productivity▌

AI-assisted automation for GitHub workflows including PR reviews, issue triage, CI/CD integration, and Git operations. \n \n Automated PR reviews with diff analysis, issue detection, and formatted feedback comments \n Issue triage with AI classification, auto-labeling, severity assessment, and stale issue management \n Smart test selection and deployment validation based on changed files and risk analysis \n Git operations including automated rebasing, conflict resolution, cherry-pick assistance

Automated Windows Flutter development environment setup with platform-specific toolchain configuration. \n \n Configures Flutter SDK paths, Visual Studio C++ toolchain installation, and platform-specific settings via interactive prompts for Windows Desktop, Android, or both targets \n Handles Android Studio setup, device/emulator configuration, and USB driver installation when Android is selected \n Generates self-signed MSIX certificates using OpenSSL for local Windows app packaging and deploym

Debug and fix failing GitHub Actions checks in pull requests using gh CLI inspection and log analysis. \n \n Inspects PR checks via GitHub CLI, fetches GitHub Actions logs, and summarizes failure context with actionable log snippets \n Requires prior gh authentication with repo and workflow scopes; verifies status before proceeding \n Drafts a fix plan (using create-plan skill if available, otherwise inline) and implements only after explicit user approval \n Treats external CI providers (Buildk

Framework-based assessment of product-market fit using signals from 46 product leaders. \n \n Apply the Sean Ellis \"very disappointed\" survey as a leading PMF indicator, targeting 40% threshold before long-term retention data is available \n Diagnose stage through retention curves, reference customer counts, and customer pull signals; distinguish between vanity metrics and genuine PMF evidence \n Recognize PMF across four levels (nascent to extreme) with segment-specific fit; understand that P

Local markdown search engine supporting keyword, semantic, and hypothetical-document queries across indexed collections. \n \n Three query types: lex (BM25 keyword matching), vec (semantic/natural language), and hyde (hypothetical document answers) with optional auto-expansion and intent-based disambiguation \n Accessible via MCP tools ( query , get , multi_get ), CLI commands, and HTTP API on port 8181 \n Supports collection filtering, phrase matching, term exclusion, and result reranking via r

Help users work with Worktrunk, a CLI tool for managing git worktrees.

Frameworks and principles for clearer, more persuasive business writing drawn from 38 product leaders. \n \n Applies the pyramid principle: lead with your conclusion, then support it, rather than building up to an answer \n Emphasizes cutting preamble and unnecessary context to start at the point of highest relevance or tension \n Guides users to test clarity by ensuring someone unfamiliar with the topic could understand the core message \n Covers recurring mistakes: burying conclusions, over-re

Extract and manage error codes for React applications. \n \n Automatically extracts error messages from React source code and assigns unique error codes to new messages \n Detects \"unknown error code\" warnings and flags messages that need code assignment \n Validates that error codes remain synchronized with the current codebase through a simple yarn command \n

Structured legal risk assessment using severity-by-likelihood matrix with escalation guidance. \n \n Evaluates risks across two dimensions (severity 1–5 and likelihood 1–5) to calculate a risk score determining classification as low (green), medium (yellow), high (orange), or critical (red) \n Provides escalation criteria and recommended actions for each risk level, from acceptance and monitoring for low-risk items to immediate senior counsel and outside counsel engagement for critical risks \n

Captures learnings, errors, and corrections to enable continuous improvement across agent tasks. \n \n Logs failures, user corrections, knowledge gaps, and API errors to structured markdown files ( .learnings/ERRORS.md , LEARNINGS.md , FEATURE_REQUESTS.md ) with consistent ID, priority, and metadata \n Supports promotion of broadly applicable learnings to project memory files ( CLAUDE.md , AGENTS.md , .github/copilot-instructions.md ) to prevent recurring mistakes \n Includes recurring pattern d