[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ARYS9JG64RMDXP5EXN5ZFC":3,"skill-same:01M7ARYS9JG64RMDXP5EXN5ZFC":48},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7ARYS9JG64RMDXP5EXN5ZFC","robotics-safety-standards-and-deployment",null,"Use when a robot has real-world consequences: real-time and safety-critical engineering, testing, debugging and field deployment, functional safety and standards including the ISO 10218:2025 revision and the humanoid gap, and the aerospace flight-software practices at the far end of the rigour spectrum including DO-178C, formal methods and redundancy.","the-vibey-project\u002Fvibey","the-vibey-project","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F329298758?v=4","01M7AJHGZ9722CTJ4JNQZVRH0Q","the vibey project","01M7AJHGZVMG2K7TGXQ6XFHVG3",5,"MIT","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Frobotics-software\u002Fskills\u002Frobotics-safety-standards-and-deployment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: robotics-safety-standards-and-deployment\ndescription: \"Use when a robot has real-world consequences: real-time and safety-critical engineering, testing, debugging and field deployment, functional safety and standards including the ISO 10218:2025 revision and the humanoid gap, and the aerospace flight-software practices at the far end of the rigour spectrum including DO-178C, formal methods and redundancy.\"\n---\n\n# Robotics Software: Real-Time and Safety-Critical Engineering, Testing, Standards, and Aerospace\n\n> **Part 4 of 5** of the *Robotics Software* reference (plugin `robotics-software`), covering §11–§14. Sibling skills: `robotics-stack-ros2-and-perception` (§0–§4), `robotics-planning-control-and-manipulation` (§5–§7), `robotics-learning-simulation-and-fleets` (§8–§10), `robotics-reference` (§15–§20). Section numbers are shared across the set; a reference written as §N → `skill` points into that sibling skill.\n>\n> **Currency:** Verified August 2026. See §17 → `robotics-reference` for the currency snapshot and what goes stale first.\n\n> **How to read this.** Reference for engineers building robots that operate in the\n> physical world with real consequences — deliberately distinct from a hobbyist kit\n> reference. Three markers:\n> - **[DURABLE]** — control theory, estimation, architecture, and safety discipline.\n>   Most of this document.\n> - **[VERSIONED]** — frameworks, models, standards, tooling.\n> - **[CONTESTED]** — genuine and active disagreement, of which this field currently has\n>   a lot.\n>\n> **⚠️ GOTCHA** boxes mark the failures that damage hardware, or people.\n>\n> **The three framings that organize everything below:**\n> 1. **Physics doesn't have an undo button.** A web service that fails returns a 500;\n>    a robot that fails puts mass through space. **This single asymmetry justifies every\n>    piece of apparently excessive rigour below** — the redundancy, the state machines,\n>    the simulation, the safety cases (§11, §13).\n> 2. **⚠️ Robotics is an integration discipline, and the integration is where it fails.**\n>    Perception, estimation, planning, and control each work in isolation and break at\n>    the seams — timing, coordinate frames, latency, and units. **The classic robotics bug\n>    is not a bad algorithm; it's a transform published 40ms late** (§3.4 → `robotics-stack-ros2-and-perception`, §12).\n> 3. **The field is in the middle of a genuine methodological argument** between\n>    classical model-based robotics and learned end-to-end policies (§8 → `robotics-learning-simulation-and-fleets`, §16.1 → `robotics-reference`).\n>    **Neither side has won, production systems are overwhelmingly hybrid, and anyone\n>    telling you the argument is settled is selling something.**\n\n---\n\n## §11. Real-Time and Safety-Critical Engineering\n\n**[DURABLE] \"Real-time\" means deterministic, not fast.** A system that responds in 10ms\nevery single time is real-time; one that averages 1ms and occasionally takes 100ms is not.\n**Hard real-time** means a missed deadline is a system failure.