[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EMC46H7411EB9DVQQPHESC":3,"skill-same:01M7EMC46H7411EB9DVQQPHESC":44},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7EMC46H7411EB9DVQQPHESC","verify",null,"Evidence before claims: before saying work is done, fixed or passing, run the proving command fresh, read its output and the git diff, and report VERIFIED and NOT VERIFIED items separately. Use before declaring any task complete and after any subagent reports success.","VolkovIlia\u002Fdeadlion-studio","VolkovIlia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43730119?v=4","01M7EM9F1A574SS7HEZRWMCA9C","Ilia Volkov","01M7EM9F1Z1DM8DEAT2WYZB6D0",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVolkovIlia\u002Fdeadlion-studio\u002Fblob\u002Fmain\u002Fplugins\u002Fdeadlion\u002Fskills\u002Fverify\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: verify\ndescription: \"Evidence before claims: before saying work is done, fixed or passing, run the proving command fresh, read its output and the git diff, and report VERIFIED and NOT VERIFIED items separately. Use before declaring any task complete and after any subagent reports success.\"\n---\n\n# Verify\n\nNo claim of done\u002Ffixed\u002Fpassing without fresh evidence from this turn.\n\n## Procedure\n1. Identify the command that proves the claim: the task's `Verify:` line, the test that\n   reproduces the bug, the acceptance criterion's check. If none exists, that is a\n   NOT VERIFIED item.\n2. Run it now. Earlier output, a subagent's pasted output, or \"it should work\" does not count.\n3. Read the output: exit code, pass\u002Ffail counts, warnings. Skipped or zero collected tests\n   are not a pass.\n4. `git status --short && git diff --stat` — the changed files match what is claimed; no\n   stray, missing or unintended files.\n5. Run the linter if the project uses one, `dl-size` on changed files and `dl-budget` on\n   changed programs (`${CLAUDE_SKILL_DIR}\u002F..\u002Fsuckless-code\u002Fscripts\u002F`), and `dl-contrast`\n   on changed token files (`${CLAUDE_SKILL_DIR}\u002F..\u002Fux-design\u002Fscripts\u002F`).\n6. Report.\n\n## Report format\n```\nVERIFIED: \u003Cclaim> — `\u003Ccommand>` → \u003Cobserved result>\nNOT VERIFIED: \u003Cclaim> — \u003Cwhat was not exercised and why>\n```\nPut every VERIFIED line first, then every NOT VERIFIED line. If anything is NOT VERIFIED,\ndo not call the work complete.\n\n## Honest reporting\nPartial work reported honestly is acceptable. Partial work reported as complete is a\nfailure. When something cannot be verified, downgrade the claim; never round it up.\n\n## Prohibited claims\n- \"Done\", \"fixed\", \"all tests pass\" without command output from this turn.\n- \"All tests pass\" when no test covers the changed lines.\n- \"Ready for review\" without proof.\n- Future tense as completion: \"I'll update…\", \"Next I need to…\".\n- Accepting a subagent's success report without checking its diff and rerunning its check.\n- Weakening a test, gate, threshold or verify command so it goes green.\n- Reporting part of the work (backend done, frontend missing) as the whole.\n\n## Claim → evidence\n| Claim | Required evidence this turn | Not enough |\n|---|---|---|\n| tests pass | test command output, 0 failures, >0 collected | earlier run, \"should pass\", a subagent's paste |\n| it builds | build command exit 0 | linter or type check passing |\n| bug fixed | the repro test failed before the fix and passes after | \"the code looks right\" |\n| program done | `make -C \u003Cdir> test` and `dl-budget \u003Cdir>` exit 0 | unit tests alone |\n| contract honoured | producer output matches the contract example; consumer fixture test passes | reading the code |\n| UI works | ui-verify PASS this turn: dl-tui blocks at 80×24 and 40×12 (terminal) or Playwright screenshots at 375\u002F768\u002F1280 (web), and dl-contrast exit 0 | \"looks right\", a description without a capture |\n","# Verify\n\nNo claim of done\u002Ffixed\u002Fpassing without fresh evidence from this turn.\n\n## Procedure\n1. Identify the command that proves the claim: the task's `Verify:` line, the test that\n   reproduces the bug, the acceptance criterion's check. If none exists, that is a\n   NOT VERIFIED item.\n2. Run it now. Earlier output, a subagent's pasted output, or \"it should work\" does not count.\n3. Read the output: exit code, pass\u002Ffail counts, warnings. Skipped or zero collected tests\n   are not a pass.\n4. `git status --short && git diff --stat` — the changed files match what is claimed; no\n   stray, missing or unintended files.\n5. Run the linter if the project uses one, `dl-size` on changed files and `dl-budget` on\n   changed programs (`${CLAUDE_SKILL_DIR}\u002F..\u002Fsuckless-code\u002Fscripts\u002F`), and `dl-contrast`\n   on changed token files (`${CLAUDE_SKILL_DIR}\u002F..\u002Fux-design\u002Fscripts\u002F`).\n6. Report.\n\n## Report format\n```\nVERIFIED: \u003Cclaim> — `\u003Ccommand>` → \u003Cobserved result>\nNOT VERIFIED: \u003Cclaim> — \u003Cwhat was not exercised and why>\n```\nPut every VERIFIED line first, then every NOT VERIFIED line. If anything is NOT VERIFIED,\ndo not call the work complete.