[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EQAVVGV60EMM5BJ2QQ683T":3,"skill-same:01M7EQAVVGV60EMM5BJ2QQ683T":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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7EQAVVGV60EMM5BJ2QQ683T","verify-unattended",null,"Install, instrument and verify a web app end to end without pausing for a human. Use in an autonomous or goal-mode agent, in CI, or in any client that asks for approval on every command: it never says \"restart your client\" or \"open a browser\", because it takes a route that needs neither. Prefer the normal install-and-verify skill when a human is present and can answer.","FarhanS7\u002FEcom","FarhanS7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F163057878?v=4","01M7EQ3RQNHRCTXHD9K9JS4SKM","Farhan Shahriar","01M7EQ3RR784WS07MT2FKFA186",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FFarhanS7\u002FEcom\u002Fblob\u002Ffeature\u002Fplatform\u002Ft001-review-scope-and-proposed-decisions\u002Fskills\u002Freticle-main\u002Fskills\u002Fverify-unattended\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: verify-unattended\ndescription: 'Install, instrument and verify a web app end to end without pausing for a human. Use in an autonomous or goal-mode agent, in CI, or in any client that asks for approval on every command: it never says \"restart your client\" or \"open a browser\", because it takes a route that needs neither. Prefer the normal install-and-verify skill when a human is present and can answer.'\nlicense: Apache-2.0\nmetadata:\n  version: 2.13.1\n  homepage: https:\u002F\u002Fwww.reticle.sh\n  repository: https:\u002F\u002Fgithub.com\u002Freticlehq\u002Freticle\n---\n\n# Reticle, unattended\n\nSame product, same verdicts, one difference: **nothing here waits for a human.**\n\nThe normal skill has two places where it hands control back: \"restart your client so it picks up the MCP server\" and \"open the app in a browser\". Both are correct when someone is sitting there. In goal mode they are dead ends: the restart ends the context holding these instructions, and there is nobody to open a tab.\n\nSo this skill takes the route that needs neither, and stops only when it has a verdict or a reason.\n\n## The one rule that makes this work\n\n**You cannot add MCP tools to your own running process.** No slash command, no config edit, no re-registration reaches the tool list you already have. Your client read it before Reticle existed. Do not try, and do not ask to be restarted.\n\nInstead, branch once on what you already have:\n\n- **`reticle_*` tools present** → drive with them. Best evidence, source-mapped, full verdicts.\n- **not present** → use the CLI. `reticle verify` produces a verdict and an exit code with no MCP involvement at all.\n\nBoth routes end in a verdict. Pick the one your process allows and go.\n\n## Step 1: wire it, once, quietly\n\n```\nexport RETICLE_INSTALL_SOURCE=npx_skill\nnpx -y @reticlehq\u002Fserver@latest init\n```\n\nThe `export` is on its own line on purpose. Every other copy of this command carries the marker inline, but this skill runs where commands are matched against a prefix allowlist (see \"Keep commands plain\" below), and `RETICLE_INSTALL_SOURCE=... npx ...` no longer starts with `npx`. Inline, it would stop matching the very rule this file tells you to rely on.\n\nThen read the report rather than assuming it. Two lines matter:\n\n- **`⚠` on the app's build config**: the wiring did not land. Apply the printed edit yourself; do not carry on as if it had.\n- **`ℹ` naming a version fallback**: the pinned SDK was refused and a different one installed. The SDK and the daemon must agree; if a later call reports a protocol error, this is why.\n\n`init` is idempotent. A step reading `already wired` is a pass, not a skip.\n\n**If `init` reports every step already done, the app was instrumented before you arrived.** That is fine, but it means this run has not proved the install. Say so rather than claiming you set it up.\n\n## Step 2: make sure the app is actually running\n\nThe daemon needs a page to look at, and a page needs a server. Do not ask whether to start one.\n\n1. Read the dev script out of `package.json`.\n2. Start it in the background, on the port the script implies.