with one click
agent-skills
agent-skills contains 10 collected skills from OilProducts, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
End-to-end workflow for creating original children's books (picture books, early readers, chapter books) including brief, outline, page-by-page plan, manuscript drafting, revision checklists, and illustration/art direction prompts. Use when a user asks for help writing, outlining, revising, or planning a children's book; creating page breakdowns/spreads; generating illustration prompts; or scaffolding a book project folder with structured files.
Unified ComfyUI skill for direct API workflow runs and RenderSpec-based multi-page pipeline phases (draft/refine/inpaint/upscale_print) with reproducibility artifacts. Use for both ad-hoc workflow execution and full storybook/page production loops.
Apply final governance and release-gate checks to a judged change set by reading `handoff.json`, `verdict.json`, optional eval evidence, and emitting machine-readable `audit.json` with `gate` status. Use when implementation already has a judge verdict and a separate auditor must decide landability (`pass`, `fail`, or `needs-human`) without modifying source files.
Implement a scoped software task by editing code, running targeted smoke checks, and producing machine-readable handoff artifacts (`patch.diff` and `handoff.json`) for downstream evaluation. Use when a user or orchestrator asks to implement/build/fix a task card and hand work to a separate judge; do not use this skill to grade final correctness or make merge decisions.
Evaluate a proposed implementation patch and handoff artifact against task scope and verification checks, then produce a machine-readable `verdict.json`. Use when a doer has delivered `patch.diff` and `handoff.json` and a separate judging role must accept, reject, or escalate without editing source files.
Orchestrate separated doer-judge-auditor software development loops with git worktrees, codex exec runs, and machine-readable handoff/verdict/audit artifacts. Use when a user asks to implement and verify iteratively with strict role separation, including optional governance gating before final acceptance.
Use for SSH and remote shell tasks through the shell-only ssh-ops wrappers (`scripts/ssh_ops.sh`). Supports ad-hoc host/user/auth, command execution, guarded PTY workflows, scp copy, credentials, and transcript-aware troubleshooting.
Add and validate BRP hooks in Bevy projects so BRP consumers (especially bevy-eyes-on) can drive deterministic state transitions and capture reliable screenshots. Use when a task requires reproducible camera/player pose, frame-based stabilization, state probes, deterministic screenshots, or explicit capability reporting for Bevy apps.
Capture Bevy visuals with BRP state-gated scenarios first, and timed screenshots only as fallback. Use when a task needs reliable screenshots of specific game states.
Design and refine web UI interfaces with deliberate visual direction, reusable design-system decisions, and consistency checks for product UIs (dashboards, apps, tools, and admin panels). Use when a user asks to create, redesign, critique, or standardize web pages/components; establish visual tokens and patterns; extract a system from existing code; or audit design drift in implemented UI files.