Loading...
Loading...
Found 2,738 Skills
Backtest crypto trading strategies from natural language ideas. Use when: user describes trading ideas, wants to validate strategies, mentions "backtest", "trading strategy", "buy low sell high", "RSI", "MACD", "oversold", "overbought", "crypto strategy", "validate strategy", "backtest", "DCA", or similar.
Review code changes against a plan using the plan location and implementing git commit(s).
Verify a specific claim by searching for evidence across web and academic sources. Use when the user asks to verify, fact-check, or confirm a statement.
Comprehensive toolkit for validating, linting, and securing Dockerfiles. Use this skill when validating Dockerfile syntax, checking security best practices, optimizing image builds. Applies to all Dockerfile variants (Dockerfile, Dockerfile.prod, Dockerfile.dev, etc.).
Surface, prioritize, and track risky assumptions before investing significant effort. Use when starting a new project, before major feature work, when feeling uncertain about direction, when the user says "I think users want...", "we assume...", "probably...", or before any build decision that hasn't been validated with real users.
Minimal smoke test for Security Center SAS skill. Validate read-only query flow.
When the user wants to set up, audit, or optimize analytics tracking (GA4, events, conversions). Also use when the user mentions "Google Analytics," "GA4," "event tracking," "conversions," "gtag," or "data layer."
Create Trae IDE rules (.trae/rules/*.md) for AI behavior constraints. Use when user wants to: create a project rule, set up code style guidelines, enforce naming conventions, make AI always do X, customize AI behavior for specific files, configure AI coding standards, or establish project-specific AI guidelines. Triggers on: 'create rule', '创建 rule', 'project rule', '.trae/rules/', 'AGENTS.md', 'CLAUDE.md', 'set up coding rules', 'make AI always use PascalCase', 'enforce naming convention', 'configure AI behavior'. Do NOT use for skills (use trae-skill-writer) or agents (use trae-agent-writer).
Verification discipline for completion claims. Use when about to assert success, claim a fix is complete, report tests passing, or before commits and PRs. Enforces evidence-first workflow.
Minimal smoke test for OpenClaw setup skill. Validate official channel discovery workflow, DingTalk/Feishu integrations, Discord token configuration, and gateway health checks with non-destructive commands.
Inline adversarial plan review — 3 sequential checks (Feasibility, Completeness, Scope & Alignment) performed by the calling LLM in its own context. No subagents spawned. Call after saving a plan. Returns GATE_PASS or GATE_FAIL with blocking issues.
Systematically verifies suspected security bugs to eliminate false positives. Produces TRUE POSITIVE or FALSE POSITIVE verdicts with documented evidence for each bug.