[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F3S6KC61TK5H6TYDBC94YW":3,"skill-same:01M7F3S6KC61TK5H6TYDBC94YW":46},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7F3S6KC61TK5H6TYDBC94YW","image_snapshot",null,"LakoMoor\u002FopenTPU-tangnano20k","LakoMoor","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F44299427?v=4","01M7F3RNYJKP4S25B8Y5MMKVJM","Nikolay","01M7F3RNZ9JVRHWGAYGSR7W449",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FLakoMoor\u002FopenTPU-tangnano20k\u002Fblob\u002Fmain\u002Fasic\u002Fnangate45\u002Fopenlayout\u002Fskills\u002Fskills_Nangate45\u002Fimage_snapshot\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"# Skill: Whole-die-with-pins image snapshot\n\nRender a PNG that shows the **entire die plus the top-level IO pins**, so a\nchecker (or human) can see the macro placement *and* which die edges the pins\nsit on. This is exactly what the agent flow saves at every stage; use the\nstandalone tool to capture it on demand from any checkpoint.\n\n## What \"whole die with pins\" means\n\nThe saved area is the **die box**, expanded outward by a small `margin` so the\nboundary pins are not clipped, and (if enabled) the pin boxes are redrawn on top\nbecause OpenROAD rasterizes thin pins to near-invisibility at the die zoom.\n\nSettings live in `config_macro.yaml`:\n\n```yaml\nimage:\n  save_width: 1024     # save_image -width (px); height keeps the layout aspect\n  margin: 0.03         # fractional pad around die\u002Fpins (0.03 = 3% of the larger side)\n  pin_overlay: true    # redraw bterm boxes over the PNG so pins stay visible\n```\n\n## The code path (flow)\n\n1. `macroflow\u002Frecipes.py` `DIE_CORE` + `PIN_COORDS` query the die box and every\n   bterm pin box from OpenROAD.\n2. `macroflow\u002Fcontext.py` `FlowState.image_area(margin)` unions the die (+ any\n   out-of-die pin boxes) and pads by `margin`.\n3. `macroflow\u002Fopenroad.py` `ORSession.save_image()` emits\n   `save_image -area {x0 y0 x1 y1} -width 1024 image.png`.\n4. If `pin_overlay: true`, `macroflow\u002Fcontext.py` `draw_pin_overlay()` draws the\n   pin boxes on top of the OpenROAD PNG.\n\nFor **bp_fe** (`DIE_AREA 0 0 800 600`, `margin 0.03`) the area becomes\n`-24 -24 824 624`, so the manual OpenROAD command is:\n\n```tcl\nsave_image -area {-24 -24 824 624} -width 1024 whole_die_with_pins.png\n```\n\n`margin` is a fraction of the larger die side: `pad = max(w, h) * margin`,\nso `800 * 0.03 = 24`.\n\n## Standalone tool: `save_die_image.py`\n\nReuses the same pipeline (`load_image_settings`, `DIE_CORE`\u002F`PIN_COORDS`,\n`FlowState.image_area`, `draw_pin_overlay`), so a manual capture is identical to\nthe flow's snapshots. Defaults read from `config_macro.yaml`.\n\n```bash\nconda activate coder\n\n# From a checkpoint ODB (read_db restores tech + LEF + placement):\npython save_die_image.py \\\n    --odb work\u002F\u003Crun>\u002Fsaves_db\u002Ffloorplan.odb \\\n    -o whole_die_with_pins.png\n\n# From a DEF (reads the dataset's lef\u002F*.lef, tech LEF first, then the DEF):\npython save_die_image.py \\\n    --data-dir Benchmark\u002FPlaceReasoner-Bench\u002Fbp_fe \\\n    --def def\u002Fpre_place.def \\\n    -o whole_die_with_pins.png\n```\n\nUseful overrides: `--width 2048`, `--margin 0.05`, `--no-pins` (skip the\noverlay), `--pins` (force it on). The tool prints the die\u002Fcore\u002Fpin counts and\nthe exact `save_image` command it emits.\n\n## Notes\n\n- ODB mode is preferred: a single `read_db` restores tech + LEF + placement.\n- DEF mode needs the LEFs; it globs `lef\u002F*.lef` and loads any file whose name\n  contains `tech` first.