Productivity & Workflow Agent Skills for Codex CLI

Scan task tracking files for epic completion status and perform hygiene operations (archiving, cleanup, validation)

Preview and summarize epics for high-level review of scope and progress before diving into implementation

Implement tasks from an OpenSpec change.

Ground factual claims and evidence-dependent decisions in inspectable evidence; distinguish verified facts, reported context, inference…

When the user wants to find, size, qualify, time or justify expansion revenue inside customers they already have — for one account, a…

Just say what you spent — your AI logs it, categorizes it, and tracks it against your budget.

Systematic framework for analyzing product documents (PRDs, feature specs, user stories, roadmaps, one-pagers) to identify gaps, generate…

For factoring agreements, framework agreements, receivables purchases, purchase price, and retention of security: defines the standard…

Use when the user wants to add a new feature, capability, or cluster of work to an existing active Mymir project.

Use when a feature specification already exists and the user wants it built: "implement what-to-build.md", "build this feature", "now…

Orchestrates end-to-end coding workflows from test-driven development and commenting to automated PR creation and review cycles.

Use when someone wants a feature, change, or improvement in an existing codebase and what to build is not yet pinned down: a rough idea, a…

Analyzes competitor feature implementations and audits internal product capabilities to determine whether to build, adapt, or skip new…

Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings…

Resolve a single HL7 FHIR JIRA ticket end-to-end.

Partition a backlog (TODOS.md / PROGRESS.md / PRD / pasted requirements / codebase scan) into independent task groups that can run…

Invoke this skill when the user asks to fill in a weekly timesheet — collect git commits and Jira tasks, build a plan, and auto-log 40…

Use to drive consistent forecast methodology, grading, and inspection

Delete a memory from Origin by ID. Destructive and cannot be undone — prefer `/capture` with `supersedes` for corrections. Invoked as…

Give a decisive, project-grounded point of view in the subject's own shape: a graded verdict on an external-adoption question, a holistic…

Derives formal legal consequences, liability types, compensation amounts, and sentencing ranges using a four-layer legal reasoning model…