[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EBBCVE9PPC5EGH8S1T2M4D":3,"skill-same:01M7EBBCVE9PPC5EGH8S1T2M4D":46},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":45},"01M7EBBCVE9PPC5EGH8S1T2M4D","verify",null,"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","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\u002F02-厂商系统提示词\u002Fsystem_prompts_leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fverify\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: verify\ndescription: Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.\ndisable-model-invocation: true\n---\n\n**Verification is runtime observation.** You build the app, run it,\ndrive it to where the changed code executes, and capture what you\nsee. That capture is your evidence. Nothing else is.\n\n**Don't run tests. Don't typecheck.** Running them here proves you\ncan run CI — not that the change works. Not as a warm-up,\nnot \"just to be sure,\" not as a regression sweep after. The time\ngoes to running the app instead.\n\n**Don't import-and-call.** `import { foo } from '.\u002Fsrc\u002F...'` then\n`console.log(foo(x))` is a unit test you wrote. The function did what\nthe function does — you knew that from reading it. The app never ran.\nWhatever calls `foo` in the real codebase ends at a CLI, a socket, or\na window. Go there.\n\n## Find the change\n\nThe scope is what you're verifying — usually a diff, sometimes just\n\"does X work.\" In a git repo, establish the full range (a branch may\nbe many commits, or the change may still be uncommitted):\n\n```bash\ngit log --oneline @{u}..              # count commits (if upstream set)\ngit diff @{u}.. --stat                # full range, not HEAD~1\ngit diff origin\u002FHEAD... --stat        # no upstream: committed vs base\ngit diff HEAD --stat                  # uncommitted: working tree vs HEAD\ngh pr diff                            # if in a PR context\n```\n\nState the commit count. Large diff truncating? Redirect to a file\nthen Read it. Repo but no diff from any of these → say so, stop.\n**No repo → the scope is whatever the user named; ask if they\ndidn't.**\n\n**The diff is ground truth. Any description is a claim about it.**\nRead both. If they disagree, that's a finding.\n\n## Surface\n\nThe surface is where a user — human or programmatic — meets the\nchange. That's where you observe.\n\n| Change reaches | Surface | You |\n|---|---|---|\n| CLI \u002F TUI | terminal | type the command, capture the pane — [example](examples\u002Fcli.md) |\n| Server \u002F API | socket | send the request, capture the response — [example](examples\u002Fserver.md) |\n| GUI | pixels | drive it under xvfb\u002FPlaywright, screenshot |\n| Library | package boundary | sample code through the public export — `import pkg`, not `import .\u002Fsrc\u002F...` |\n| Prompt \u002F agent config | the agent | run the agent, capture its behavior |\n| CI workflow | Actions | dispatch it, read the run |\n\n**Internal function? Not a surface.** Something in the repo calls it\nand that caller ends at one of the rows above. Follow it there. A\nbash security gate's surface isn't the function's return value — it's\nthe CLI prompting or auto-allowing when you type the command.\n\n**No runtime surface at all** — docs-only, type declarations with no\nemit, build config that produces no behavioral diff — report\n**SKIP — no runtime surface: (reason).** Don't run tests to fill\nthe space.\n\n**Tests in the diff are the author's evidence, not a surface.** CI\nruns them. You'd be re-running CI. Tests-only PR → SKIP, one line.\nMixed src+tests → verify the src, ignore the test files. Reading a\ntest to learn what to check is fine — it's a spec. But then go run\nthe app. Checking that assertions match source is code review.\n\n## Get a handle\n\n**Check `.claude\u002Fskills\u002F` first — even if you already know how to\nbuild and run.** A matching `verifier-*` skill is the repo's\nevidence-capture protocol: it wraps the session so a reviewer can\nreplay what you saw (recording, screenshots). Drive the surface\nwithout it and you get a verdict with no replay.\n\nSkills live at the repo root **and** in the package\u002Fapp dirs the\ndiff touches — in a monorepo the unlock for `apps\u002Fdesktop\u002F` is\nusually `apps\u002Fdesktop\u002F.claude\u002Fskills\u002F`, not the root. Probe both:\n\n```bash\nls .claude\u002Fskills\u002F                    # repo root\nls \u003Ctouched-dir>\u002F.claude\u002Fskills\u002F      # each dir level the diff names\n```\n\n- **`verifier-*` matching your surface** (CLI verifier for a CLI\n  change, etc.) → invoke it with the Skill tool and follow its\n  setup. Mismatched surface → skip that one, try the next. Stale\n  verifier (fails on mechanics unrelated to the change) → ask the\n  user whether to patch it; don't FAIL the change for verifier rot.