\n- The session runs headless (`QT_QPA_PLATFORM=minimal`); no X server needed.\n",{},"main","7a3dd79ef4c19a37095c8bba148a7ca6c58f953c","asic\u002Fnangate45\u002Fopenlayout\u002Fskills\u002Fskills_Nangate45\u002Fimage_snapshot",0,"https:\u002F\u002Fgithub.com\u002FLakoMoor\u002FopenTPU-tangnano20k","https:\u002F\u002Flakomoor.github.io\u002FopenTPU-tangnano20k\u002F","https:\u002F\u002Fgithub.com\u002FLakoMoor","lakomoor.com","i'm the bird of hermes | ML\u002FDL Research Engineer","2026-10-26 00:35:17",{"source":7,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add LakoMoor\u002FopenTPU-tangnano20k --skill image_snapshot",{"tool":38,"command":39},"bunx","bunx skills add LakoMoor\u002FopenTPU-tangnano20k --skill image_snapshot",{"tool":41,"command":42},"pnpm","pnpm dlx skills add LakoMoor\u002FopenTPU-tangnano20k --skill image_snapshot","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLakoMoor\u002FopenTPU-tangnano20k\u002Fblob\u002Fmain\u002Fasic\u002Fnangate45\u002Fopenlayout\u002Fskills\u002Fskills_Nangate45\u002Fimage_snapshot\u002FSKILL.md",true,[],[47,54,60,66,72,78],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M7F3S9GT8DQHJXQC88PQAEMZ","openroad-image-snapshot","Whole-die layout snapshot for any checkpoint: the executable template reads an ODB, expands the die box by a margin so boundary pins stay visible, and saves a PNG. The Worker runs it after every stage; it can also be run standalone on any saved checkpoint.","https:\u002F\u002Fgithub.com\u002FLakoMoor\u002FopenTPU-tangnano20k\u002Fblob\u002Fmain\u002Fasic\u002Fnangate45\u002Fopenlayout\u002Fskills\u002Fskills_openroad_flow\u002Fimage_snapshot\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M7F3S87AJJ70XA5TZPVGBQJN","macro_pin_side","https:\u002F\u002Fgithub.com\u002FLakoMoor\u002FopenTPU-tangnano20k\u002Fblob\u002Fmain\u002Fasic\u002Fnangate45\u002Fopenlayout\u002Fskills\u002Fskills_Nangate45\u002Fmacro_pin_side\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7F3S5EP83V3ATJHP5B5B9WM","get_macro_current_location","https:\u002F\u002Fgithub.com\u002FLakoMoor\u002FopenTPU-tangnano20k\u002Fblob\u002Fmain\u002Fasic\u002Fnangate45\u002Fopenlayout\u002Fskills\u002Fskills_Nangate45\u002Fget_macro_current_location\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7F3S4CPDCB3SMJSKJMRCXMC","get_die_core_info","https:\u002F\u002Fgithub.com\u002FLakoMoor\u002FopenTPU-tangnano20k\u002Fblob\u002Fmain\u002Fasic\u002Fnangate45\u002Fopenlayout\u002Fskills\u002Fskills_Nangate45\u002Fget_die_core_info\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M7F3S2R47TSYTJ41CW3P67JN","5.optimizer","https:\u002F\u002Fgithub.com\u002FLakoMoor\u002FopenTPU-tangnano20k\u002Fblob\u002Fmain\u002Fasic\u002Fnangate45\u002Fopenlayout\u002Fskills\u002Fskills_Nangate45\u002F5.optimizer\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M7F3RZ147AKZF57HHGRJ66WF","post-route-timing-check","Check post-route static timing (TNS\u002FWNS) in OpenROAD to decide whether a macro placement exploration iteration is done. Use this skill whenever the user is running macro placement exploration, sweeping floorplans, or asking whether a placement run is \"good enough to stop\" — anytime post-route timing in OpenROAD needs to be read and compared against a goal, even if the user doesn't explicitly say \"TNS\" or \"WNS\".","https:\u002F\u002Fgithub.com\u002FLakoMoor\u002FopenTPU-tangnano20k\u002Fblob\u002Fmain\u002Fasic\u002Fnangate45\u002Fopenlayout\u002Fskills\u002Fskills_Nangate45\u002F4.PPA_checker\u002FSKILL.md",[],[]]