\n3. Poll the port until it answers. A dev server that has to compile a route can take 30 seconds on first hit; a timeout here is not a failure yet.\n\nIf a server is **already** listening on that port, use it. Starting a second one on a different port gives you an app nobody is verifying, and leaves a process behind.\n\n**Restarting matters after `init`.** A build plugin added to a config the running server already read is not in the bundle. If the server was up before step 1, restart it now or nothing you do next will find an instrumented page.\n\n## Step 3: get a page connected\n\nWith the MCP tools:\n\n```\nreticle_sessions\n```\n\nA listed session is the proof. Nothing else in this skill can tell you anything about the app until one appears.\n\nNo session, and no human to open a tab? Take one yourself:\n\n```\nreticle_lease { action: \"acquire\", url: \"http:\u002F\u002Flocalhost:\u003Cport>\u002F\" }\n```\n\nThe lease opens a browser Reticle owns and drives. It is the whole answer to \"there is nobody here to open the page\".\n\nWithout the MCP tools, skip to step 4: `verify` opens its own browser.\n\n## Step 4: the verdict\n\n**Declare the consequence before you act.** This is the difference between a check and a rationalisation, and it is the entire reason this tool exists:\n\n```\nreticle_act_and_wait { ref, action, until: { … } }\n```\n\nAssert what the app _did_, not what it _shows_. A UI that renders the value it just sent, rather than the value the server returned, passes every DOM-level check ever written:\n\n```\nuntil: { kind: \"net\", method: \"POST\", urlContains: \"\u002Fapi\u002Frefund\",\n         status: 200, bodyContains: \"\\\"refunded\\\":1187.01\" }\n```\n\n`bodyContains` reads the **response**: what the server answered. It needs body capture, which `init` writes into the app's config; if a verdict comes back `outcome_unread`, that is what is missing.\n\nWithout the MCP tools:\n\n```\nnpx @reticlehq\u002Fserver verify http:\u002F\u002Flocalhost:\u003Cport>\u002F\n```\n\nExit 0 is a pass. It drives the app and re-verifies **saved flows**, so if the project has none, it will tell you nothing was checked. That is not a pass. Record one first, or say plainly that there was nothing to verify.\n\n## Step 5: read the verdict honestly\n\n- **`verified: \"yes\"`**: proved. Say what held.\n- **`verified: \"no\"`**: the app is wrong, or your expectation was. Both are results. Report it.\n- **`verified: \"unknown\"`**: Reticle drove the app and could not tell. **Not a pass.** Never round it up, and never weaken the assertion until it goes green. That converts a real signal into a false one, which is the failure this product exists to prevent.\n\nA drive that ends without `act_and_wait` or `assert` has no result, however many tools it used.\n\n## When you are genuinely stuck\n\nStop and say which of these it is. A precise dead end beats a green report.\n\n| What you see | What it means |\n| --- | --- |\n| tools absent, `verify` says no saved flows | nothing to verify yet: record a flow, or report that |\n| `reticle_sessions` empty, port listening | the bundle has no SDK: restart the dev server after `init` |\n| `verified: \"unknown\"`, `outcome_unread` | the response body was not recorded: check the plugin options `init` wrote |\n| lease loads the page but never connects | the app refused to dial; on a non-localhost host it needs a pairing token as well as `allowNonLocalhost` |\n\n## Notes for approval-gated clients\n\nSome clients ask a human to approve each command. Two things reduce that to near zero:\n\n- **Keep commands plain.** `npx @reticlehq\u002Fserver init` matches a prefix rule; the same command wrapped in a subshell or a `$(…)` usually does not.\n- **Expect one prompt about the home directory.** The daemon keeps its state in `~\u002F.reticle`, which is outside the workspace. Approving that family once covers every later call.\n\nIf your client offers an autonomous or goal mode, this skill is written for it. Turn it on before starting rather than approving forty prompts. Approval fatigue is a real reason runs are abandoned half-installed, with the tools connected and nothing ever verified.