docs: animated team peer-review hero SVG in README #222
Conversation
Add docs/_static/hero-team.svg — an animated overview of the h5i team flow: one task fans out to claude and codex in sealed sandboxes, they peer-review each other in a continuous loop (flowing dashes + traveling SMIL particles), a neutral verifier replays and tests every candidate, and the one verified result is merged back into your repo. Replaces the static screenshot_sandbox_h5i_3.png as the README hero image.
Drop the in-figure eyebrow/title/subline (duplicated the README h1 and intro paragraph directly above) and recrop the viewBox so the diagram fills the frame. Picks up the README width 95%->99% tweak.
Increase agent/label/meta/small/stage/chip sizes, widen the verifier card and shift the result block right so the larger text fits without overflow. No canvas height change needed.
Added instructions for monitoring the status and included an image for visual explanation.
🪙 75% AI-authored · 4 files · prompt 30/100
Important 🎯 Goal: Create an animated SVG hero image for README showing the team peer-review loop (claude <-> codex in sandboxes -> user)
💬 The ask
📍 What shipped
Note 🪴 Prompt maturity: 30/100 · developing · 3 prompts scored (100% of AI commits) 📊 heuristic breakdown
Readability (display-only): Flesch 75 · FK grade 7.2 · Gunning Fog 10.3 Offline classical-NLP score — no LLM. Higher = more specific, bounded, and grounded prompting. Tip ✅ Security scan cleanNo credentials leaked in this branch's diff. h5i scanned every added line against the secret rule pack and found nothing to rotate. Note Duplicate-code scan clean — no copy-paste blocks introduced. 🧠 Reasoning by file — 9766 nodes across 6 lanes, latest 24 only%%{init: {"flowchart": {"nodeSpacing": 42, "rankSpacing": 48, "diagramPadding": 14}, "themeVariables": {"fontSize": "18px"}} }%%
flowchart TB
subgraph lane_0["💭 Reasoning · 4 steps"]
direction LR
n_lane_0_0["THINK · Let me build a new, polished animated hero SVG focused on the `team` pee…"]:::t
n_lane_0_1["THINK · Nothing is pushed — let me know if you want `h5i share push` (for the h5…"]:::t
n_lane_0_2["THINK · The descriptive subline (”One task fans out…”) also duplicates the intro…"]:::t
n_lane_0_3["THINK · I'll widen the verifier card and nudge the result block right to keep sp…"]:::t
n_lane_0_0 --> n_lane_0_1
n_lane_0_1 --> n_lane_0_2
n_lane_0_2 --> n_lane_0_3
end
subgraph lane_1["📄 docs/_static/hero-team.svg · 9 ops"]
direction LR
n_lane_1_0["EDIT × 9"]:::a
end
subgraph lane_2["📄 README.md · 3 ops"]
direction LR
n_lane_2_0["READ × 2"]:::o
n_lane_2_1["EDIT"]:::a
n_lane_2_0 --> n_lane_2_1
end
subgraph lane_3["📄 docs/pitch/index.html · 1 op"]
direction LR
n_lane_3_0["EDIT"]:::a
end
subgraph lane_4["📄 docs/_static/h5i-team.svg · 1 op"]
direction LR
n_lane_4_0["READ"]:::o
end
subgraph lane_5["🗂 Other · 6 nodes"]
direction LR
n_lane_5_0["READ · read hero.png"]:::o
n_lane_5_1["READ · read hero2.png"]:::o
n_lane_5_2["READ · read hero3.png"]:::o
n_lane_5_3["READ · read hero4.png"]:::o
n_lane_5_4["READ · read hero5.png"]:::o
n_lane_5_5["READ · read hero6.png"]:::o
n_lane_5_0 --> n_lane_5_1
n_lane_5_1 --> n_lane_5_2
n_lane_5_2 --> n_lane_5_3
n_lane_5_3 --> n_lane_5_4
n_lane_5_4 --> n_lane_5_5
end
classDef o fill:#dbeafe,stroke:#1e3a8a,color:#0b1c4a;
classDef t fill:#fef3c7,stroke:#92400e,color:#3f2d05;
classDef a fill:#dcfce7,stroke:#166534,color:#0a2e16;
classDef n fill:#ede9fe,stroke:#5b21b6,color:#221251;
classDef m fill:#e5e7eb,stroke:#374151,color:#0b0f17;
Note 🪙 Token reduction — 4 captured tool outputs kept out of context: 2666 → 1854 tokens (30% saved, 812 tokens). Full output is recoverable with 📜 Per-commit provenance
|
No description provided.