\n\n**How you actually get it**: **PREEMPT_RT** (mainlined into Linux, and the common\nfoundation), a genuine **RTOS** (QNX, VxWorks, Zephyr, FreeRTOS) for the hard layers,\n**⚠️ CPU isolation and shielding** (`isolcpus`, IRQ affinity) so your control thread owns a\ncore, **memory locking** (`mlockall`) and **no allocation in the control loop**,\n**priority inheritance** on any shared mutex, and **⚠️ lock-free structures for\nproducer-consumer across priority levels.**\n\n> **⚠️ GOTCHA — the things that silently destroy determinism:** dynamic memory allocation,\n> unbounded loops, `printf` and logging in the hot path, page faults, garbage collection,\n> **CPU frequency scaling and thermal throttling**, network stack processing on your\n> control core, and **priority inversion**. ⚠️ **Measure worst-case, not average — the\n> distribution's tail is the whole specification.**\n\n**Architecturally**: separate the **safety-critical** path from the **mission** path, and\nrun them at different assurance levels. ⚠️ **A watchdog with an independent path to\nactuator power is the last line of defence and it must not depend on the software it's\nwatching.**\n\n---\n\n## §12. Testing, Debugging, and Deployment\n\n**[DURABLE] The testing pyramid, robotics edition:**\n```\nUnit                     pure logic, no hardware. Fast, and undervalued\nComponent-in-sim         one node against simulated inputs\nIntegration-in-sim       full stack, scripted scenarios, in CI\nHardware-in-the-loop     real compute + real timing, simulated world  ⚠️ high value\nReal hardware, safe env  cage, tether, E-stop, reduced speed\u002Fpower\nField trials             real environment, safety operator\nProduction               with monitoring, and a rollback path\n```\n\n**⚠️ HIL is the most under-invested rung** and catches the timing and driver bugs that\npure simulation cannot.\n\n**[DURABLE] Debugging discipline specific to robots:**\n- **⚠️ Record everything, always.** `rosbag`\u002FMCAP of every run, including failures.\n  **A robot failure you didn't record is a failure you cannot fix**, because you may not\n  reproduce it.\n- **Deterministic replay** from logs — the single most valuable debugging capability in\n  the field.\n- **Visualize** — rviz2 and Foxglove. ⚠️ **Most perception and transform bugs are obvious\n  the moment you look at them and invisible in numbers** (§3.4 → `robotics-stack-ros2-and-perception`).\n- **Check the transform tree and timestamps first.** §3.4 → `robotics-stack-ros2-and-perception` is genuinely the first\n  hypothesis, not the last.\n- **Bisect the stack**: replay recorded sensor data into a live planner; feed synthetic\n  perfect perception into control. **Isolate which layer is lying.**\n- **⚠️ Watch for correlated failures.** Robots fail in cascades — a perception dropout\n  causes a planner stall causes a controller timeout causes an E-stop.\n\n**Field deployment**: staged rollout, ⚠️ **shadow mode** (run the new policy without\nletting it actuate, and compare), extensive telemetry, remote diagnostics,\n**a rollback path that works without physical access**, and **an incident process\nthat treats near-misses as reportable.**\n\n---\n\n## §13. Functional Safety and Standards\n\n**[VERSIONED — and this regime changed substantially in 2025, which many practitioners\nhave not caught up with.]**\n\n### 13.1 ⚠️ The ISO 10218:2025 revision\n\n**ISO 10218-1:2025** (robot manufacturers) and **ISO 10218-2:2025** (integrators,\napplications, and cells) were **published February 2025 and came into force 1 April 2025**\n— **the first major revision since 2011**, taking experts from **20+ countries nearly\neight years**.\n\n**What changed, and why it matters:**\n- ⚠️ **ISO\u002FTS 15066 no longer exists as a standalone specification.** Its power-and-force-\n  limiting and collaborative-application requirements were **folded directly into\n  ISO 10218-2**. **There is no separate cobot standard to cite anymore.**\n- ⚠️ **The terms \"collaborative robot\" and \"collaborative operation\" do not appear in the\n  revised standard.** **Collaboration is a property of the *application*, not the robot** —\n  only an application can be assessed. **This kills the \"we bought a collaborative robot,\n  therefore we're safe\" reasoning outright**, and that reasoning was extremely common.\n- **Functional safety requirements are now explicit rather than implied**, with a\n  robot **classification scheme** (Class I \u002F Class II).