Loading...
Loading...
Found 145 Skills
Generate headless Claude Code cron jobs from a task description and schedule. Creates a wrapper script with safety mechanisms (lockfile, budget cap, dry-run default, logging) and installs crontab entries via deterministic Python script. Use when user says "schedule", "run every", "cron job", "run twice daily", "run hourly", "run daily", "run weekly", or "schedule task".
Defense-in-depth verification before declaring any task complete. Run tests, check build, validate changed files, verify no regressions. Applies 4-level adversarial artifact verification (EXISTS > SUBSTANTIVE > WIRED > DATA FLOWS) with goal-backward framing. Use before saying "done", "fixed", or "complete" on any code change. Use for "verify", "make sure it works", "check before committing", or "validate changes". Do NOT use for debugging (use systematic-debugging) or code review (use systematic-code-review).
Review and revise content to remove AI-sounding patterns. Voice-agnostic editor that detects cliches, passive voice, structural monotony, and meta-commentary. Use when content sounds robotic, needs de-AIing, or voice validation flags synthetic patterns. Use for "edit for AI", "remove AI patterns", "make it sound human", or "de-AI this". Do NOT use for grammar checking, factual editing, or full rewrites. Do NOT use for voice generation (use voice skills instead).
Explicit anti-rationalization enforcement for maximum-rigor task execution. Loads all anti-rationalization patterns, gate enforcement, and pressure resistance as a composable modifier on any task. Use when executing critical production changes, security-sensitive code, complex multi-file refactors, or any task where shortcuts could cause harm. Use for "with rigor", "carefully", "maximum verification", or "no shortcuts". Do NOT use for trivial lookups, documentation-only edits, or simple typo fixes where full gate enforcement would be disproportionate overhead.
A/B test agent variants measuring quality and total session token cost across simple and complex benchmarks. Use when creating compact agent versions, validating agent changes, comparing internal vs external agents, or deciding between variants for production. Use for "compare agents", "A/B test", "benchmark agents", or "test agent efficiency". Do NOT use for evaluating single agents, testing skills, or optimizing prompts without variant comparison.
Guided Perses dashboard creation: gather requirements (metrics, datasource, layout), generate CUE definition or JSON spec, validate with percli lint, deploy with percli apply or MCP perses_create_dashboard. Use when user wants to create a new Perses dashboard, build a monitoring dashboard, or generate dashboard definitions. Use for "create perses dashboard", "new dashboard", "perses new dashboard", "build dashboard". Do NOT use for Grafana migration (use perses-grafana-migrate) or plugin development (use perses-plugin-create).
Deterministic 3-phase service health monitoring: Discover, Check, Report. Use when user asks about service status, process health, uptime, or whether services are running. Use for "health check", "is service up", "service status", "what's running", or "check if alive". Do NOT use for HTTP endpoint validation, performance profiling, or log analysis without a specific health concern.
Decision-first data analysis with statistical rigor gates. Use when analyzing CSV, JSON, database exports, API responses, logs, or any structured data to support a business decision. Handles: trend analysis, cohort comparison, A/B test evaluation, distribution profiling, anomaly detection. Do NOT use for codebase analysis (use codebase-analyzer), codebase exploration (use explore-pipeline), or ML model training.
Full-repo SAP Converged Cloud Go compliance audit. Reviews every package against established review standards — focusing on over-engineering, error message quality, dead code, interface contracts, copy-paste structs, and pattern consistency with keppel. Dispatches parallel agents by package group, each reading ALL sapcc rules. Produces code-level findings with actual before/after diffs. Invoked via "/sapcc-audit" or through /do.
Resolve implementation ambiguities before planning begins. Two modes: Discussion mode surfaces gray areas with concrete options for greenfield work. Assumptions mode reads the codebase, forms evidence-based opinions, and asks the user to correct only what's wrong (brownfield work). Use for "discuss ambiguities", "resolve gray areas", "clarify before planning", "assumptions mode", "what are the gray areas", "before we plan". Do NOT use for broad design exploration (use feature-design) or for planning itself (use feature-plan).
Condition-based polling and retry patterns: exponential backoff, health checks, rate limit recovery, circuit breakers. Use when replacing arbitrary sleeps with condition checks, implementing retry logic, waiting for service availability, or handling API rate limits. Use for "wait for", "poll until", "retry with backoff", "health check", or "rate limit". Do NOT use for async event-driven architectures, distributed locking, or real-time guarantees.
Go-specific code review with 6-phase methodology: Context, Automated Checks, Quality Analysis, Specific Analysis, Line-by-Line, Documentation. Use when reviewing Go code, PRs, or auditing Go codebases for quality and best practices. Use for "review Go", "Go PR", "check Go code", "Go quality", "review .go". Do NOT use for writing new Go code, debugging Go bugs, or refactoring -- use golang-general-engineer, systematic-debugging, or systematic-refactoring for those tasks.