Run AI coding agents efficiently, and coordinate more than one of them. Zero fluff, zero runtime deps.
Skill Claude CodeCodex
Use when an algorithm is non-trivial enough that getting the logic right matters more than the syntax — concurrency-sensitive code, a non-obvious data-structure choice, or anything where a subtle off-by-one or complexity mistake is expensive to find after implementation. Write the algorithm in language-agnostic…
Skill Claude CodeCodex
Use before any creative or ambiguous request — a new feature, a "can we..." feasibility question, a vague bug report with no clear fix yet — to classify how much process it needs and block implementation until that process is done and approved. Skip once the ask is already concrete and scoped…
Skill Claude CodeCodex
Use when writing or maintaining an OpenAPI/Swagger 3.0 specification for a REST API — new endpoints, request/response schemas, auth schemes, or error responses that need to be documented accurately and stay in sync with the implementation. Skip for internal-only functions/modules with no HTTP surface, and skip for…
Skill Claude CodeCodex
Product management for any project — read-only reporting (/pm:standup, /pm:groom, /pm:plan, /pm:health, /pm:portfolio) plus PM mode, an explicitly-activated execution arm that creates and dispatches work via handoff instead of implementing it directly. Embedded in the agentflare binary, so it's available regardless of…
Skill Claude CodeCodex
Use when a feature request or bug report is vague enough that "what does done look like" isn't obvious yet — turns a fuzzy ask into testable functional/non-functional requirements, constraints, and Gherkin-style acceptance criteria before any design or code starts. Skip for small, already-unambiguous changes, and skip…
Skill Claude CodeCodex
Use when a change is big enough to need a deliberate structural decision first — new service boundaries, a data model that will be expensive to change later, a technology choice, or anything crossing multiple components — and you want the trade-offs and rationale written down, not just the diagram. Skip for changes…
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes — walks through root-cause investigation, pattern comparison, and a single tested hypothesis before any code changes. Skip when there's no failure to explain yet (greenfield feature work) — use algorithm-pseudocode-design or…