\n- ⚠️ **Cybersecurity requirements were added** — for the first time, on the reasoning that\n  millions of networked industrial robots exist.\n- Manual load\u002Funload and end-effector guidance folded in from separate technical reports.\n- **ISO 10218-2:2025 nearly tripled in length.**\n\n**The standards stack around it**: **ISO 12100** (risk assessment methodology) and\n**ISO 13849-1:2023** (safety-related control systems, PL\u002Fcategories) underneath;\n**ANSI\u002FA3 R15.06-2025** and **CSA Z434** as the North American adoptions;\n**IEC 61508** for general functional safety; **ISO 26262** (automotive) and **ISO 21448\n\u002F SOTIF** (⚠️ **safety of the intended function — hazards from performance limitations\nrather than faults, which is exactly the right frame for learned perception**).\n\n**⚠️ On enforceability**: ISO standards are voluntary in themselves. **They become binding\nthrough contracts and through harmonisation** — in the EU under **Machinery Regulation\n2023\u002F1230, which applies from 20 January 2027**. In the US, OSHA enforcement provides the\npressure.\n\n### 13.2 ⚠️ The humanoid gap\n\n**[VERSIONED and genuinely unresolved.]** The 2025 revision **explicitly leaves regulatory\ngaps around AI, humanoids, and mobile manipulation.** ISO\u002FTS 15066's contact-force model\naddressed **stationary arms**; **humanoids walk, balance, and carry energy-dense\nbatteries** — different hazards entirely (fall zones, dynamic stability, thermal events).\n**ISO 25785-1 is under development for dynamically stable robots**, and until it lands,\n**humanoid deployments are being certified against a standard that wasn't written for\nthem.** ⚠️ **If you are deploying humanoids, this gap is your problem, not the standard's.**\n\n### 13.3 [DURABLE] The engineering practices\n**Risk assessment first** (ISO 12100 methodology), **safety functions on rated hardware**\n(⚠️ **a safety-rated stop is not `if (bad) stop();` in your application code**),\n**redundancy and diversity** for safety functions, **safe states designed rather than\ninherited**, **E-stop reachable from anywhere in the workspace**, **speed and separation\nmonitoring** or **power and force limiting** as the collaborative strategies, and\n**⚠️ a written safety case** — the artifact that says what the system will not do and why\nyou believe it.\n\n---\n\n## §14. Aerospace Flight Software\n\n**[DURABLE] The far end of the rigour spectrum, and worth knowing even if you never work\nthere — because it shows what \"we cannot fail\" looks like as engineering practice.**\n\n**Standards**: **DO-178C** (airborne software, DAL A–E; ⚠️ **DAL A demands MC\u002FDC coverage\nand full requirements traceability**), **DO-254** (hardware), **ECSS** (European space),\n**NASA NPR 7150.2** and the **NASA\u002FJPL Power of 10** coding rules, **MISRA C\u002FC++** in\nadjacent industries.\n\n**The architectural patterns**: **triple modular redundancy with voting**,\n**radiation-hardened or rad-tolerant compute** (⚠️ **and the flight computer is often\ngenerations behind consumer silicon precisely because it's qualified**), **watchdogs at\nmultiple levels**, **partitioned RTOS** (ARINC 653), **NASA cFS** as a reusable flight\nsoftware framework, **no dynamic allocation after initialization**, **bounded loops and\nbounded recursion**, and **extensive formal analysis**.\n\n**⚠️ The cultural practices are as important as the technical ones**: exhaustive\nrequirements traceability, independent verification and validation, **change control that\nwould feel absurd anywhere else**, hardware-in-the-loop and flatsat testing,\n**anomaly review boards**, and the doctrine that **every in-flight anomaly is investigated\nto root cause and fed back into process.**\n\n**[DURABLE] The transferable lesson for ordinary robotics**: **the practices scale down.**\nRequirements traceability, deterministic execution, resource bounds, comprehensive logging,\nand a written safety case are all achievable outside aerospace and all improve reliability.\n⚠️ **You don't need DO-178C to adopt bounded loops and a no-allocation control path.