Productivity & Workflow Agent Skills for Claude Desktop

Bootstrap any repo with a full AI-ready scaffold.

Take a list of projects and their related documentation, and organize them into the SRED format for submission.

Go back through the previous year of work and create a Notion doc that groups relevant links into projects that can then be documented as…

Push or pull changes to the shared shared-config repo.

Compact the session so the next one can continue.

Confirm the work is actually done. Use when you ask whether something is finished. Requires evidence: a command that ran, a page that…

Generate personalized status briefings on demand.

Infer the current Ultra route, baseline gaps, stale evidence, task risk, and installation health from repository files and host manifests.

This skill should be used when the user asks a broad engineering question that could match several areas, asks "which skill covers this"…

Use when drafting the RSS (Robotics: Science and Systems) invited one-page rebuttal — the above-threshold-only response read primarily by…

Use when auditing an RSS (Robotics: Science and Systems) submission for OpenReview readiness — the abstract/paper/supplement deadline…

Use when planning an RSS (Robotics: Science and Systems) campaign end to end — the late-January abstract/paper/supplement cascade, the…

It works alone towards the current objective in check-act cycles, with hard brakes, until the done condition is met.

Run a decision process end-to-end: RAPID/DACI roles, options matrix, decision log, comms.

Author and run declarative YAML workflows on the Marshal fleet - reusable orchestration recipes (fan a goal out across clients, collect…

Turn settled decisions into an implementation plan for requested planning, handoffs, or multi-session work.

Continue working on an OpenSpec change by creating the next artifact.

Make any code/UI change reversibly with a rollback-first checkpoint system.

Protects AI agent sessions from content inspection failures and 400 error loops during external web research on moderated model backends.

Automate Safetyculture tasks via Rube MCP (Composio).

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation.