[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EBXBX03THA560J49DXTCSX":3,"skill-same:01M7EBXBX03THA560J49DXTCSX":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M7EBXBX03THA560J49DXTCSX","codebase-onboarding",null,"Use when you land in an unfamiliar or inherited codebase and must get productive fast: a breadth-first map of entry points, request flow, module ownership, hidden side effects (cron, webhooks, workers) and churn hotspots, committed as CODEBASE-MAP.md. NOT a deep audit of one module (that is `analyze`) or chasing one failure (that is `debug`).","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fcodebase-onboarding\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codebase-onboarding\ndescription: \"Use when you land in an unfamiliar or inherited codebase and must get productive fast: a breadth-first map of entry points, request flow, module ownership, hidden side effects (cron, webhooks, workers) and churn hotspots, committed as CODEBASE-MAP.md. NOT a deep audit of one module (that is `analyze`) or chasing one failure (that is `debug`).\"\ntags: [onboarding, codebase, code-mapping, legacy-code, architecture, reverse-engineering, hotspots]\nrecommends: [analyze, debug, decision-records, harness, init, knowledge-ops]\norigin: risco\n---\n\n# Codebase onboarding — get oriented fast, leave a map\n\nYou have just landed in a codebase you did not write: a fresh clone, an inherited project, an acquired repo, an abandoned side project someone handed you. The instinct is to start reading files top-to-bottom. Resist it. That is how a week disappears and you still cannot answer \"where does X happen\". This skill runs a disciplined **breadth-first reconnaissance pass** and produces one durable artifact: a map a teammate can trust and you can re-read tomorrow.\n\nThe payoff is measured. Engineers using AI to onboard reach the same milestones roughly **2x faster** — productive in 1–2 weeks instead of 4–6 — and the biggest gains are exactly in *searching for code, decoding undocumented patterns, and tracing data flows* (super-productivity.com, accessed 2026-06-02). That is what the recon pass below targets, in order.\n\n## Lead with the deliverable\n\nBefore you grep a single line, know the target: a single living file, `CODEBASE-MAP.md`, committed at the repo root. You work *backward* from its sections — every recon step fills one. Minimal schema:\n\n```markdown\n# CODEBASE-MAP.md — \u003Crepo name>\n\n## Stack          # languages, framework + versions, package manager, run scripts\n## Entry points   # main \u002F server bootstrap \u002F route registration \u002F CLI commands\n## Request flow   # one real path traced transport -> business logic -> persistence\n## Module ownership   # who owns transport \u002F business logic \u002F persistence \u002F UI\n## Hidden behavior    # cron, webhooks, queue workers, event listeners, env branches\n## Hotspots       # most-churned + most-complex files = highest risk\n## How to run     # the exact commands to boot it and hit one path locally\n```\n\nWhy a file and not a chat answer: a map that lives only in the conversation dies when the session ends, and the next agent re-does the work. The artifact is the point. `verify.sh` checks these sections exist (structure, not content).\n\n## Two operating rules\n\n1. **Breadth before depth.** First pass maps *where things are*, not *how they work*. You are drawing the subway map, not reading every passenger's diary. Depth is `analyze`\u002F`debug` work, on demand, later. — Reading everything is the failure mode onboarding exists to replace.\n2. **Hypothesis before answer.** Spend ~5 minutes forming your own guess (\"auth probably lives in `src\u002Fmiddleware`\"), then grep to confirm or kill it. — Verifying a hypothesis builds the mental model that makes you fast; a handed-to-you answer does not stick (martinfowler.com, Böckeler, accessed 2026-06-02).\n\n## The recon pass — ordered\n\nRun these in order. Each step writes one map section. Stop escalating the moment the section is answerable.\n\n**a. Orient — read the manifest, size the repo.**\nRead the manifest(s) and lockfile, not the README first: `package.json` \u002F `pyproject.toml` \u002F `go.mod` \u002F `Gemfile` \u002F `pom.xml` tell you the real stack, framework version and run scripts; the lockfile tells you what is actually installed. Then size it:\n\n```bash\nscc --by-file --sort lines .   # LOC, complexity, COCOMO estimate per file\n```\n\n`scc` (Sloc Cloc and Code, pure-Go, v3.7.0 Apr 2026) is the fast structural counter of record — materially faster than cloc\u002Ftokei and it reports per-file complexity, which you reuse for hotspots. Why manifest-first: the README describes intent (often stale); the manifest describes reality.\n\n**b. Find the entry points.**\nWhere does execution start? Look for `main`, the server bootstrap, route registration, CLI command definitions. Let the framework's convention guide you (Next.js `app\u002F`\u002F`pages\u002F`, Express `app.use`\u002Frouter mounts, Django `urls.py`, FastAPI `@app`\u002F`APIRouter`, Rails `routes.rb`, Spring `@RestController`). See `references\u002Frecon-playbook.md` for per-ecosystem patterns.\n\n**c. Trace one real request end-to-end.**\nPick a single meaningful path (a login, a checkout, the main CLI command) and follow it: transport (route\u002Fhandler) → business logic → persistence → response. One path traced beats ten skimmed. This is the spine of the map.\n\n**d. Map module ownership.**\nFor the directories `scc` flagged as large, label each: transport, business logic, persistence, UI, shared\u002Futil. You are answering \"if I need to change pricing, which folder do I open\" — the question teammates actually ask.\n\n**e. Hunt hidden behavior.**\nThe bugs live in what runs *without* a request. Grep for cron schedules, webhook receivers, queue\u002Fbackground workers, event listeners and env-driven branches (see the appendix). Why this step is non-negotiable: side effects are invisible in a top-down read and they are where inherited codebases bite.\n\n**f. Rank hotspots.**\nGit churn is the cheapest risk signal — no extra tooling, and high-churn files are a proxy for \"lacks tests\u002Fabstraction\":\n\n```bash\ngit log --format=format: --name-only --since=12.month \\\n  | grep -v '^$' | sort | uniq -c | sort -nr | head -50\n```\n\nThe richer move is **churn × complexity**: the top-right quadrant (changes constantly *and* is hard to read) is your real danger zone (understandlegacycode.com Hotspots, accessed 2026-06-02). Escalate to that — or to a tree-sitter dependency graph — only when grep + churn is not enough: `references\u002Frecon-playbook.md` has the churn×complexity recipe (code-maat) and when codegraph PageRank \u002F FileScopeMCP earn their setup cost.\n\n**g. Confirm hands-on.**\nRun the app, walk one end-user journey, send a real request, watch the logs. Reading alone leaves the map unverified; a single real request validates the whole trace in step c.\n\n## Scope the effort\n\nMatch the pass to the repo. Do not stand up heavy tooling on a small project.\n\n| Repo shape | Map fully | Skip \u002F defer | Escalate to a graph tool? |\n| --- | --- | --- | --- |\n| Tiny (\u003C20 files) | a, b, c, g | churn, ownership table | No — grep is faster than setup |\n| Single-service app | all a–g | — | Only if ownership is unclear after grep |\n| Large monorepo | a, b, then per-package c–f | mapping every package at once | Yes — codegraph PageRank to find the load-bearing packages |\n| Polyglot | a, b, c per language boundary | one unified flow diagram | Yes, if cross-language calls obscure the flow |\n\n## Command appendix\n\nLanguage-tagged, copy-ready. Per-ecosystem depth lives in `references\u002Frecon-playbook.md`.\n\n```bash\n# Size + complexity (reuse the complexity column for hotspots)\nscc --by-file --sort complexity .\n\n# Route registration (adjust per framework)\nrg -n \"app\\.(get|post|put|delete|use)\\(|@app\\.(get|post)|APIRouter|router\\.(get|post)\" --type-add 'web:*.{js,ts,py}' -tweb\n\n# Cron \u002F scheduled jobs\nrg -n \"cron|schedule|@scheduled|setInterval|celery\\.beat|node-cron\" -i\n\n# Webhook receivers\nrg -n \"webhook|\u002Fhooks\u002F|stripe.*signature|x-hub-signature\" -i\n\n# Queue \u002F background workers\nrg -n \"queue|worker|bull|sidekiq|celery|sqs|rabbitmq|kafka|@task\" -i\n\n# Env-driven branches (hidden config-conditional behavior)\nrg -n \"process\\.env\\.|os\\.environ|ENV\\[|getenv\" \n```\n\n## Writing & maintaining the map\n\n- **Commit it.** `CODEBASE-MAP.md` at the repo root, in version control. A map outside the repo rots silently.\n- **Keep it living.** When the recon reveals you guessed wrong, fix the line — the map is the record of what is *true now*, not your first impression.\n- **Link out, do not duplicate.** The map says *what is*. For *why a choice was made*, write an ADR (`..\u002Fdecision-records\u002FSKILL.md`). To scaffold project tooling and a wiki, that is `..\u002Fharness\u002FSKILL.md`. To write the agent-memory `CLAUDE.md`, that is `..\u002Finit\u002FSKILL.md` — onboarding is the broader recon that feeds it. For generic note\u002Fwiki capture, `..\u002Fknowledge-ops\u002FSKILL.md`.\n- **Hand off to depth tools.** Once the map exists, a deep correctness\u002Fsecurity read of one module is `..\u002Fanalyze\u002FSKILL.md`; chasing a specific failure through the system is `..\u002Fdebug\u002FSKILL.md`. Onboarding builds the map you debug *with*.\n\n## Anti-patterns\n\n| Bad | Why it bites | Good |\n| --- | --- | --- |\n| Read every file top-to-bottom | Burns the week; you finish exhausted and still can't trace one request | Breadth-first: map locations first, depth on demand |\n| Trust the README over the code | READMEs drift; the manifest and the routes are the truth | Read manifest + lockfile first, confirm by grep |\n| Map everything at full depth | Analysis paralysis on a monorepo; you map dead modules | Trace one real flow end-to-end; expand only where needed |\n| Skip the run step | An unverified map is a hypothesis, not a map | Boot it, hit one path, watch logs before you trust the trace |\n| Map lives only in chat | Dies with the session; next agent redoes it | Write & commit `CODEBASE-MAP.md` |\n| Guess instead of grep | Confident-wrong is worse than slow-right | Form the hypothesis, then `rg` to confirm or kill it |\n| Stand up a tree-sitter MCP graph on a 5-file repo | Setup costs more than the whole recon | Reserve graph tools for large monorepos; grep + churn first |\n","# Codebase onboarding — get oriented fast, leave a map\n\nYou have just landed in a codebase you did not write: a fresh clone, an inherited project, an acquired repo, an abandoned side project someone handed you. The instinct is to start reading files top-to-bottom. Resist it. That is how a week disappears and you still cannot answer \"where does X happen\". This skill runs a disciplined **breadth-first reconnaissance pass** and produces one durable artifact: a map a teammate can trust and you can re-read tomorrow.\n\nThe payoff is measured. Engineers using AI to onboard reach the same milestones roughly **2x faster** — productive in 1–2 weeks instead of 4–6 — and the biggest gains are exactly in *searching for code, decoding undocumented patterns, and tracing data flows* (super-productivity.com, accessed 2026-06-02). That is what the recon pass below targets, in order.\n\n## Lead with the deliverable\n\nBefore you grep a single line, know the target: a single living file, `CODEBASE-MAP.md`, committed at the repo root. You work *backward* from its sections — every recon step fills one. Minimal schema:\n\n```markdown\n# CODEBASE-MAP.md — \u003Crepo name>\n\n## Stack          # languages, framework + versions, package manager, run scripts\n## Entry points   # main \u002F server bootstrap \u002F route registration \u002F CLI commands\n## Request flow   # one real path traced transport -> business logic -> persistence\n## Module ownership   # who owns transport \u002F business logic \u002F persistence \u002F UI\n## Hidden behavior    # cron, webhooks, queue workers, event listeners, env branches\n## Hotspots       # most-churned + most-complex files = highest risk\n## How to run     # the exact commands to boot it and hit one path locally\n```\n\nWhy a file and not a chat answer: a map that lives only in the conversation dies when the session ends, and the next agent re-does the work. The artifact is the point. `verify.sh` checks these sections exist (structure, not content).\n\n## Two operating rules\n\n1. **Breadth before depth.** First pass maps *where things are*, not *how they work*. You are drawing the subway map, not reading every passenger's diary. Depth is `analyze`\u002F`debug` work, on demand, later. — Reading everything is the failure mode onboarding exists to replace.\n2. **Hypothesis before answer.** Spend ~5 minutes forming your own guess (\"auth probably lives in `src\u002Fmiddleware`\"), then grep to confirm or kill it. — Verifying a hypothesis builds the mental model that makes you fast; a handed-to-you answer does not stick (martinfowler.com, Böckeler, accessed 2026-06-02).\n\n## The recon pass — ordered\n\nRun these in order. Each step writes one map section. Stop escalating the moment the section is answerable.\n\n**a. Orient — read the manifest, size the repo.**\nRead the manifest(s) and lockfile, not the README first: `package.json` \u002F `pyproject.toml` \u002F `go.mod` \u002F `Gemfile` \u002F `pom.xml` tell you the real stack, framework version and run scripts; the lockfile tells you what is actually installed. Then size it:\n\n```bash\nscc --by-file --sort lines .   # LOC, complexity, COCOMO estimate per file\n```\n\n`scc` (Sloc Cloc and Code, pure-Go, v3.7.0 Apr 2026) is the fast structural counter of record — materially faster than cloc\u002Ftokei and it reports per-file complexity, which you reuse for hotspots. Why manifest-first: the README describes intent (often stale); the manifest describes reality.\n\n**b. Find the entry points.**\nWhere does execution start? Look for `main`, the server bootstrap, route registration, CLI command definitions. Let the framework's convention guide you (Next.js `app\u002F`\u002F`pages\u002F`, Express `app.use`\u002Frouter mounts, Django `urls.py`, FastAPI `@app`\u002F`APIRouter`, Rails `routes.rb`, Spring `@RestController`). See `references\u002Frecon-playbook.md` for per-ecosystem patterns.\n\n**c. Trace one real request end-to-end.**\nPick a single meaningful path (a login, a checkout, the main CLI command) and follow it: transport (route\u002Fhandler) → business logic → persistence → response. One path traced beats ten skimmed. This is the spine of the map.\n\n**d. Map module ownership.**\nFor the directories `scc` flagged as large, label each: transport, business logic, persistence, UI, shared\u002Futil. You are answering \"if I need to change pricing, which folder do I open\" — the question teammates actually ask.\n\n**e. Hunt hidden behavior.**\nThe bugs live in what runs *without* a request. Grep for cron schedules, webhook receivers, queue\u002Fbackground workers, event listeners and env-driven branches (see the appendix). Why this step is non-negotiable: side effects are invisible in a top-down read and they are where inherited codebases bite.\n\n**f. Rank hotspots.**\nGit churn is the cheapest risk signal — no extra tooling, and high-churn files are a proxy for \"lacks tests\u002Fabstraction\":\n\n```bash\ngit log --format=format: --name-only --since=12.month \\\n  | grep -v '^$' | sort | uniq -c | sort -nr | head -50\n```\n\nThe richer move is **churn × complexity**: the top-right quadrant (changes constantly *and* is hard to read) is your real danger zone (understandlegacycode.com Hotspots, accessed 2026-06-02). Escalate to that — or to a tree-sitter dependency graph — only when grep + churn is not enough: `references\u002Frecon-playbook.md` has the churn×complexity recipe (code-maat) and when codegraph PageRank \u002F FileScopeMCP earn their setup cost.\n\n**g. Confirm hands-on.**\nRun the app, walk one end-user journey, send a real request, watch the logs. Reading alone leaves the map unverified; a single real request validates the whole trace in step c.\n\n## Scope the effort\n\nMatch the pass to the repo. Do not stand up heavy tooling on a small project.\n\n| Repo shape | Map fully | Skip \u002F defer | Escalate to a graph tool? |\n| --- | --- | --- | --- |\n| Tiny (\u003C20 files) | a, b, c, g | churn, ownership table | No — grep is faster than setup |\n| Single-service app | all a–g | — | Only if ownership is unclear after grep |\n| Large monorepo | a, b, then per-package c–f | mapping every package at once | Yes — codegraph PageRank to find the load-bearing packages |\n| Polyglot | a, b, c per language boundary | one unified flow diagram | Yes, if cross-language calls obscure the flow |\n\n## Command appendix\n\nLanguage-tagged, copy-ready. Per-ecosystem depth lives in `references\u002Frecon-playbook.md`.\n\n```bash\n# Size + complexity (reuse the complexity column for hotspots)\nscc --by-file --sort complexity .\n\n# Route registration (adjust per framework)\nrg -n \"app\\.(get|post|put|delete|use)\\(|@app\\.(get|post)|APIRouter|router\\.(get|post)\" --type-add 'web:*.{js,ts,py}' -tweb\n\n# Cron \u002F scheduled jobs\nrg -n \"cron|schedule|@scheduled|setInterval|celery\\.beat|node-cron\" -i\n\n# Webhook receivers\nrg -n \"webhook|\u002Fhooks\u002F|stripe.*signature|x-hub-signature\" -i\n\n# Queue \u002F background workers\nrg -n \"queue|worker|bull|sidekiq|celery|sqs|rabbitmq|kafka|@task\" -i\n\n# Env-driven branches (hidden config-conditional behavior)\nrg -n \"process\\.env\\.|os\\.environ|ENV\\[|getenv\" \n```\n\n## Writing & maintaining the map\n\n- **Commit it.** `CODEBASE-MAP.md` at the repo root, in version control. A map outside the repo rots silently.\n- **Keep it living.** When the recon reveals you guessed wrong, fix the line — the map is the record of what is *true now*, not your first impression.\n- **Link out, do not duplicate.** The map says *what is*. For *why a choice was made*, write an ADR (`..\u002Fdecision-records\u002FSKILL.md`). To scaffold project tooling and a wiki, that is `..\u002Fharness\u002FSKILL.md`. To write the agent-memory `CLAUDE.md`, that is `..\u002Finit\u002FSKILL.md` — onboarding is the broader recon that feeds it. For generic note\u002Fwiki capture, `..\u002Fknowledge-ops\u002FSKILL.md`.\n- **Hand off to depth tools.** Once the map exists, a deep correctness\u002Fsecurity read of one module is `..\u002Fanalyze\u002FSKILL.md`; chasing a specific failure through the system is `..\u002Fdebug\u002FSKILL.md`. Onboarding builds the map you debug *with*.\n\n## Anti-patterns\n\n| Bad | Why it bites | Good |\n| --- | --- | --- |\n| Read every file top-to-bottom | Burns the week; you finish exhausted and still can't trace one request | Breadth-first: map locations first, depth on demand |\n| Trust the README over the code | READMEs drift; the manifest and the routes are the truth | Read manifest + lockfile first, confirm by grep |\n| Map everything at full depth | Analysis paralysis on a monorepo; you map dead modules | Trace one real flow end-to-end; expand only where needed |\n| Skip the run step | An unverified map is a hypothesis, not a map | Boot it, hit one path, watch logs before you trust the trace |\n| Map lives only in chat | Dies with the session; next agent redoes it | Write & commit `CODEBASE-MAP.md` |\n| Guess instead of grep | Confident-wrong is worse than slow-right | Form the hypothesis, then `rg` to confirm or kill it |\n| Stand up a tree-sitter MCP graph on a 5-file repo | Setup costs more than the whole recon | Reserve graph tools for large monorepos; grep + churn first |\n",{"name":5,"tags":24,"origin":32,"recommends":33,"description":7},[25,26,27,28,29,30,31],"onboarding","codebase","code-mapping","legacy-code","architecture","reverse-engineering","hotspots","risco",[34,35,36,37,38,39],"analyze","debug","decision-records","harness","init","knowledge-ops","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","03-逆向工程\u002Fcodebase-onboarding",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill codebase-onboarding",{"tool":54,"command":55},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill codebase-onboarding",{"tool":57,"command":58},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill codebase-onboarding","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fcodebase-onboarding\u002FSKILL.md",true,[62,68,72],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"evals\u002Fcases.yaml","REFERENCE","参考文档",4469,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fcodebase-onboarding\u002Fevals\u002Fcases.yaml",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"evals\u002FREADME.md",1030,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fcodebase-onboarding\u002Fevals\u002FREADME.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Frecon-playbook.md",4490,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fcodebase-onboarding\u002Freferences\u002Frecon-playbook.md",[77,85,90,97,104,111],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":84},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":86,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":84},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":84},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":84},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":84},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":84},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]