**\n","# Robotics Software: Real-Time and Safety-Critical Engineering, Testing, Standards, and Aerospace\n\n> **Part 4 of 5** of the *Robotics Software* reference (plugin `robotics-software`), covering §11–§14. Sibling skills: `robotics-stack-ros2-and-perception` (§0–§4), `robotics-planning-control-and-manipulation` (§5–§7), `robotics-learning-simulation-and-fleets` (§8–§10), `robotics-reference` (§15–§20). Section numbers are shared across the set; a reference written as §N → `skill` points into that sibling skill.\n>\n> **Currency:** Verified August 2026. See §17 → `robotics-reference` for the currency snapshot and what goes stale first.\n\n> **How to read this.** Reference for engineers building robots that operate in the\n> physical world with real consequences — deliberately distinct from a hobbyist kit\n> reference. Three markers:\n> - **[DURABLE]** — control theory, estimation, architecture, and safety discipline.\n>   Most of this document.\n> - **[VERSIONED]** — frameworks, models, standards, tooling.\n> - **[CONTESTED]** — genuine and active disagreement, of which this field currently has\n>   a lot.\n>\n> **⚠️ GOTCHA** boxes mark the failures that damage hardware, or people.\n>\n> **The three framings that organize everything below:**\n> 1. **Physics doesn't have an undo button.** A web service that fails returns a 500;\n>    a robot that fails puts mass through space. **This single asymmetry justifies every\n>    piece of apparently excessive rigour below** — the redundancy, the state machines,\n>    the simulation, the safety cases (§11, §13).\n> 2. **⚠️ Robotics is an integration discipline, and the integration is where it fails.**\n>    Perception, estimation, planning, and control each work in isolation and break at\n>    the seams — timing, coordinate frames, latency, and units. **The classic robotics bug\n>    is not a bad algorithm; it's a transform published 40ms late** (§3.4 → `robotics-stack-ros2-and-perception`, §12).\n> 3. **The field is in the middle of a genuine methodological argument** between\n>    classical model-based robotics and learned end-to-end policies (§8 → `robotics-learning-simulation-and-fleets`, §16.1 → `robotics-reference`).\n>    **Neither side has won, production systems are overwhelmingly hybrid, and anyone\n>    telling you the argument is settled is selling something.**\n\n---\n\n## §11. Real-Time and Safety-Critical Engineering\n\n**[DURABLE] \"Real-time\" means deterministic, not fast.** A system that responds in 10ms\nevery single time is real-time; one that averages 1ms and occasionally takes 100ms is not.\n**Hard real-time** means a missed deadline is a system failure.\n\n**How you actually get it**: **PREEMPT_RT** (mainlined into Linux, and the common\nfoundation), a genuine **RTOS** (QNX, VxWorks, Zephyr, FreeRTOS) for the hard layers,\n**⚠️ CPU isolation and shielding** (`isolcpus`, IRQ affinity) so your control thread owns a\ncore, **memory locking** (`mlockall`) and **no allocation in the control loop**,\n**priority inheritance** on any shared mutex, and **⚠️ lock-free structures for\nproducer-consumer across priority levels.**\n\n> **⚠️ GOTCHA — the things that silently destroy determinism:** dynamic memory allocation,\n> unbounded loops, `printf` and logging in the hot path, page faults, garbage collection,\n> **CPU frequency scaling and thermal throttling**, network stack processing on your\n> control core, and **priority inversion**. ⚠️ **Measure worst-case, not average — the\n> distribution's tail is the whole specification.**\n\n**Architecturally**: separate the **safety-critical** path from the **mission** path, and\nrun them at different assurance levels. ⚠️ **A watchdog with an independent path to\nactuator power is the last line of defence and it must not depend on the software it's\nwatching.**\n\n---\n\n## §12. Testing, Debugging, and Deployment\n\n**[DURABLE] The testing pyramid, robotics edition:**\n```\nUnit                     pure logic, no hardware. Fast, and undervalued\nComponent-in-sim         one node against simulated inputs\nIntegration-in-sim       full stack, scripted scenarios, in CI\nHardware-in-the-loop     real compute + real timing, simulated world  ⚠️ high value\nReal hardware, safe env  cage, tether, E-stop, reduced speed\u002Fpower\nField trials             real environment, safety operator\nProduction               with monitoring, and a rollback path\n```\n\n**⚠️ HIL is the most under-invested rung** and catches the timing and driver bugs that\npure simulation cannot.