\n\n## Report feedback\n\nReticle is built for agents, so your experience is the signal that decides what gets fixed, and it disappears when your context does. One call, then carry on:\n\n```\nreticle_feedback { kind: \"bug\" | \"gap\" | \"ambiguity\" | \"feature_request\" | \"improvement\", text: \"…\" }\n```\n\nUnreachable? `npx @reticlehq\u002Fserver feedback --agent --kind \u003Ckind> \"what happened\"`. Report defects in **Reticle**; a bug you find in the app under test is Reticle working, and belongs in your answer.\n","# Reticle, unattended\n\nSame product, same verdicts, one difference: **nothing here waits for a human.**\n\nThe normal skill has two places where it hands control back: \"restart your client so it picks up the MCP server\" and \"open the app in a browser\". Both are correct when someone is sitting there. In goal mode they are dead ends: the restart ends the context holding these instructions, and there is nobody to open a tab.\n\nSo this skill takes the route that needs neither, and stops only when it has a verdict or a reason.\n\n## The one rule that makes this work\n\n**You cannot add MCP tools to your own running process.** No slash command, no config edit, no re-registration reaches the tool list you already have. Your client read it before Reticle existed. Do not try, and do not ask to be restarted.\n\nInstead, branch once on what you already have:\n\n- **`reticle_*` tools present** → drive with them. Best evidence, source-mapped, full verdicts.\n- **not present** → use the CLI. `reticle verify` produces a verdict and an exit code with no MCP involvement at all.\n\nBoth routes end in a verdict. Pick the one your process allows and go.\n\n## Step 1: wire it, once, quietly\n\n```\nexport RETICLE_INSTALL_SOURCE=npx_skill\nnpx -y @reticlehq\u002Fserver@latest init\n```\n\nThe `export` is on its own line on purpose. Every other copy of this command carries the marker inline, but this skill runs where commands are matched against a prefix allowlist (see \"Keep commands plain\" below), and `RETICLE_INSTALL_SOURCE=... npx ...` no longer starts with `npx`. Inline, it would stop matching the very rule this file tells you to rely on.\n\nThen read the report rather than assuming it. Two lines matter:\n\n- **`⚠` on the app's build config**: the wiring did not land. Apply the printed edit yourself; do not carry on as if it had.\n- **`ℹ` naming a version fallback**: the pinned SDK was refused and a different one installed. The SDK and the daemon must agree; if a later call reports a protocol error, this is why.\n\n`init` is idempotent. A step reading `already wired` is a pass, not a skip.\n\n**If `init` reports every step already done, the app was instrumented before you arrived.** That is fine, but it means this run has not proved the install. Say so rather than claiming you set it up.\n\n## Step 2: make sure the app is actually running\n\nThe daemon needs a page to look at, and a page needs a server. Do not ask whether to start one.\n\n1. Read the dev script out of `package.json`.\n2. Start it in the background, on the port the script implies.\n3. Poll the port until it answers. A dev server that has to compile a route can take 30 seconds on first hit; a timeout here is not a failure yet.\n\nIf a server is **already** listening on that port, use it. Starting a second one on a different port gives you an app nobody is verifying, and leaves a process behind.\n\n**Restarting matters after `init`.** A build plugin added to a config the running server already read is not in the bundle. If the server was up before step 1, restart it now or nothing you do next will find an instrumented page.\n\n## Step 3: get a page connected\n\nWith the MCP tools:\n\n```\nreticle_sessions\n```\n\nA listed session is the proof. Nothing else in this skill can tell you anything about the app until one appears.\n\nNo session, and no human to open a tab? Take one yourself:\n\n```\nreticle_lease { action: \"acquire\", url: \"http:\u002F\u002Flocalhost:\u003Cport>\u002F\" }\n```\n\nThe lease opens a browser Reticle owns and drives. It is the whole answer to \"there is nobody here to open the page\".\n\nWithout the MCP tools, skip to step 4: `verify` opens its own browser.\n\n## Step 4: the verdict\n\n**Declare the consequence before you act.** This is the difference between a check and a rationalisation, and it is the entire reason this tool exists:\n\n```\nreticle_act_and_wait { ref, action, until: { … } }\n```\n\nAssert what the app _did_, not what it _shows_. A UI that renders the value it just sent, rather than the value the server returned, passes every DOM-level check ever written:\n\n```\nuntil: { kind: \"net\", method: \"POST\", urlContains: \"\u002Fapi\u002Frefund\",\n         status: 200, bodyContains: \"\\\"refunded\\\":1187.01\" }\n```\n\n`bodyContains` reads the **response**: what the server answered. It needs body capture, which `init` writes into the app's config; if a verdict comes back `outcome_unread`, that is what is missing.\n\nWithout the MCP tools:\n\n```\nnpx @reticlehq\u002Fserver verify http:\u002F\u002Flocalhost:\u003Cport>\u002F\n```\n\nExit 0 is a pass. It drives the app and re-verifies **saved flows**, so if the project has none, it will tell you nothing was checked. That is not a pass. Record one first, or say plainly that there was nothing to verify.\n\n## Step 5: read the verdict honestly\n\n- **`verified: \"yes\"`**: proved. Say what held.\n- **`verified: \"no\"`**: the app is wrong, or your expectation was. Both are results. Report it.\n- **`verified: \"unknown\"`**: Reticle drove the app and could not tell. **Not a pass.** Never round it up, and never weaken the assertion until it goes green. That converts a real signal into a false one, which is the failure this product exists to prevent.\n\nA drive that ends without `act_and_wait` or `assert` has no result, however many tools it used.\n\n## When you are genuinely stuck\n\nStop and say which of these it is. A precise dead end beats a green report.\n\n| What you see | What it means |\n| --- | --- |\n| tools absent, `verify` says no saved flows | nothing to verify yet: record a flow, or report that |\n| `reticle_sessions` empty, port listening | the bundle has no SDK: restart the dev server after `init` |\n| `verified: \"unknown\"`, `outcome_unread` | the response body was not recorded: check the plugin options `init` wrote |\n| lease loads the page but never connects | the app refused to dial; on a non-localhost host it needs a pairing token as well as `allowNonLocalhost` |\n\n## Notes for approval-gated clients\n\nSome clients ask a human to approve each command. Two things reduce that to near zero:\n\n- **Keep commands plain.** `npx @reticlehq\u002Fserver init` matches a prefix rule; the same command wrapped in a subshell or a `$(…)` usually does not.\n- **Expect one prompt about the home directory.** The daemon keeps its state in `~\u002F.reticle`, which is outside the workspace. Approving that family once covers every later call.\n\nIf your client offers an autonomous or goal mode, this skill is written for it. Turn it on before starting rather than approving forty prompts. Approval fatigue is a real reason runs are abandoned half-installed, with the tools connected and nothing ever verified.\n\n## Report feedback\n\nReticle is built for agents, so your experience is the signal that decides what gets fixed, and it disappears when your context does. One call, then carry on:\n\n```\nreticle_feedback { kind: \"bug\" | \"gap\" | \"ambiguity\" | \"feature_request\" | \"improvement\", text: \"…\" }\n```\n\nUnreachable? `npx @reticlehq\u002Fserver feedback --agent --kind \u003Ckind> \"what happened\"`. Report defects in **Reticle**; a bug you find in the app under test is Reticle working, and belongs in your answer.\n",{"name":5,"license":15,"metadata":24,"description":7},{"version":25,"homepage":26,"repository":27},"2.13.1","https:\u002F\u002Fwww.reticle.sh","https:\u002F\u002Fgithub.com\u002Freticlehq\u002Freticle","feature\u002Fplatform\u002Ft001-review-scope-and-proposed-decisions","bc45c04601bb6d8318372e77414633cf51704880","skills\u002Freticle-main\u002Fskills\u002Fverify-unattended","https:\u002F\u002Fgithub.com\u002FFarhanS7\u002FEcom","https:\u002F\u002Fgithub.com\u002FFarhanS7","2026-10-16 16:37:01",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add FarhanS7\u002FEcom --skill verify-unattended",{"tool":40,"command":41},"bunx","bunx skills add FarhanS7\u002FEcom --skill verify-unattended",{"tool":43,"command":44},"pnpm","pnpm dlx skills add FarhanS7\u002FEcom --skill verify-unattended","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFarhanS7\u002FEcom\u002Fblob\u002Ffeature\u002Fplatform\u002Ft001-review-scope-and-proposed-decisions\u002Fskills\u002Freticle-main\u002Fskills\u002Fverify-unattended\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},"01M7EQAPBYJA3E1S84J0HPAHD2","verify-ui-change","Check that a change to a web app actually works in the running app before calling it done. Drives the real page and returns a pass\u002Ffail verdict with the request that fired, the state that moved, and the file:line to fix. Use after editing a component, a form, a route, or an API call; when you have said \"fixed\" but have not opened the app; when the user asks \"does it actually work?