Loading...
Loading...
Found 1,981 Skills
Deterministic 4-phase documentation drift detector: Scan, Cross-Reference, Detect, Report. Use when skills/agents/commands are added, removed, or renamed, when README files seem outdated, or before committing documentation changes. Use for "check docs", "sync README", "documentation audit", or "stale entries". Do NOT use for writing documentation content, improving descriptions, or generating new README files.
Audit and maintain blog taxonomy (categories/tags) for consistency, SEO, and navigation: scan content, detect orphans and duplicates, merge and rename terms, verify builds. Use when user asks to "audit tags", "fix taxonomy", "consolidate categories", "merge tags", or "clean up taxonomy". Do NOT use for writing new content, individual post SEO optimization, or major content restructuring.
Propose a new spec-driven change. Scaffolds proposal.md, design.md, tasks.md, and questions.md for a named change, populated with project context.
Annotates codebases with dimensional analysis comments documenting units, dimensions, and decimal scaling. Use when someone asks to annotate units in a codebase, perform a dimensional analysis, or find vulnerabilities in a DeFi protocol, offchain code, or other blockchain-related codebase with arithmetic. Prevents dimensional mismatches and catches formula bugs early.
Email deliverability for outbound sales — domain authentication (SPF/DKIM/DMARC), mailbox warmup, sending limits, inbox placement, blacklist monitoring, sender reputation, custom tracking domains, and list hygiene. Use when setting up a new sending domain, warming up mailboxes, diagnosing spam/deliverability issues, recovering from blacklisting, scaling outbound volume, or switching email platforms. Do NOT use for cadence content and strategy (use /sales-cadence), Apollo sequence mechanics (use /sales-apollo-sequences), Mailshake platform help (use /sales-mailshake), Smartlead platform help (use /sales-smartlead), Lemlist platform help (use /sales-lemlist), Yesware platform help (use /sales-yesware), Mixmax-specific config (use /sales-mixmax), Reply.io-specific config (use /sales-reply), or Woodpecker-specific config (use /sales-woodpecker).
Guides the agent through creating a new Ionic app using the Ionic CLI. Covers project scaffolding with ionic start, framework selection (Angular, React, Vue), template selection (blank, tabs, sidemenu), Capacitor integration, and optional Tailwind CSS setup. After app creation with Capacitor integration, delegates to the capacitor-app-creation skill for further Capacitor setup. Do not use for existing Ionic projects, migrating Ionic apps, upgrading Capacitor versions, or non-Ionic mobile frameworks.
Use when an approved current phase has 3 or more independent ready tasks and parallel execution will materially reduce cycle time. Orchestrates bounded workers, monitors blockers and file conflicts, coordinates rescues, and hands off to planning or reviewing when the current execution scope is complete. Use for prompts about swarming, parallel workers, launching multiple agents, coordinating a worker pool, or running approved current-phase work at scale.
Security Check - Security review for skills before installation. Triggers: Before installing new skills, regular review of installed skills, or when security issues with a skill are suspected. Security Checks: - Dangerous Commands: rm -rf, sudo, curl|bash, etc. - Network Requests: Potential data leakage risks - File Writes: Writing to sensitive locations - Credentials: Risk of API key/password leakage - Resource Exhaustion: Infinite loops - Privilege Escalation: Privilege escalation attempts - External Dependencies: Suspicious dependencies Commands: - /安检 <skill-path> - Review skill security - /安检 scan <path> - Deep scan - /安检 list - List risks of installed skills - /安检 fix <skill> - Fix security issues - /security <skill-path> - English command Actions: - Auto-fix: Remove or replace dangerous code - Disable: Disable dangerous features - User Confirm: User chooses whether to proceed - Block: Block installation for severe risks Capabilities: Static code analysis, dangerous pattern recognition, risk assessment, auto-fix, user interactive decision making.
Design partition schemes, select partition keys, create GSI, and write SQL for PolarDB-X 2.0 Enterprise Edition AUTO mode databases, handling PolarDB-X vs MySQL differences (partitioned tables, GSI, CCI, Sequence, table groups, TTL, pagination, etc.). Use when designing partition schemes, selecting partition keys, converting single tables to partitioned tables, creating GSI/CCI indexes, writing or migrating SQL for PolarDB-X, or diagnosing slow queries on PolarDB-X. Triggers: "PolarDB-X SQL", "PolarDB-X create table", "partitioned table", "partition design", "partition scheme", "partition key", "GSI", "CCI", "Sequence", "MySQL migrate to PolarDB-X", "PolarDB-X compatibility", "single table to partitioned table", "convert to partitioned table", "large table", "distributed table", "AUTO mode", "pagination query", "Keyset pagination", "Range partition", "auto add partition", "PolarDB-X slow query", "full-shard scan"
Trigger: Invoked when multiple tasks are competing for time, attention, computing power or budget at the same time, and it is necessary to determine the main attack direction and stop dispersing efforts; common signals include too many priorities, tight resources, scattered progress, and the need to decide what to do first. English: Trigger when limited resources are being split across too many tasks and one main target must be chosen. Use this skill to concentrate effort, sequence work decisively, and finish a meaningful breakthrough before expanding.
Trigger: Invoke when you start from scratch with extremely limited resources and need to find the minimum viable entry point first to build a stable base. Common signals include bootstrap, MVP, pilot, first foothold, and small team startup. Trigger when starting from almost nothing and needing a viable foothold before scaling up. Use this skill to build a durable base, start small, and grow from a validated nucleus instead of scattering effort.
Deep Angular 21 clean code audit with parallel specialist agents and senior team lead. Scans architecture, signals, stores, AI slop, ViewModel patterns, and more. Guarantees craftsman-level output. Use whenever the user says 'clean code', 'audit Angular', 'review frontend', 'check quality', 'anti-patterns', wants Angular code reviewed, or needs senior-level code standards enforced — even if they don't say 'clean code' explicitly.