\n\n**[DURABLE] Debugging discipline specific to robots:**\n- **⚠️ Record everything, always.** `rosbag`\u002FMCAP of every run, including failures.\n  **A robot failure you didn't record is a failure you cannot fix**, because you may not\n  reproduce it.\n- **Deterministic replay** from logs — the single most valuable debugging capability in\n  the field.\n- **Visualize** — rviz2 and Foxglove. ⚠️ **Most perception and transform bugs are obvious\n  the moment you look at them and invisible in numbers** (§3.4 → `robotics-stack-ros2-and-perception`).\n- **Check the transform tree and timestamps first.** §3.4 → `robotics-stack-ros2-and-perception` is genuinely the first\n  hypothesis, not the last.\n- **Bisect the stack**: replay recorded sensor data into a live planner; feed synthetic\n  perfect perception into control. **Isolate which layer is lying.**\n- **⚠️ Watch for correlated failures.** Robots fail in cascades — a perception dropout\n  causes a planner stall causes a controller timeout causes an E-stop.\n\n**Field deployment**: staged rollout, ⚠️ **shadow mode** (run the new policy without\nletting it actuate, and compare), extensive telemetry, remote diagnostics,\n**a rollback path that works without physical access**, and **an incident process\nthat treats near-misses as reportable.**\n\n---\n\n## §13. Functional Safety and Standards\n\n**[VERSIONED — and this regime changed substantially in 2025, which many practitioners\nhave not caught up with.]**\n\n### 13.1 ⚠️ The ISO 10218:2025 revision\n\n**ISO 10218-1:2025** (robot manufacturers) and **ISO 10218-2:2025** (integrators,\napplications, and cells) were **published February 2025 and came into force 1 April 2025**\n— **the first major revision since 2011**, taking experts from **20+ countries nearly\neight years**.\n\n**What changed, and why it matters:**\n- ⚠️ **ISO\u002FTS 15066 no longer exists as a standalone specification.** Its power-and-force-\n  limiting and collaborative-application requirements were **folded directly into\n  ISO 10218-2**. **There is no separate cobot standard to cite anymore.**\n- ⚠️ **The terms \"collaborative robot\" and \"collaborative operation\" do not appear in the\n  revised standard.** **Collaboration is a property of the *application*, not the robot** —\n  only an application can be assessed. **This kills the \"we bought a collaborative robot,\n  therefore we're safe\" reasoning outright**, and that reasoning was extremely common.\n- **Functional safety requirements are now explicit rather than implied**, with a\n  robot **classification scheme** (Class I \u002F Class II).\n- ⚠️ **Cybersecurity requirements were added** — for the first time, on the reasoning that\n  millions of networked industrial robots exist.\n- Manual load\u002Funload and end-effector guidance folded in from separate technical reports.\n- **ISO 10218-2:2025 nearly tripled in length.**\n\n**The standards stack around it**: **ISO 12100** (risk assessment methodology) and\n**ISO 13849-1:2023** (safety-related control systems, PL\u002Fcategories) underneath;\n**ANSI\u002FA3 R15.06-2025** and **CSA Z434** as the North American adoptions;\n**IEC 61508** for general functional safety; **ISO 26262** (automotive) and **ISO 21448\n\u002F SOTIF** (⚠️ **safety of the intended function — hazards from performance limitations\nrather than faults, which is exactly the right frame for learned perception**).\n\n**⚠️ On enforceability**: ISO standards are voluntary in themselves. **They become binding\nthrough contracts and through harmonisation** — in the EU under **Machinery Regulation\n2023\u002F1230, which applies from 20 January 2027**. In the US, OSHA enforcement provides the\npressure.\n\n### 13.2 ⚠️ The humanoid gap\n\n**[VERSIONED and genuinely unresolved.]** The 2025 revision **explicitly leaves regulatory\ngaps around AI, humanoids, and mobile manipulation.** ISO\u002FTS 15066's contact-force model\naddressed **stationary arms**; **humanoids walk, balance, and carry energy-dense\nbatteries** — different hazards entirely (fall zones, dynamic stability, thermal events).