\"; or when a change looks right on screen and you cannot prove it.","https:\u002F\u002Fgithub.com\u002FFarhanS7\u002FEcom\u002Fblob\u002Ffeature\u002Fplatform\u002Ft001-review-scope-and-proposed-decisions\u002Fskills\u002Freticle-main\u002Fskills\u002Fverify-ui-change\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},"01M7EQAHE5AXACDQ4MHR66VTAR","test-error-states","Force the states a happy-path run never reaches (a failing API, an empty list, a slow request, a timeout, an expired session, a toast that auto-dismisses) and check the UI actually handles them. Use when error handling was written but never run, when a loading or empty state needs verifying, when a bug only happens on a slow connection, or when a timer, poll, debounce or retry needs testing without sleeping.","https:\u002F\u002Fgithub.com\u002FFarhanS7\u002FEcom\u002Fblob\u002Ffeature\u002Fplatform\u002Ft001-review-scope-and-proposed-decisions\u002Fskills\u002Freticle-main\u002Fskills\u002Ftest-error-states\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},"01M7EQAB4JWN05QGKJR21RZ145","replay-user-flows","Turn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model in the loop and no test code to write. Use when you have driven the same flow twice, when the user wants regression coverage without a Playwright suite, when a refactor needs proving against every existing journey, or when re-verifying by hand is costing a full drive every time.","https:\u002F\u002Fgithub.com\u002FFarhanS7\u002FEcom\u002Fblob\u002Ffeature\u002Fplatform\u002Ft001-review-scope-and-proposed-decisions\u002Fskills\u002Freticle-main\u002Fskills\u002Freplay-user-flows\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},"01M7EQA48T3SWMJJZ6JAG4K78D","install-and-verify","Verify that a web app change actually works by driving the running app from the inside (DOM, network, routing, console, framework state) instead of screenshots or guessing. Use after any user-facing change, when a fix is claimed but unproven, when a test passes but the UI is broken, or when you need a real verdict rather than \"looks right\". Also use to install and wire up Reticle in a project that does not have it yet.","https:\u002F\u002Fgithub.com\u002FFarhanS7\u002FEcom\u002Fblob\u002Ffeature\u002Fplatform\u002Ft001-review-scope-and-proposed-decisions\u002Fskills\u002Freticle-main\u002Fskills\u002Finstall-and-verify\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},"01M7EQ9YBFPBQH5NP8HQBPX067","fix-what-i-pointed-at","Pick up the bugs a human flagged by pointing at them in the running app, each arriving with the element, the note they typed, and the source file and line. Use when the user says they marked or flagged something, when starting a session on an app someone has been clicking through, when a designer or PM has left feedback in the UI, or when the user describes a problem as \"that button there\" without saying which file.","https:\u002F\u002Fgithub.com\u002FFarhanS7\u002FEcom\u002Fblob\u002Ffeature\u002Fplatform\u002Ft001-review-scope-and-proposed-decisions\u002Fskills\u002Freticle-main\u002Fskills\u002Ffix-what-i-pointed-at\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},"01M7EQ9RCFHGPJAZX6H8CP5962","false-green-tests","Find out why the tests pass but the app is broken. Catches false greens: a green suite over a feature that does not work, a mocked API standing in for a real one, an assertion that holds no matter what the app does, a click handler wired to nothing. Use when the suite is green and the user says it is broken, when a test never fails, when coverage looks fine but bugs still ship, or before trusting a passing run you did not watch.","https:\u002F\u002Fgithub.com\u002FFarhanS7\u002FEcom\u002Fblob\u002Ffeature\u002Fplatform\u002Ft001-review-scope-and-proposed-decisions\u002Fskills\u002Freticle-main\u002Fskills\u002Ffalse-green-tests\u002FSKILL.md",[],[]]