Total 32,714 skills
Showing 12 of 32714 skills
Single table design patterns for DynamoDB with SST - modeling complex data relationships in a single table for optimal performance and cost
Auto-detect and fix common Excel formatting issues like merged cells, inconsistent types, duplicate headers, and encoding problems.
Update and upgrade published mir snippets. Use this when you want to update a published snippet, fix a published snippet, or upgrade the version of a snippet.
PMU observation pattern for agent health monitoring. Runs patrol loops, detects stalled agents, sends nudges, and escalates persistent failures to the mayor. Never modifies agent work or resolves conflicts.
Kubernetes cluster operations: kubectl commands, manifest generation, Helm charts, RBAC, debugging, and deployment strategies.
Operate OpenAI Codex CLI (terminal coding agent) to accomplish software engineering tasks. Use when the user asks to: run codex commands, use codex for coding tasks, execute codex exec for automation, do code review with codex, manage codex sessions (resume/fork), configure codex (config.toml, approval modes, sandbox), use codex cloud, set up MCP servers in codex, or any task involving the `codex` command-line tool. Triggers: codex, codex exec, codex review, codex cloud, codex mcp, codex resume, codex sandbox, openai codex.
Design APIs using Kin Lane's "API Evangelist" philosophy. Emphasizes Design-First (OpenAPI), governance, treating APIs as products, and the political/business impact of interfaces. Use when building public platforms or large-scale internal ecosystems.
Durable asynchronous messaging channel for inter-agent communication. Implements write-once read-many filesystem mail using atomic writes and directory-based mailboxes.
Use when setting, tracking, or scoring quarterly Rocks
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.
React Native performance review checklist for code reviews. Use when reviewing RN code to detect rendering, animation, and native performance regressions. Complements zereight-review — run both together on RN PRs.
Add a grant (funding) to an existing Karma project. Use when user says "add a grant", "record funding", "create grant", "add funding to project", or "received a grant".