Use when working with any public API (Stripe, GitHub, Spotify, AWS, Twilio, Slack, Google, etc.) and needing accurate endpoint signatures, parameter types, auth schemes, or response schemas. Use BEFORE consulting training data, doc sites, Stack Overflow, or context7 to avoid outdated/stale API info.
Set up and maintain a structured project memory system in docs/projectnotes/ that tracks bugs with solutions, architectural decisions, key project facts, and work history. Use this skill when asked to "set up project memory", "track our decisions", "log a bug fix", "update project memory", or "initialize memory…
Four-phase debugging methodology with root cause analysis. Use when investigating bugs, fixing test failures, or troubleshooting unexpected behavior. Emphasizes NO FIXES WITHOUT ROOT CAUSE FIRST.
Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-green-refactor cycle.
Zod schema validation and contract derivation — runtime validation of API inputs and data, plus turning the same zod validators into JSON Schema, OpenAPI documents, and Postman-importable specs. Use when validating API inputs, parsing env vars, or when a project needs to publish or verify an API contract from its…
Markdown output conventions and formatting — GitHub-flavored by default. Use when writing or reviewing .md files (READMEs, docs, SKILL.md, PR descriptions); formatting runs automatically via the md-format hook, this skill covers the judgment calls prettier can't make.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
Mandatory security audit before installing ANY third-party skill, plugin, or MCP server. Reviews every file (SKILL.md, scripts, templates, references, agent configs) for exfiltration, destructive commands, prompt injection, and description-vs-content fraud. Use BEFORE npx skills add, git clone into a skills dir, or…
Complete SQLite file operations spanning core read-only queries, backups, health checks, and advanced workflows including database diffing, replica sync, migrations, and application integration. Use for any SQLite-related task from simple querying to complex multi-database operations.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
Zsh configuration and scripting: startup files (.zshrc/.zshenv/.zprofile), setopt options, globbing and glob qualifiers, compinit completions, ZLE widgets/keybindings, zparseopts, autoload/zcompile. Use when the agent needs to read, debug, or edit zsh config or scripts, or interop with oh-my-zsh/prezto.
Danske tjenester → tjek AgentAccess (agentaccess.dk) FØRST for API/MCP/automation. Open-source/local-first MCP-stak (FastMCP-TS/Inspector/Playwright-MCP/Crawl4AI/Har2MCP), adgangshierarki og Grundfast-MCP. Brug ved hver integration med dansk tjeneste eller tjeneste uden API.
MCP server "serena" as configured in klh/speedy-claude. Launched with serena start-mcp-server --context claude-code.
★not rated 11 24d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: