[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M752V7X3HGMWGCPSWMG498TY":3,"skill-same:01M752V7X3HGMWGCPSWMG498TY":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M752V7X3HGMWGCPSWMG498TY","verify-with-prototype",null,"Prototype-before-production workflow for risky host integrations (sudo, privileges, system config). Use when a feature touches the real OS, when behavior must be proven with a small script before full implementation, or when the user mentions prototype verification, POC script, or verify-with-prototype. Run after investigate\u002Ffollowup and before doctest-TDD integration.","xhd2015\u002Fagent-pro","xhd2015","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14964938?v=4","01M752R5K679TBRT2X43X9RYCR","01M752R5MBCWS6252YZW22Y49W",1,"MIT","https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro\u002Fblob\u002Fmaster\u002Fagents\u002Fverify-with-prototype\u002Frun\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: verify-with-prototype\ndescription: >-\n  Prototype-before-production workflow for risky host integrations (sudo,\n  privileges, system config). Use when a feature touches the real OS, when\n  behavior must be proven with a small script before full implementation, or when\n  the user mentions prototype verification, POC script, or verify-with-prototype.\n  Run after investigate\u002Ffollowup and before doctest-TDD integration.\n---\n\nYou guide the agent through **prototype verification** before full implementation\nand integration. The goal is to learn failure modes cheaply (false positives,\nsession caches, TTY requirements) in a throwaway script, then encode lessons in\na real package with fakes-based tests.\n\n# When to use\n\n- Host or privilege integration: `sudo`, `\u002Fetc\u002Fsudoers.d`, TUN, `networksetup`, etc.\n- Persistent state vs session cache can be confused (`sudo -n`, timestamp cache)\n- Production mistakes are hard to undo or dangerous to test in CI\n- User wants \"setup once, then never password again\" or similar UX proofs\n\n# When not to use\n\n- Pure documentation or config-only changes\n- Behavior already covered by isolated unit tests with no OS side effects\n- User only wants root-cause explanation → use `investigate` instead\n\n# Required workflow\n\n## Phase 0 — Understand (often already done)\n\n- Symptom, expected behavior, and constraints from `investigate` \u002F `followup`\n- Identify the **stand-in** for the expensive dependency (e.g. `hello.sh` instead of `sing-box`)\n\n## Phase 1 — POC script\n\nCreate `script\u002F\u003Cfeature>-poc\u002F` (Go preferred) with **small command surface**:\n\n| Command | Purpose |\n|---------|---------|\n| `detect` | Report persistent state vs cache vs \"works right now\" **separately** |\n| `auto-setup` | One-time install path (may prompt on TTY) |\n| `remove-*` | Tear down + invalidate session cache if relevant |\n\nDocument a **manual test matrix** in the script header:\n\n```\nremove → auto-setup (password once) → auto-setup (no password) → remove → auto-setup (password again)\n```\n\n**POC rules**\n\n- Do not infer persistent install from `sudo -n` alone — use drop-in file + local manifest (or equivalent)\n- On remove, flush sudo timestamp cache (`sudo -k`) when testing \"prompt again\" behavior\n- Distinguish **stdin** vs **stdout** TTY when password is required\n\n## Phase 2 — Manual verification\n\nUser (or agent with user) runs the matrix in a real terminal. Capture lessons:\n\n- False positives (e.g. warm cache after `remove-sudo`)\n- Missing non-TTY guard\n- Wrong detection signal\n\nFix the POC until the matrix passes. **Do not** proceed to production until manual proof succeeds.\n\n## Phase 3 — Requirement doc\n\nWrite `REQUIREMENT-DESIGN-\u003Cslug>.md` with:\n\n- Data model (`Config`, `Rule`, manifest paths, sudoers drop-in name)\n- Approved scope (package only vs integration)\n- Test tree outline (doctests with injectable `FS` + `Runner`, no real `\u002Fetc` or `sudo`)\n\nGet explicit user approval before TDD implementation.\n\n## Phase 4 — Extract package + TDD\n\n- Extract core logic to `pkgs\u002F\u003Cname>\u002F` with injectable `FS` and `Runner`\n- Doctest tree with **fakes only** — no real system modification in CI\n- Thin CLIs: POC script + production caller(s) share the package\n- Guards:\n  - Under `go test`, panic if `FS`\u002F`Runner` nil (production deps would touch the OS)\n  - Before interactive `sudo`, error if stdin is not a TTY (already-installed path may skip)\n\n## Phase 5 — Integration\n\n- Wire production entrypoints (flags like `--no-setup-sudo` for opt-out of auto-setup)\n- Hook layer in existing packages for test injection\n- Bump \u002F `replace` module deps as needed\n\n# Response shape\n\n1. **Risk summary** — what can go wrong on the real system\n2. **POC plan** — commands, stand-in, manual matrix\n3. **Detection model** — persistent vs cache vs live probe (table)\n4. **After manual proof** — package API sketch + test groups\n5. **Stop** — do not implement production code until POC matrix passes and user approves REQUIREMENT-DESIGN\n\n# Case study (this repo)\n\nVPN passwordless sudo (`master-2026-07-06-vpn-no-password` work):\n\n- POC: `script\u002Fsudo-nopasswd-poc` (`detect`, `auto-setup`, `remove-sudo`)\n- Lesson: `sudo -n` after `remove-sudo` succeeded via **timestamp cache**, not NOPASSWD\n- Fix: manifest + `\u002Fetc\u002Fsudoers.d` stat for `IsInstalled`; `sudo -k` on remove\n- Package: `pkgs\u002Fsudosetup` with fake FS\u002FRunner doctests\n- Integration: `ws-proxy vpn` auto-setup + `--no-setup-sudo`\n- Guards: test-time production-deps panic; stdin-TTY check before first setup\n\n# Related commands\n\n```sh\nagent-pro skill investigate --show\nagent-pro skill followup --show\nagent-pro skill verify-with-prototype --show\n```\n\nInstall locally:\n\n```sh\nagent-pro skill verify-with-prototype install\n```","You guide the agent through **prototype verification** before full implementation\nand integration. The goal is to learn failure modes cheaply (false positives,\nsession caches, TTY requirements) in a throwaway script, then encode lessons in\na real package with fakes-based tests.\n\n# When to use\n\n- Host or privilege integration: `sudo`, `\u002Fetc\u002Fsudoers.d`, TUN, `networksetup`, etc.\n- Persistent state vs session cache can be confused (`sudo -n`, timestamp cache)\n- Production mistakes are hard to undo or dangerous to test in CI\n- User wants \"setup once, then never password again\" or similar UX proofs\n\n# When not to use\n\n- Pure documentation or config-only changes\n- Behavior already covered by isolated unit tests with no OS side effects\n- User only wants root-cause explanation → use `investigate` instead\n\n# Required workflow\n\n## Phase 0 — Understand (often already done)\n\n- Symptom, expected behavior, and constraints from `investigate` \u002F `followup`\n- Identify the **stand-in** for the expensive dependency (e.g. `hello.sh` instead of `sing-box`)\n\n## Phase 1 — POC script\n\nCreate `script\u002F\u003Cfeature>-poc\u002F` (Go preferred) with **small command surface**:\n\n| Command | Purpose |\n|---------|---------|\n| `detect` | Report persistent state vs cache vs \"works right now\" **separately** |\n| `auto-setup` | One-time install path (may prompt on TTY) |\n| `remove-*` | Tear down + invalidate session cache if relevant |\n\nDocument a **manual test matrix** in the script header:\n\n```\nremove → auto-setup (password once) → auto-setup (no password) → remove → auto-setup (password again)\n```\n\n**POC rules**\n\n- Do not infer persistent install from `sudo -n` alone — use drop-in file + local manifest (or equivalent)\n- On remove, flush sudo timestamp cache (`sudo -k`) when testing \"prompt again\" behavior\n- Distinguish **stdin** vs **stdout** TTY when password is required\n\n## Phase 2 — Manual verification\n\nUser (or agent with user) runs the matrix in a real terminal. Capture lessons:\n\n- False positives (e.g. warm cache after `remove-sudo`)\n- Missing non-TTY guard\n- Wrong detection signal\n\nFix the POC until the matrix passes. **Do not** proceed to production until manual proof succeeds.\n\n## Phase 3 — Requirement doc\n\nWrite `REQUIREMENT-DESIGN-\u003Cslug>.md` with:\n\n- Data model (`Config`, `Rule`, manifest paths, sudoers drop-in name)\n- Approved scope (package only vs integration)\n- Test tree outline (doctests with injectable `FS` + `Runner`, no real `\u002Fetc` or `sudo`)\n\nGet explicit user approval before TDD implementation.\n\n## Phase 4 — Extract package + TDD\n\n- Extract core logic to `pkgs\u002F\u003Cname>\u002F` with injectable `FS` and `Runner`\n- Doctest tree with **fakes only** — no real system modification in CI\n- Thin CLIs: POC script + production caller(s) share the package\n- Guards:\n  - Under `go test`, panic if `FS`\u002F`Runner` nil (production deps would touch the OS)\n  - Before interactive `sudo`, error if stdin is not a TTY (already-installed path may skip)\n\n## Phase 5 — Integration\n\n- Wire production entrypoints (flags like `--no-setup-sudo` for opt-out of auto-setup)\n- Hook layer in existing packages for test injection\n- Bump \u002F `replace` module deps as needed\n\n# Response shape\n\n1. **Risk summary** — what can go wrong on the real system\n2. **POC plan** — commands, stand-in, manual matrix\n3. **Detection model** — persistent vs cache vs live probe (table)\n4. **After manual proof** — package API sketch + test groups\n5. **Stop** — do not implement production code until POC matrix passes and user approves REQUIREMENT-DESIGN\n\n# Case study (this repo)\n\nVPN passwordless sudo (`master-2026-07-06-vpn-no-password` work):\n\n- POC: `script\u002Fsudo-nopasswd-poc` (`detect`, `auto-setup`, `remove-sudo`)\n- Lesson: `sudo -n` after `remove-sudo` succeeded via **timestamp cache**, not NOPASSWD\n- Fix: manifest + `\u002Fetc\u002Fsudoers.d` stat for `IsInstalled`; `sudo -k` on remove\n- Package: `pkgs\u002Fsudosetup` with fake FS\u002FRunner doctests\n- Integration: `ws-proxy vpn` auto-setup + `--no-setup-sudo`\n- Guards: test-time production-deps panic; stdin-TTY check before first setup\n\n# Related commands\n\n```sh\nagent-pro skill investigate --show\nagent-pro skill followup --show\nagent-pro skill verify-with-prototype --show\n```\n\nInstall locally:\n\n```sh\nagent-pro skill verify-with-prototype install\n```",{"name":5,"description":7},"master","d5d5361083d4adf0dd8a15272123af778b38117a","agents\u002Fverify-with-prototype\u002Frun",0,"https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro","https:\u002F\u002Fgithub.com\u002Fxhd2015","https:\u002F\u002Fblog.xhd2015.xyz","@Harbin Institute of Technology","2026-11-12 07:05:51",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add xhd2015\u002Fagent-pro --skill verify-with-prototype",{"tool":38,"command":39},"bunx","bunx skills add xhd2015\u002Fagent-pro --skill verify-with-prototype",{"tool":41,"command":42},"pnpm","pnpm dlx skills add xhd2015\u002Fagent-pro --skill verify-with-prototype","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro\u002Fblob\u002Fmaster\u002Fagents\u002Fverify-with-prototype\u002Frun\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"verify_with_prototype.go","SCRIPT","脚本",71,"https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro\u002Fblob\u002Fmaster\u002Fagents\u002Fverify-with-prototype\u002Frun\u002Fverify_with_prototype.go",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M752V363XA61Q2PSVS0W9M3H","verify-on-behalf-of-user","Run human-style scenario verification after an agent claims work is done: git status, build into ~\u002F.sandbox\u002Fbin (default sandbox mode) or opt-in host mode (outside sandbox: wrk --reinstall-local \u002F change-scoped install), real integration\u002FE2E scenarios (start servers, browser-agent for UI), always-labeled depth, markdown transcript written and inlined for review. Use for \"verify on my behalf\", before commit. Complements doctests; does not replace them. Load a sub-topic with: agent-pro skill --show verify-on-behalf-of-user\u002F\u003Ctopic>","https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro\u002Fblob\u002Fmaster\u002Fagents\u002Fverify-on-behalf-of-user\u002Frun\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M752TVN3Y9ZMKW52A8MKZ3QP","test-case-tree-design-expert","Use when the user wants a decision-tree style test case design with inherited setup and per-leaf assertions.","https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro\u002Fblob\u002Fmaster\u002Fagents\u002Ftest-case-tree-design-expert\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M752TSECEXD80J650BC6YXMY","test-case-design-expert","Use when the user wants comprehensive user-facing end-to-end test scenarios for a feature description.","https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro\u002Fblob\u002Fmaster\u002Fagents\u002Ftest-case-design-expert\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M752TQB00WQJ9475GF0JVEGY","tdd-expert","Use when the user has a test-case-tree output and wants runnable Go tests plus stub implementation following Test-Driven Development.","https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro\u002Fblob\u002Fmaster\u002Fagents\u002Ftdd-expert\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M752TGQ1905Y0FTCTQPMJTA7","summarize-a-skill","Meta-skill: distill durable high-signal guidance (worked vs failed, wrong → correct, and anything else that quickens future similar tasks) into a brief reusable skill document with YAML frontmatter. When the user does not explicitly ask for a new skill\u002Ffile, prefer updating an existing skill over creating one. Writes skills\u002F\u003Cname>\u002FSKILL.md (or docs|doc\u002Fskills\u002F…). Use for \u002Fsummarize-a-skill, \"summarize what worked\", \"lessons learned into a skill\", or \"write a skill from this session\".","https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro\u002Fblob\u002Fmaster\u002Fagents\u002Fsummarize-a-skill\u002Frun\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M752TBFMMQJRCWFMYX6PX0XN","split-phases","Break a large implementation plan into dependency-ordered phases that are independently implementable and verifiable. Use when the user runs \u002Fsplit-phases, or says \"split into phases\", \"phase this plan\", \"break into units of work\", \"dependency-ordered milestones\", or wants a giant plan split for phase-by-phase work.","https:\u002F\u002Fgithub.com\u002Fxhd2015\u002Fagent-pro\u002Fblob\u002Fmaster\u002Fagents\u002Fsplit-phases\u002Frun\u002FSKILL.md",[],[]]