Loading...
Loading...
Found 55 Skills
The clhbid house rules. Use when writing, testing or reviewing code in a clhbid repo.
Read and set work state on the CLHbid Delivery board — the delivery language, issues via gh, the Status field, the board query recipes, cycles, epics, labels, the commit convention and the decomposition rules. Use for any GitHub issue or project-board operation in a clhbid repo, and for what a cycle, epic or slipped issue means.
Mentor a reviewer through a pull request step by step, teaching the code as it goes, and post the agreed findings as one GitHub review in their name.
Sweep flagged Outlook threads, or threads named by subject, into GitHub issues or comments.
Use this skill whenever the user wants to work with the Loops CLI from the terminal. This includes installing or updating the CLI, authenticating, storing and selecting API keys, validating credentials, and running commands for contacts, contact properties, lists, events, transactional email, campaigns, email messages, themes, and components. Trigger on phrases like "Loops CLI", "loops auth login", "loops campaigns create", "loops email-messages update", "loops themes list", "loops components get", "loops contacts create", "loops events send", "loops transactional send", "loops api-key", "loops agent-context", "brew install loops-so/tap/loops", or any time the user wants to use Loops from the shell instead of application code.
You MUST use this when drafting, rewriting, shortening, tightening, reviewing, or explaining edits to prose in English or Ukrainian for a particular reader - docs, READMEs, PR descriptions and review replies, chat messages, emails, articles, reports, and product copy - including a single paragraph, email, or reply the user pastes, requests to make text clearer, shorter, less generic, less AI-sounding, or less bureaucratic, and rewriting a draft to match a sample of the author's writing. Dash policy belongs to dashfix, negative-parallelism audits to negafix, deciding whether a review finding is valid to review-resolution, agent instruction files to maintaining-agent-context, and interface copy written while designing a UI to frontend-crafting. Not for translation.
You MUST use this when deciding whether a recurring workflow needs a reusable agent skill, or when designing, creating, evaluating, improving, splitting, merging, or retiring skills. Covers trigger boundaries, architecture, behavior contracts, and effectiveness evaluation. Not for repository agent instruction maintenance (maintaining-agent-context), settled implementation planning (plan-crafting), or code behavior fixes (tdd).
Execute the implementation planning workflow and generate design artifacts using the plan template. Trigger phrase: "speckit plan".
Write, audit, and improve agent context files (AGENTS.md, CLAUDE.md) for AI coding agents. Use when creating or improving agent context for a codebase.
Enables autonomous context management for codebases through claude.md files. Use when creating, maintaining, or synchronizing AI agent context. Provides tools and workflows for monitoring context health, detecting staleness, and updating intelligently. Helps Claude work proactively as a context manager.
Never Use TaskOutput
Set up and manage a Memory Bank system for cross-session context continuity across AI coding agents. Use when the user mentions 'memory bank' with any action intent — setup, install, initialize, init, update, refresh, sync, status, check, read, show, review, display, or equivalents in any language (e.g. Turkish: kur, kurulum, güncelle, durumu, oku; German: einrichten, aktualisieren; Spanish: configurar, actualizar; French: installer, mettre à jour). Supports Claude Code, Cursor, Windsurf, Cline, GitHub Copilot, Roo Code, Aider, Antigravity, and OpenAI Codex.