Agent building

Run a detailed, adversarial multi-agent review of an implementation plan — a GitHub PR, a branch, or a planning document — against the baseline spec, ADR, or…

Babysit a GitHub pull request through CI and review closure.

Grade installed agent skills by scoring real local coding-agent sessions (normalized with a bundled Letta trajectory pipeline) against efficiency and…

Diagnose where an AI coding agent's tokens go over the last 7 days and produce a standard summary with ranked optimisation findings.

Generate PPT/slides with Felo PPT Task API in Claude Code.

Use this skill when users want to generate UI mockups, landing pages, wireframes, design concepts, marketing sections, or page prototypes from a prompt and…

Plan implementation as one epic plus concrete child issues, with review, verification, local mode, resource handoff, UI prototyping (-pr runs a rough-UI…

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.

Build the standardized prompt for a fresh reviewer subagent that evaluates implemented work against its spec without access to the implementation conversation.

Initialize an AI-native development workspace with spec-driven workflow infrastructure.

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.

One-click contribution flow for Open Design (nexu-io/open-design) — even for non-coders.

Review coding-agent plans, replies, diffs, prototypes, or pull requests in a terminal Thread and return human comments as a Message.

(💛) Create and manage AI agents using Google's Agent Development Kit (ADK) for Python.

Pass the baton with a deterministic ACTIVE_CONTEXT.md snapshot so fresh context picks up the work.

**REFRESH SKILL** — Keep `tools/inventory.yaml` (the workspace cross-runtime tools inventory) accurate and up to date, grounded in the latest GitHub Copilot…

Post-build quality review that asks whether finished work is good — not just done, correct or free of slop — and returns a lettered crit sheet of pinned…

Emacs daemon — org manipulation, denote notes, citar bibliography, org-agenda, arbitrary elisp.

Create or update a skill so it encodes judgment, not just knowledge — decision trees, do/don't pairs, on-demand references, a check script with tests, and a…

Use when installing, resuming or repairing a repository's Docker Compose Hermes Agent, including a silent bot, stopped gateway, pending activation, or…

Pick up and execute one task from a Light-Kanban board, then return it for human confirmation.

Design and initialize a maintainable knowledge base through a knowledge-base-specific interview.

Execute one bounded, already-decided work item — code, document, configuration, research artifact, Skill, or generic project task — by inspecting relevant…

Session retrospective: evidence-cited, severity-ranked findings about the agent's environment, then one user-approved fix — a guard or a rerun-gated experiment.