\n- **`run-*` but no matching verifier** → use its build\u002Flaunch\n  primitives as your handle.\n- **Neither** → cold start from README\u002Fpackage.json\u002FMakefile. Timebox\n  ~15min. Stuck → BLOCKED with exactly where, plus a filled-in\n  `\u002Frun-skill-generator` prompt. Got through → **persist what you\n  learned**: create `.claude\u002Fskills\u002Fverify\u002FSKILL.md` at the level you\n  probed above — repo root for a single-package repo; the touched\n  package\u002Fapp dir (`apps\u002Fdesktop\u002F.claude\u002Fskills\u002Fverify\u002FSKILL.md`) in\n  a monorepo where verification is per-package — capturing the\n  build\u002Flaunch\u002Fdrive recipe that worked, so the next session skips\n  this cold start. Keep it short: the commands that worked, the\n  flows worth driving, any gotchas. A project verify skill already\n  exists → edit it only when it steered you wrong: a documented\n  command failed or turned out wrong, or a needed step it doesn't\n  cover. Routine learnings don't warrant an edit, and never rewrite\n  or reorganize existing content for style.\n\n## Drive it\n\nSmallest path that makes the changed code execute:\n\n- Changed a flag? Run with it.\n- Changed a handler? Hit that route.\n- Changed error handling? Trigger the error.\n- Changed an internal function? Find the CLI command \u002F request \u002F render\n  that reaches it. Run that.\n\n**Read your plan back before running.** If every step is build \u002F\ntypecheck \u002F run test file — you've planned a CI rerun, not a\nverification. Find a step that reaches the surface or report BLOCKED.\n\n**The verdict is table stakes. Your observations are the signal.**\nA PASS with three sharp \"hey, I noticed…\" lines is worth more than a\nbare PASS. You're the only reviewer who actually *ran* the thing —\nanything that made you pause, work around, or go \"huh\" is information\nthe author doesn't have. Don't filter for \"is this a bug.\" Filter for\n\"would I mention this if they were sitting next to me.\"\n\n**End-to-end, through the real interface.** Pieces passing in\nisolation doesn't mean the flow works — seams are where bugs hide.\nIf users click buttons, test by clicking buttons, not by curling the\nAPI underneath.\n\n**Destructive path?** If the change touches code that deletes,\npublishes, sends, or writes outside the workspace and there's no\ndry-run or safe target, don't drive it live. Verify what you can\naround it and say which path you didn't exercise and why.\n\n## Push on it\n\nThe claim checked out — that's the first half. Confirming is step\none, not the job. The description is what the author intended;\nyour value is what they didn't.\n\nYou know exactly what changed. Probe *around* it, at the same\nsurface you just drove:\n\n- **New flag \u002F option** → empty value, passed twice, combined with a\n  conflicting flag, typo'd (does the error name it?)\n- **New handler \u002F route** → wrong method, malformed body, missing\n  required field, oversized payload\n- **Changed error path** → the adjacent errors it didn't touch —\n  did the refactor catch them too, or only the one in the diff?\n- **Interactive \u002F TUI** → Ctrl-C mid-op, resize the pane, paste\n  garbage, rapid-fire the key, Esc at the wrong moment\n- **State \u002F persistence** → do it twice, do it with stale state\n  underneath, do it in two sessions at once\n- **Wander** → what's adjacent? What looked off while you were\n  confirming? Go back to it.\n\nThese aren't a checklist — pick the ones the change points at. Stop\nwhen you've covered the obvious adjacents or hit something worth a\n⚠️. A probe that finds nothing is still a step: \"🔍 passed `--from ''`\n→ clean `error: --from requires a value`, exit 2.\" That the author\ndidn't test it is exactly why it's worth knowing it holds.\n\nStill not a test run. You're at the surface, typing what a user\nwould type wrong.\n\n## Capture\n\nStdout, response bodies, screenshots, pane dumps. Captured output is\nevidence; your memory isn't. Something unexpected? Don't route around\nit — capture, note, decide if it's the change or the environment.\nUnrelated breakage is a finding, not noise.\n\nShared process state (tmux, ports, lockfiles) — isolate. `tmux -L\nname`, bind `:0`, `mktemp -d`. You share a namespace with your host.