An open-source collection of AI agents and skills for software development workflows.
Skill Claude CodeCodex
Analyze a project and generate a Mermaid sequence diagram showing the full data flow from the application layer through any framework/middleware down to Valkey operations. Works for any language or framework.
Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Skill Claude CodeCodex
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
Skill Claude CodeCodex
Production-ready patterns for Valkey GLIDE clients across 6 languages. Activate when generating, reviewing, or debugging Valkey GLIDE code including client creation, batch/pipeline/transaction operations, clustering, authentication, TLS, error handling, and timeout configuration.
Skill Claude CodeCodex
Given a PR link containing a Valkey integration in a project, create a cookbook matching the style of valkey-io/Valkey-Samples (you can find it in /valkey/Valkey-Samples). Builds the cookbook locally in the project directory, verifies it runs, then copies to /valkey/valkey-samples/ and removes the local copy. Use when…
Skill Claude CodeCodex
Use when a developer needs a thorough technical introduction to an unfamiliar local repository, including its architecture, subsystem responsibilities, runtime behavior, verification evidence, security concerns, and operational risks.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Use when refreshing an existing Valkey cookbook from archive/main-pre-reorg to current CONTRIBUTING.md guidance, checking for duplicate or overlapping cookbook PRs, adding runnable validation, or preparing local draft materials for language-specific CI.
Skill Claude CodeCodex
Given a PR link, reviews edlng's review comments, verifies each was addressed in the latest code, and provides a final verdict (APPROVE, REQUEST CHANGES, or COMMENT) with code evidence.
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
Skill Claude CodeCodex
Use when implementing any feature or bugfix, before writing implementation code.
Skill Claude CodeCodex
Test Valkey integration code against a live valkey-bundle container. Starts Valkey from a clean slate, exercises staged/unstaged git changes (cache backend, vector search provider, rate limiter, connection parsing), validates all configurations by tearing down and recreating the container as needed. Use when Valkey…
Skill Claude CodeCodex
Use when the user invokes the harness-native update-sysprompts skill or asks to persist a concise instruction across Kiro, Claude Code, and Codex global context, including commit, test, coding-style, or workflow rules.
Skill Claude CodeCodex
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
Skill Claude CodeCodex
Analyze a repository for Valkey integration opportunities and empirically verify feasibility. Combines static codebase analysis (existing Redis/cache usage, command compatibility, vector search potential) with a live spike against a running Valkey instance to prove the riskiest assumptions before committing to a full…
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Generate a concise, human-sounding PR description from current git changes in a reviewer-first format. Optionally accepts a commit range (e.g. HEAD3) and/or a PR template path. Reads the diff, drafts from the repository PR template (or a structured default), verifies accuracy, then humanizes the output.
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: