visual-result-showcase
Skill7 starsChanged 53 days agoMITView on GitHub
Create blog, README, social, or demo-review visual showcases from completed Roboclaws run artifacts, especially chaptered GIFs/contact sheets for household cleanup runs. Use when asked to turn report output, robot_views, traces, or run_result.json into polished visual result evidence without rerunning the robot task.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- eval-evolutionSkill
- eval-harnessSkill
- household-worldSkill
- raw-fpv-visual-labelerSkill
- report-performance-analysisSkill
- scene-gaussian-map-alignmentSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill when a completed Roboclaws run needs to become a publishable visual artifact: blog GIF, README demo strip, release note …
- Distinctive: line 22
Do not run a new robot task, call a VLM, inspect private manifests, or imply that report-only views were agent inputs.
- Distinctive: line 32
every object cleanup chain, preserving the visible tool order.
- Distinctive: line 35
Use the bundled renderer:
- Distinctive: line 57
Keep claims honest: "Codex agent drives bounded MCP cleanup tools" is fine.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Visual Result Showcase
Use this skill when a completed Roboclaws run needs to become a publishable visual artifact: blog GIF, README demo strip, release note contact sheet, or operator-facing result montage.
Boundary
This is post-run artifact work. By default, use only:
run_result.jsontrace.jsonlagent_view.jsonrobot_views/*- public report images such as
before.png,after.png, and map previews
Do not run a new robot task, call a VLM, inspect private manifests, or imply that report-only views were agent inputs. If a score is shown, label it as post-run evaluation.
Household Cleanup GIF
For cleanup result showcases, prefer the whole-task story:
- task and before state;
- observe sweep progress;
- every object cleanup chain, preserving the visible tool order;
- final state and post-run evaluation.
Use the bundled renderer:
python skills/visual-result-showcase/scripts/render_household_cleanup_showcase.py \
--run-dir output/household/household-world/cleanup/direct-world-public-labels/seed-7 \
--out-dir docs/blog/assets/household-cleanup-showcaseThe script writes:
showcase.gifcontact_sheet.pngframes/*.pngmanifest.json
Visual Rules
- Make FPV the main panel. Prefer
.fpv.bbox.pngwhen available. - Label FPV as the agent-facing view.
- Label chase/RPV and verification/map views as report-only evidence.
- Include an MCP tool trace bar so the viewer sees
observe, navigation,pick,place, receptacle open/close, anddone. - Keep claims honest: "Codex agent drives bounded MCP cleanup tools" is fine; "visual-only", "real robot", or "fully solved cleanup" is not unless the source run proves that exact claim.
- For WeChat/blog publication, keep a GIF plus source frames. Use the contact sheet for quick human review before embedding.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