\n**ISO 25785-1 is under development for dynamically stable robots**, and until it lands,\n**humanoid deployments are being certified against a standard that wasn't written for\nthem.** ⚠️ **If you are deploying humanoids, this gap is your problem, not the standard's.**\n\n### 13.3 [DURABLE] The engineering practices\n**Risk assessment first** (ISO 12100 methodology), **safety functions on rated hardware**\n(⚠️ **a safety-rated stop is not `if (bad) stop();` in your application code**),\n**redundancy and diversity** for safety functions, **safe states designed rather than\ninherited**, **E-stop reachable from anywhere in the workspace**, **speed and separation\nmonitoring** or **power and force limiting** as the collaborative strategies, and\n**⚠️ a written safety case** — the artifact that says what the system will not do and why\nyou believe it.\n\n---\n\n## §14. Aerospace Flight Software\n\n**[DURABLE] The far end of the rigour spectrum, and worth knowing even if you never work\nthere — because it shows what \"we cannot fail\" looks like as engineering practice.**\n\n**Standards**: **DO-178C** (airborne software, DAL A–E; ⚠️ **DAL A demands MC\u002FDC coverage\nand full requirements traceability**), **DO-254** (hardware), **ECSS** (European space),\n**NASA NPR 7150.2** and the **NASA\u002FJPL Power of 10** coding rules, **MISRA C\u002FC++** in\nadjacent industries.\n\n**The architectural patterns**: **triple modular redundancy with voting**,\n**radiation-hardened or rad-tolerant compute** (⚠️ **and the flight computer is often\ngenerations behind consumer silicon precisely because it's qualified**), **watchdogs at\nmultiple levels**, **partitioned RTOS** (ARINC 653), **NASA cFS** as a reusable flight\nsoftware framework, **no dynamic allocation after initialization**, **bounded loops and\nbounded recursion**, and **extensive formal analysis**.\n\n**⚠️ The cultural practices are as important as the technical ones**: exhaustive\nrequirements traceability, independent verification and validation, **change control that\nwould feel absurd anywhere else**, hardware-in-the-loop and flatsat testing,\n**anomaly review boards**, and the doctrine that **every in-flight anomaly is investigated\nto root cause and fed back into process.**\n\n**[DURABLE] The transferable lesson for ordinary robotics**: **the practices scale down.**\nRequirements traceability, deterministic execution, resource bounds, comprehensive logging,\nand a written safety case are all achievable outside aerospace and all improve reliability.\n⚠️ **You don't need DO-178C to adopt bounded loops and a no-allocation control path.**\n",{"name":5,"description":7},"develop","ae32736a1aabddabca5d2c96d665aa0ebc7d8700","src\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Frobotics-software\u002Fskills\u002Frobotics-safety-standards-and-deployment",3,"https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey","https:\u002F\u002Fthe-vibey-project.github.io\u002Fvibey\u002F","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project","https:\u002F\u002Fvibewithadam.matthewsteinberger.com","freedom for software engineers","2026-11-15 05:47:42",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add the-vibey-project\u002Fvibey --skill robotics-safety-standards-and-deployment",{"tool":40,"command":41},"bunx","bunx skills add the-vibey-project\u002Fvibey --skill robotics-safety-standards-and-deployment",{"tool":43,"command":44},"pnpm","pnpm dlx skills add the-vibey-project\u002Fvibey --skill robotics-safety-standards-and-deployment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Frobotics-software\u002Fskills\u002Frobotics-safety-standards-and-deployment\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7AT1FQJAE1FQYAMDTF490Y4","white-paper-writing","Use when writing white papers, technical reports, policy documents, thought leadership pieces, or any long-form authoritative document. Triggers on requests to write, structure, outline, or review white papers, technical reports, position papers, policy briefs, or evidence-driven arguments. Also use for B2B content marketing strategy, technical documentation requiring authority, academic-style reports, or any document that must educate while persuading. Use when someone asks \"how should I structure this\" for a long-form document.