\n\n## Report\n\nInline, final message:\n\n```\n## Verification: \u003Cone-line what changed>\n\n**Verdict:** PASS | FAIL | BLOCKED | SKIP\n\n**Claim:** \u003Cwhat it's supposed to do — your read of the diff and\u002For\nthe stated claim; note any mismatch>\n\n**Method:** \u003Chow you got a handle — which verifier\u002Frun-skill, or\ncold start; what you launched>\n\n### Steps\n\nEach step is one thing you did to the **running app** and what it\nshowed. Build\u002Finstall\u002Fcheckout are setup, not steps. Test runs and\ntypecheck don't belong here — they're CI's output.\n\n1. ✅\u002F❌\u002F⚠️\u002F🔍 \u003Cwhat you did to the running app> → \u003Cwhat you observed>\n   \u003Cevidence: the app's own output — pane capture, response body,\n   screenshot>\n\n🔍 marks a probe — a step off the claim's happy path, trying to\nbreak it. At least one. A Steps list that's all ✅ and no 🔍 is a\nhappy-path replay: still PASS, but you stopped at the first half.\n\n**Screenshot \u002F sample:** \u003Cthe one frame a reviewer looks at to see\nthe feature — an image for GUI\u002FTUI, code block for library\u002FAPI;\nomit for build\u002Ftypes-only>\n\n### Findings\n\u003CThings you noticed. Not just bugs — friction, surprises, anything\na first-time user would trip on. \"Took three tries to find the right\nflag.\" \"Error message on typo was unhelpful.\" \"Default seems odd for\nthe common case.\" \"Works, but slower than I expected.\" Lower the bar:\nif it made you pause, it goes here. But the pause has to be yours,\nfrom running the app — not from reading the PR page. A red CI check,\na review comment, someone else's bot: visible to anyone already, and\nyou relaying it isn't an observation. Claim\u002Fdiff mismatch, pre-existing\nbreakage, and env notes also belong.\n\nEach probe gets a line here even when it held — \"🔍 empty `--from`\n→ clean error\" tells the author what *was* covered, which they\ncan't see from a bare PASS.\n\nLead with ⚠️ for lines worth interrupting the reviewer for; plain\nbullets are context. Empty is fine if nothing stuck out — but nothing\nsticking out is itself rare.>\n```\n\n**Evidence has to reach the reader.** A file path is only evidence\nif the person reading the report can open it. If the `SendUserFile`\ntool is in your toolset, you're on a remote surface where they\ncan't — send the screenshots and recordings with it and let the\nreport name what you sent. Without it, reference the path and keep\nthe evidence that matters inline — pane captures and response\nbodies travel in the report; a bare path only works when the reader\nshares your filesystem.\n\n**Verdicts:**\n- **PASS** — you ran the app, the change did what it should at its\n  surface. Not: tests pass, builds clean, code looks right.\n- **FAIL** — you ran it and it doesn't. Or it breaks something else.\n  Or claim and diff disagree materially.\n- **BLOCKED** — couldn't reach a state where the change is observable.\n  Build broke, env missing a dep, handle wouldn't come up. Not a\n  verdict on the change. Never report an approach blocked or\n  impossible until you've enumerated the skills along the touched\n  subtree — environment-specific unlocks (headless runners, login\n  helpers, VM harnesses) usually live there. Say exactly where it\n  stopped + `\u002Frun-skill-generator` prompt.\n- **SKIP** — no runtime surface exists. Docs-only, types-only,\n  tests-only. Nothing went wrong; there's just nothing here to run.\n  One line why.\n\nNo partial pass. \"3 of 4 passed\" is FAIL until 4 passes or is\nexplained away.\n\n**When in doubt, FAIL.** False PASS ships broken code; false FAIL\ncosts one more human look. Ambiguous output is FAIL with the raw\ncapture attached — don't interpret.\n","**Verification is runtime observation.** You build the app, run it,\ndrive it to where the changed code executes, and capture what you\nsee. That capture is your evidence. Nothing else is.\n\n**Don't run tests. Don't typecheck.** Running them here proves you\ncan run CI — not that the change works. Not as a warm-up,\nnot \"just to be sure,\" not as a regression sweep after. The time\ngoes to running the app instead.\n\n**Don't import-and-call.** `import { foo } from '.\u002Fsrc\u002F...'` then\n`console.log(foo(x))` is a unit test you wrote. The function did what\nthe function does — you knew that from reading it. The app never ran.\nWhatever calls `foo` in the real codebase ends at a CLI, a socket, or\na window. Go there.\n\n## Find the change\n\nThe scope is what you're verifying — usually a diff, sometimes just\n\"does X work.\" In a git repo, establish the full range (a branch may\nbe many commits, or the change may still be uncommitted):\n\n```bash\ngit log --oneline @{u}..              # count commits (if upstream set)\ngit diff @{u}.. --stat                # full range, not HEAD~1\ngit diff origin\u002FHEAD... --stat        # no upstream: committed vs base\ngit diff HEAD --stat                  # uncommitted: working tree vs HEAD\ngh pr diff                            # if in a PR context\n```\n\nState the commit count. Large diff truncating? Redirect to a file\nthen Read it. Repo but no diff from any of these → say so, stop.\n**No repo → the scope is whatever the user named; ask if they\ndidn't.**\n\n**The diff is ground truth. Any description is a claim about it.**\nRead both. If they disagree, that's a finding.\n\n## Surface\n\nThe surface is where a user — human or programmatic — meets the\nchange. That's where you observe.\n\n| Change reaches | Surface | You |\n|---|---|---|\n| CLI \u002F TUI | terminal | type the command, capture the pane — [example](examples\u002Fcli.md) |\n| Server \u002F API | socket | send the request, capture the response — [example](examples\u002Fserver.md) |\n| GUI | pixels | drive it under xvfb\u002FPlaywright, screenshot |\n| Library | package boundary | sample code through the public export — `import pkg`, not `import .\u002Fsrc\u002F...` |\n| Prompt \u002F agent config | the agent | run the agent, capture its behavior |\n| CI workflow | Actions | dispatch it, read the run |\n\n**Internal function? Not a surface.** Something in the repo calls it\nand that caller ends at one of the rows above. Follow it there. A\nbash security gate's surface isn't the function's return value — it's\nthe CLI prompting or auto-allowing when you type the command.\n\n**No runtime surface at all** — docs-only, type declarations with no\nemit, build config that produces no behavioral diff — report\n**SKIP — no runtime surface: (reason).** Don't run tests to fill\nthe space.\n\n**Tests in the diff are the author's evidence, not a surface.** CI\nruns them. You'd be re-running CI. Tests-only PR → SKIP, one line.\nMixed src+tests → verify the src, ignore the test files. Reading a\ntest to learn what to check is fine — it's a spec. But then go run\nthe app. Checking that assertions match source is code review.\n\n## Get a handle\n\n**Check `.claude\u002Fskills\u002F` first — even if you already know how to\nbuild and run.** A matching `verifier-*` skill is the repo's\nevidence-capture protocol: it wraps the session so a reviewer can\nreplay what you saw (recording, screenshots). Drive the surface\nwithout it and you get a verdict with no replay.\n\nSkills live at the repo root **and** in the package\u002Fapp dirs the\ndiff touches — in a monorepo the unlock for `apps\u002Fdesktop\u002F` is\nusually `apps\u002Fdesktop\u002F.claude\u002Fskills\u002F`, not the root. Probe both:\n\n```bash\nls .claude\u002Fskills\u002F                    # repo root\nls \u003Ctouched-dir>\u002F.claude\u002Fskills\u002F      # each dir level the diff names\n```\n\n- **`verifier-*` matching your surface** (CLI verifier for a CLI\n  change, etc.) → invoke it with the Skill tool and follow its\n  setup. Mismatched surface → skip that one, try the next. Stale\n  verifier (fails on mechanics unrelated to the change) → ask the\n  user whether to patch it; don't FAIL the change for verifier rot.\n- **`run-*` but no matching verifier** → use its build\u002Flaunch\n  primitives as your handle.\n- **Neither** → cold start from README\u002Fpackage.json\u002FMakefile. Timebox\n  ~15min. Stuck → BLOCKED with exactly where, plus a filled-in\n  `\u002Frun-skill-generator` prompt. Got through → **persist what you\n  learned**: create `.claude\u002Fskills\u002Fverify\u002FSKILL.md` at the level you\n  probed above — repo root for a single-package repo; the touched\n  package\u002Fapp dir (`apps\u002Fdesktop\u002F.claude\u002Fskills\u002Fverify\u002FSKILL.md`) in\n  a monorepo where verification is per-package — capturing the\n  build\u002Flaunch\u002Fdrive recipe that worked, so the next session skips\n  this cold start. Keep it short: the commands that worked, the\n  flows worth driving, any gotchas. A project verify skill already\n  exists → edit it only when it steered you wrong: a documented\n  command failed or turned out wrong, or a needed step it doesn't\n  cover. Routine learnings don't warrant an edit, and never rewrite\n  or reorganize existing content for style.\n\n## Drive it\n\nSmallest path that makes the changed code execute:\n\n- Changed a flag? Run with it.\n- Changed a handler? Hit that route.\n- Changed error handling? Trigger the error.\n- Changed an internal function? Find the CLI command \u002F request \u002F render\n  that reaches it. Run that.\n\n**Read your plan back before running.