Loading...
Loading...
Found 5,471 Skills
Breaks work into bite-sized tasks before coding. Activates when a multi-step task needs planning — creates tasks small enough for a junior developer to follow (2-5 minutes each), with exact file paths, complete implementation details, and verification steps. References Linear issue context and project-specific test commands from CLAUDE.md.
Test application performance, scalability, and resilience. Use when planning load testing, stress testing, or optimizing system performance.
This skill should be used when creating conventional commits for current changes and then submitting the current branch as a pull request for code review. It combines the git:commit and git:submit-pr skills into a single workflow.
Use when generating text input components in Quasar (Vue) or NiceGUI that handle Korean or CJK IME composition - prevents double-enter bugs, lagging v-model binding, and isComposing issues
Transform rough ideas into clear, engaging writing using Gary Provost's rhythm and structure principles. Use when the user needs help writing emails, tweets, scripts, sales copy, articles, or any content where readability, flow, and digestibility matter. Ideal for entrepreneurs and content creators who want to turn ideas into professional writing without sounding robotic or over-polished. Apply when the user asks for help writing, editing for clarity, improving pacing, or making content more engaging.
Génère des trésors BFRPG par type (A-U). Pièces, gemmes, bijoux et objets magiques. Utilise les tables officielles avec probabilités. Indispensable après un combat victorieux.
Review existing Datadog dashboards for operational readiness. Audits alert threshold markers, threshold proximity to normal traffic, customer-facing section completeness, and zero-knowledge readability. Uses pup CLI to fetch dashboard definitions. Use when auditing dashboards before on-call handoff, after dashboard changes, or during operational reviews. Do not use for: (1) designing new dashboards from scratch, (2) monitor/alert rule design, (3) APM instrumentation or tracing setup, (4) log pipeline configuration.
Configure Prometheus Alertmanager with routing trees, receivers (Slack, PagerDuty, email), inhibition rules, silences, and notification templates for actionable incident alerting. Use when implementing proactive monitoring with automated incident detection, routing alerts to the appropriate team by severity, reducing alert fatigue through grouping and deduplication, integrating with on-call systems like PagerDuty, or migrating from legacy alerting to Prometheus-based alerting.
A guide for creating effective Skills. It is used when users want to create new Skills (or update existing Skills) to extend Claude's capabilities, including professional knowledge, workflows or tool integration.
Deep EVM smart contract security audit system. Use when asked to audit a contract, find vulnerabilities, review code for security issues, or file security issues on a GitHub repo. Covers 500+ non-obvious checklist items across 19 domains via parallel sub-agents. Different from the security skill (which teaches defensive coding) — this is for systematically auditing contracts you didn't write.
Unified YouTube script creation for cardiology channels in Hinglish. Uses the COMPLETE research-engine pipeline (channel scraping, comment analysis, narrative monitoring, gap finding, view prediction) combined with RAG + PubMed for evidence. Data-driven topic selection, 15-30 min educational videos with 6-point voice check.
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.