Bevy Eyes-On

bevy-eyes-on

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.

OilProducts/agent-skills·0installs0stars

SKILL.md

Full skill instructions

Bevy Eyes-On

Use a minimal visual-check workflow for any Bevy app.

Default to BRP state-gated capture. Use timed capture only when BRP hooks are unavailable.

1) BRP State-Gated Screenshot (Primary)

bash /Users/chris/.codex/skills/bevy-eyes-on/scripts/capture_after_brp_sequence.sh \
  --requests-jsonl /path/to/scenario.jsonl \
  --brp-url http://127.0.0.1:15702 \
  --settle-ms 250 \
  --app "<AppName>"

Use for screenshots of gameplay/submenus/precise states.

scenario.jsonl is one JSON object per line:

action call: raw BRP body, or {"body": <request>, "wait_ms": <n>}
state probe with gate: {"probe": <request>, "until": {"path": "result.menu", "equals": "settings", "timeout_ms": 5000, "interval_ms": 100}}
until supports exactly one matcher: equals or in.
path uses dot lookup through objects/lists (list index by numeric segment, e.g. result.items.0.id).

Example:

{"body":{"method":"open_pause_menu","params":{}},"wait_ms":120}
{"probe":{"method":"ui_state","params":{}},"until":{"path":"result.current_menu","equals":"pause","timeout_ms":4000,"interval_ms":100}}
{"body":{"method":"open_settings","params":{}}}
{"probe":{"method":"ui_state","params":{}},"until":{"path":"result.current_menu","equals":"settings","timeout_ms":4000,"interval_ms":100}}

If BRP hooks are missing, use $bevy-brp-instrumentation.

2) Timed Screenshot (Fallback)

bash /Users/chris/.codex/skills/bevy-eyes-on/scripts/capture_after_delay.sh \
  --delay-seconds 3 \
  --app "<AppName>"

Use only for non-specific capture when state-driven BRP is unavailable.

Behavior

Reuse a running app by default.
Prefer state-driven BRP scenarios; do not rely on fixed sleeps for state transitions.
Targeted capture once (--app or --window-id), then one full-display fallback.
No loops, no heavyweight run artifacts.

Output

Print one absolute screenshot path on success.
Exit non-zero with a short error on failure.

Run --help on either script for full flags.

Install skill

Copy and run in your terminal

npx -y skills add https://github.com/OilProducts/agent-skills --skill bevy-eyes-on

View on GitHub

bevy-eyes-on/SKILL.md

judge-evaluate
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 sour...
0 installs
doer-implement
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;...
0 installs
loop-orchestrator
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 ac...
0 installs
bevy-brp-instrumentation
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 expli...
0 installs

More skills from OilProducts

OilProducts/agent-skills

auditor-gate

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 landabilit...

0 0

View

OilProducts/agent-skills

comfyui-image-gen

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.

0 0

View

OilProducts/agent-skills

childrens-book-creator

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 pl...

0 0

View

OilProducts/agent-skills

web-ui-design

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 tok...

0 0

View

OilProducts/agent-skills

ssh-ops

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.

0 0

View