** If every step is build \u002F\ntypecheck \u002F run test file — you've planned a CI rerun, not a\nverification. Find a step that reaches the surface or report BLOCKED.\n\n**The verdict is table stakes. Your observations are the signal.**\nA PASS with three sharp \"hey, I noticed…\" lines is worth more than a\nbare PASS. You're the only reviewer who actually *ran* the thing —\nanything that made you pause, work around, or go \"huh\" is information\nthe author doesn't have. Don't filter for \"is this a bug.\" Filter for\n\"would I mention this if they were sitting next to me.\"\n\n**End-to-end, through the real interface.** Pieces passing in\nisolation doesn't mean the flow works — seams are where bugs hide.\nIf users click buttons, test by clicking buttons, not by curling the\nAPI underneath.\n\n**Destructive path?** If the change touches code that deletes,\npublishes, sends, or writes outside the workspace and there's no\ndry-run or safe target, don't drive it live. Verify what you can\naround it and say which path you didn't exercise and why.\n\n## Push on it\n\nThe claim checked out — that's the first half. Confirming is step\none, not the job. The description is what the author intended;\nyour value is what they didn't.\n\nYou know exactly what changed. Probe *around* it, at the same\nsurface you just drove:\n\n- **New flag \u002F option** → empty value, passed twice, combined with a\n  conflicting flag, typo'd (does the error name it?)\n- **New handler \u002F route** → wrong method, malformed body, missing\n  required field, oversized payload\n- **Changed error path** → the adjacent errors it didn't touch —\n  did the refactor catch them too, or only the one in the diff?\n- **Interactive \u002F TUI** → Ctrl-C mid-op, resize the pane, paste\n  garbage, rapid-fire the key, Esc at the wrong moment\n- **State \u002F persistence** → do it twice, do it with stale state\n  underneath, do it in two sessions at once\n- **Wander** → what's adjacent? What looked off while you were\n  confirming? Go back to it.\n\nThese aren't a checklist — pick the ones the change points at. Stop\nwhen you've covered the obvious adjacents or hit something worth a\n⚠️. A probe that finds nothing is still a step: \"🔍 passed `--from ''`\n→ clean `error: --from requires a value`, exit 2.\" That the author\ndidn't test it is exactly why it's worth knowing it holds.\n\nStill not a test run. You're at the surface, typing what a user\nwould type wrong.\n\n## Capture\n\nStdout, response bodies, screenshots, pane dumps. Captured output is\nevidence; your memory isn't. Something unexpected? Don't route around\nit — capture, note, decide if it's the change or the environment.\nUnrelated breakage is a finding, not noise.\n\nShared process state (tmux, ports, lockfiles) — isolate. `tmux -L\nname`, bind `:0`, `mktemp -d`. You share a namespace with your host.\n\n## Report\n\nInline, final message:\n\n```\n## Verification: \u003Cone-line what changed>\n\n**Verdict:** PASS | FAIL | BLOCKED | SKIP\n\n**Claim:** \u003Cwhat it's supposed to do — your read of the diff and\u002For\nthe stated claim; note any mismatch>\n\n**Method:** \u003Chow you got a handle — which verifier\u002Frun-skill, or\ncold start; what you launched>\n\n### Steps\n\nEach step is one thing you did to the **running app** and what it\nshowed. Build\u002Finstall\u002Fcheckout are setup, not steps. Test runs and\ntypecheck don't belong here — they're CI's output.\n\n1. ✅\u002F❌\u002F⚠️\u002F🔍 \u003Cwhat you did to the running app> → \u003Cwhat you observed>\n   \u003Cevidence: the app's own output — pane capture, response body,\n   screenshot>\n\n🔍 marks a probe — a step off the claim's happy path, trying to\nbreak it. At least one. A Steps list that's all ✅ and no 🔍 is a\nhappy-path replay: still PASS, but you stopped at the first half.\n\n**Screenshot \u002F sample:** \u003Cthe one frame a reviewer looks at to see\nthe feature — an image for GUI\u002FTUI, code block for library\u002FAPI;\nomit for build\u002Ftypes-only>\n\n### Findings\n\u003CThings you noticed. Not just bugs — friction, surprises, anything\na first-time user would trip on. \"Took three tries to find the right\nflag.\" \"Error message on typo was unhelpful.\" \"Default seems odd for\nthe common case.\" \"Works, but slower than I expected.\" Lower the bar:\nif it made you pause, it goes here. But the pause has to be yours,\nfrom running the app — not from reading the PR page. A red CI check,\na review comment, someone else's bot: visible to anyone already, and\nyou relaying it isn't an observation. Claim\u002Fdiff mismatch, pre-existing\nbreakage, and env notes also belong.