An open-source collection of AI agents and skills for software development workflows.
Skill Claude CodeCodex
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Skill Claude CodeCodex
Research any topic and produce a structured crash course saved to Obsidian. Takes a topic as input, dispatches a researcher subagent with a bounded effort budget, optionally validates findings, formats output as a consistent crash course document, saves to the Obsidian vault, and outputs in chat. Use when asked to…
Skill Claude CodeCodex
Use when the user wants to create a new skill for their AI agents.
Skill Claude CodeCodex
Reads today's AI journal entry from Obsidian, appends a concise daily log entry to the current month's Notes file, and updates evidence and statuses in goals/roles. Use when asked to log today, write a daily log, update the monthly notes, or record career-goal evidence.
Skill Claude CodeCodex
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
Skill Claude CodeCodex
Use when you have a written implementation plan to execute in a separate session with review checkpoints.
Skill Claude CodeCodex
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
Skill Claude CodeCodex
Implement a Jira task end-to-end — fetches requirements, scans the codebase, plans with Opus, runs an Opus advisor loop over Sonnet's approach for medium-complexity subtasks before any code is written, implements with Sonnet (delegating low-complexity subtasks to Haiku), runs tests with a fix loop, then runs a merged…
Skill Claude CodeCodex
Single-command entry point that takes a plain-text task description and runs plan → advisor loop → implement → test → review using existing agents. Use when given a task description without a Jira ticket. Do NOT use for tasks that have a Jira ticket (use implement-jira), for quick one-file fixes, or when a plan…
Skill Claude CodeCodex
Run a parallel multi-discipline review across codebase alignment, correctness, security, testability, and Valkey GLIDE using dedicated sub-agents (code-reviewer, security-reviewer, tester, glide-code-reviewer). Codebase alignment is the primary lens. Findings are merged and validated by an Opus validator. Use when a…
Skill Claude CodeCodex
Humanize PR review comments to match the author's terse, direct code review voice. Strips AI-isms and rewrites comments to sound like a real engineer: short imperatives, parenthetical precision, "nit" prefix for minor things, "we should" for collaborative framing, questions to verify rather than assert, links instead…
Skill Claude CodeCodex
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
Skill Claude CodeCodex
Self-review uncommitted or unpushed work before opening a PR. Multi-phase review with Jira requirements, Valkey caching, a single Sonnet reviewer, an Opus validator skeptic pass, and auto-fix offer. Pass a branch name to review vs main, a Jira key to use as requirements source, or leave empty to review staged+unstaged…
Skill Claude CodeCodex
Senior-grade PR review for cookbook PRs. Same as review-pr but adds two cookbook-specific checks: (1) code snippets call project functions directly rather than simulating Valkey internals, and (2) valkey/valkey-bundle version tags are verified against Docker Hub.
Skill Claude CodeCodex
Senior-grade PR review against the linked Jira ticket and existing codebase. Parallel Sonnet reviewers per discipline, findings merged and validated by a single Opus validator pass. Output is local-only — printed in chat and saved to Obsidian, never posted to GitHub.
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks in the current session.
Skill Claude CodeCodex
Use when the user wants to update or modify an existing agent definition for their AI agents.
Skill Claude CodeCodex
Use when the user wants to update or modify an existing skill for their AI agents.
Skill Claude CodeCodex
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions.
Skill Claude CodeCodex
Given a Jira issue key, fetch the issue, research the topic with a research subagent, and draft a humanized technical narrative. Saves to /Documents/work/narratives/ and outputs in chat. Use when asked to write a narrative, technical assessment, or compatibility analysis for a Jira ticket. Do NOT use for PR…
Skill Claude CodeCodex
Post inline PR review comments from an Obsidian review note as a pending review. Filters out non-actionable findings, presents each remaining one for approval, then posts approved comments as a pending GitHub review (visible only to you until manually submitted).
Skill Claude CodeCodex
Use when you have a spec or requirements for a multi-step task, before touching code.
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
Skill Claude CodeCodex
Reasoning framework for systematic code review. Provides lenses (correctness, security, design fit, testability), self-challenge rubrics, and severity differentiation. Use as the reasoning frame when a reviewer subagent applies multi-lens analysis to a diff or PR. Reports only findings affecting correctness or stated…