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fwhite-paper-writing\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AT16BJRJJKK2MASXRZS76G","prose-technical-mechanics","Use when editing or writing prose at a technical\u002Fmechanical level: choosing between Anglo-Saxon and Latinate diction, placing information in topic vs stress positions, writing periodic vs cumulative sentences, handling sentence rhythm, punctuation as logic, transitions, paragraph structure, or phonesthetics. Use when someone wants to understand WHY prose works or doesn't, not just surface-level style advice. Triggers on word choice, sentence structure, emphasis, rhythm, diction, or any deep writing mechanics question.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fprose-technical-mechanics\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7AT0W9HT0ZZ9Y287NW99MR3","prose-mechanics","Use when writing, editing, or analyzing prose style; when trying to avoid generic AI-sounding writing; when applying specific prose styles such as journalistic, academic, narrative, KJV biblical, Hemingway plain, Latinate\u002FJamesian, Orwellian, Augustan, Victorian, Early Modern (Bacon, Browne, Milton), or free indirect discourse; or when coaching someone on writing voice and mechanics. Triggers on any request to improve, analyze, or write in a specific prose style, to fix \"AI-sounding\" writing, to make prose more vivid or concrete, to vary sentence rhythm, or to understand how a particular writer achieves their effects.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fprose-mechanics\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7AT0KR635JX66X2X6F3E2CP","narrative-structure","Use when structuring stories, pitches, presentations, white papers, or any persuasive narrative; analyzing the hero's journey in fiction or non-fiction; applying StoryBrand for business communication; designing narrative arcs for thought leadership; or understanding Vogler, Snyder, Propp, or Campbell frameworks. Triggers on any narrative structure, storytelling, pitch structure, StoryBrand, hero's journey, three-act structure, Freytag, Save the Cat, narrative arc, or \"how should I structure this story\u002Fpitch\u002Fpresentation\" request.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fnarrative-structure\u002FSKILL.md",[],[],{"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":19},"01M7AT0AKGW09NKKZDYBT8VRDE","legal-brief-writing","Use when writing legal briefs, motions, or any court filing; when analyzing judicial cognition and persuasion; when applying elite brief-writing techniques from Roberts, Clement, Kagan, Garner; or when structuring legal arguments for maximum persuasion. Also use for autistic\u002Fneurodivergent advocates who need to understand how their natural communication style maps to elite legal advocacy. Triggers on any legal writing, brief drafting, motion preparation, or legal argument structuring request.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Flegal-brief-writing\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7AT00VWPS4Q8B5VEMXX9NQT","journal-publishability-criteria","Use whenever a research paper, article or preprint is being written, revised, reviewed or published, and specifically before every publication of docs\u002Fpaper.md. Covers what legitimate journals actually gate on, in order of gating — the editor's desk screen (scope, novelty, package problems), what reviewers judge (methodological soundness, claims the evidence can carry, statistical and qualitative reporting), EQUATOR reporting guidelines, the ICMJE authorship criteria, COPE's view of text recycling, the near-universal generative-AI policy (no AI author, disclosure, author responsibility), TOP 2025 transparency standards, how to verify a journal is legitimate, submitting without an institution, and a pre-submission checklist. Triggers on requests to evaluate, review, prepare or submit a paper, to judge publishability, to write a declarations or data-availability section, to disclose AI use, or to check a journal.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fjournal-publishability-criteria\u002FSKILL.md",[],[]]