\n\nEach probe gets a line here even when it held — \"🔍 empty `--from`\n→ clean error\" tells the author what *was* covered, which they\ncan't see from a bare PASS.\n\nLead with ⚠️ for lines worth interrupting the reviewer for; plain\nbullets are context. Empty is fine if nothing stuck out — but nothing\nsticking out is itself rare.>\n```\n\n**Evidence has to reach the reader.** A file path is only evidence\nif the person reading the report can open it. If the `SendUserFile`\ntool is in your toolset, you're on a remote surface where they\ncan't — send the screenshots and recordings with it and let the\nreport name what you sent. Without it, reference the path and keep\nthe evidence that matters inline — pane captures and response\nbodies travel in the report; a bare path only works when the reader\nshares your filesystem.\n\n**Verdicts:**\n- **PASS** — you ran the app, the change did what it should at its\n  surface. Not: tests pass, builds clean, code looks right.\n- **FAIL** — you ran it and it doesn't. Or it breaks something else.\n  Or claim and diff disagree materially.\n- **BLOCKED** — couldn't reach a state where the change is observable.\n  Build broke, env missing a dep, handle wouldn't come up. Not a\n  verdict on the change. Never report an approach blocked or\n  impossible until you've enumerated the skills along the touched\n  subtree — environment-specific unlocks (headless runners, login\n  helpers, VM harnesses) usually live there. Say exactly where it\n  stopped + `\u002Frun-skill-generator` prompt.\n- **SKIP** — no runtime surface exists. Docs-only, types-only,\n  tests-only. Nothing went wrong; there's just nothing here to run.\n  One line why.\n\nNo partial pass. \"3 of 4 passed\" is FAIL until 4 passes or is\nexplained away.\n\n**When in doubt, FAIL.** False PASS ships broken code; false FAIL\ncosts one more human look. Ambiguous output is FAIL with the raw\ncapture attached — don't interpret.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","02-厂商系统提示词\u002Fsystem_prompts_leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fverify",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":34,"prompt":44,"zipAvailable":24},[35,38,41],{"tool":36,"command":37},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill verify",{"tool":39,"command":40},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill verify",{"tool":42,"command":43},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F02-厂商系统提示词\u002Fsystem_prompts_leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fverify\u002FSKILL.md",[],[47,54,61,68,76,83],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7EXRM12046G0GM1WGMMFXCN","ci-cd-and-automation","Automates CI\u002FCD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fci-cd-and-automation\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7EXRFYYSJ3Y15AGPDDEWWQD","chrome-devtools","Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-devtools\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7EXR6EYPE4X5X1BTAE6QJRV","chrome-cdp","Drive a real Chrome via the Chrome DevTools Protocol (CDP). Ensures a\ndebuggable Chrome is running (launching it if needed) so the agent can\nnavigate, read page content, inspect the DOM, run JavaScript, and take\nscreenshots — without the user typing any launch command. Includes a\nfirst-class \"review a live running app\" flow: point Chrome at the app under\ndevelopment and inspect\u002Fscreenshot the REAL page (what a static-artifact tool\ncannot do). Backed by Glimpse and the chrome-devtools MCP server. Use when\nasked to \"use chrome\", \"open chrome\", \"drive my browser\", \"read the page in\nchrome\", \"review the running app\", \"screenshot the app\", or \"\u002Fchrome-cdp\".","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-cdp\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7EXR1Y7E79KQKG4J798XGH6","check-identity-pack","Run an AFP 100-point or AUSTRAC safe-harbour identity check over a set of documents, and report exactly what's missing. Use when the user asks to check identity documents, verify someone's ID for onboarding, or assess whether a document pack satisfies Australian identity requirements.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcheck-identity-pack\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7EXQXW7C7PGREJW9ZZTZ16H","changelog","Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchangelog\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"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":19},"01M7EXQMH2ZME3ANN8Q8MEWPFB","cellxgene-census","Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs\u002Fdownloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcellxgene-census\u002FSKILL.md",[],[]]