code for injection risk, parameterization, indexing and performance, transactions, NULL and constraints, and dialect portability. Language-only atomic skill; output is a findings list.
Explains the mental model and architecture of the code under `packages/forms/signals`. You MUST use this skill any time you plan to work with code in `packages/forms/signals`
Read your daily Working Memory briefing to understand current context. Contains active focus areas, priorities, unresolved flags, and recent knowledge changes. Load this automatically at the beginning of sessions for cross-tool continuity.
Evaluate a website, landing page, content, or any online asset through the eyes of pre-built synthetic ICP personas. Loads personas from icp-persona-builder output, then runs them against target URLs. Supports three modes: structured scorecard, freeform focus group, and head-to-head competitive comparison. Reusable — run against the same site after changes, or against new content anytime.
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. OCD-level review and synchronization of project documents and agent memory after a session. MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "sync up", "tidy up docs", "tidy up", "update memory", "organize", "wrap up", "this phase is done", "newcomers can start directly", or any phrase suggesting a development milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. A standalone "tidy" with prior development context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.