\n\n## Honest reporting\nPartial work reported honestly is acceptable. Partial work reported as complete is a\nfailure. When something cannot be verified, downgrade the claim; never round it up.\n\n## Prohibited claims\n- \"Done\", \"fixed\", \"all tests pass\" without command output from this turn.\n- \"All tests pass\" when no test covers the changed lines.\n- \"Ready for review\" without proof.\n- Future tense as completion: \"I'll update…\", \"Next I need to…\".\n- Accepting a subagent's success report without checking its diff and rerunning its check.\n- Weakening a test, gate, threshold or verify command so it goes green.\n- Reporting part of the work (backend done, frontend missing) as the whole.\n\n## Claim → evidence\n| Claim | Required evidence this turn | Not enough |\n|---|---|---|\n| tests pass | test command output, 0 failures, >0 collected | earlier run, \"should pass\", a subagent's paste |\n| it builds | build command exit 0 | linter or type check passing |\n| bug fixed | the repro test failed before the fix and passes after | \"the code looks right\" |\n| program done | `make -C \u003Cdir> test` and `dl-budget \u003Cdir>` exit 0 | unit tests alone |\n| contract honoured | producer output matches the contract example; consumer fixture test passes | reading the code |\n| UI works | ui-verify PASS this turn: dl-tui blocks at 80×24 and 40×12 (terminal) or Playwright screenshots at 375\u002F768\u002F1280 (web), and dl-contrast exit 0 | \"looks right\", a description without a capture |\n",{"name":5,"description":7},"main","02aa71ce4bc4511265a1469ef79ed215a71f9b2f","plugins\u002Fdeadlion\u002Fskills\u002Fverify","https:\u002F\u002Fgithub.com\u002FVolkovIlia\u002Fdeadlion-studio","https:\u002F\u002Fgithub.com\u002FVolkovIlia","2026-10-15 18:45:06",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add VolkovIlia\u002Fdeadlion-studio --skill verify",{"tool":36,"command":37},"bunx","bunx skills add VolkovIlia\u002Fdeadlion-studio --skill verify",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VolkovIlia\u002Fdeadlion-studio --skill verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVolkovIlia\u002Fdeadlion-studio\u002Fblob\u002Fmain\u002Fplugins\u002Fdeadlion\u002Fskills\u002Fverify\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7EMCBYGSW1DZJP59294W9NP","write-plan","Turns approved product\u002Fdesign\u002Farchitecture artifacts or a clear request into plan.md: small ordered tasks, each with exact files, a test written first and a verification command. Use before implementing anything larger than a one-file change.","https:\u002F\u002Fgithub.com\u002FVolkovIlia\u002Fdeadlion-studio\u002Fblob\u002Fmain\u002Fplugins\u002Fdeadlion\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7EMC7ANMETP06JQ1158G7MS","workflow","Runs the deadlion pipeline (product → design → decompose → architecture → plan → build → review → verify) through plain-text artifacts in .dev-docs\u002F. Use when the user starts a new product, system, feature or multi-step change, or asks what to do next.","https:\u002F\u002Fgithub.com\u002FVolkovIlia\u002Fdeadlion-studio\u002Fblob\u002Fmain\u002Fplugins\u002Fdeadlion\u002Fskills\u002Fworkflow\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7EMBZTP61P22DG5A0EK9CXT","ux-design","Designs the user interface of a program at the lowest rung that serves the job — CLI, filter (dmenu\u002Ffzf style), terminal UI, native GUI or web — with flows, states, a key map, design tokens kept in config.def and numeric gates per rung, so every UI works alone and embeds; avoids generic AI-looking UI. Includes the dl-contrast checker. Writes design.md. Use when building or changing any user interface, screen, TUI, GUI, component or visual style.","https:\u002F\u002Fgithub.com\u002FVolkovIlia\u002Fdeadlion-studio\u002Fblob\u002Fmain\u002Fplugins\u002Fdeadlion\u002Fskills\u002Fux-design\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7EMBV6DXFPQ5B7DVJFADTRB","unix-design","Designs the internals of one program or sub-project as small single-purpose modules with plain-text interfaces, separated mechanism and policy, and one build\u002Frun command each, following the Unix philosophy. Writes arch.md. Use when designing a new feature's architecture inside a program, a CLI, module or data flow; for splitting a system into several programs use decompose.","https:\u002F\u002Fgithub.com\u002FVolkovIlia\u002Fdeadlion-studio\u002Fblob\u002Fmain\u002Fplugins\u002Fdeadlion\u002Fskills\u002Funix-design\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7EMBQ2M8RB244K803J257NP","ui-verify","Verifies a running UI against the gates in design.md — web pages in a real browser via the Playwright MCP (screenshots at 375\u002F768\u002F1280 px, console errors, axe scan, touch targets), terminal programs through dl-tui in a headless tmux (screens at 80×24, 40×12 and 20×5, NO_COLOR, key scripts per state, terminal restore, stdout purity), and token contrast with dl-contrast. Use after implementing or changing any UI, or when the user asks to check how a screen looks or works.","https:\u002F\u002Fgithub.com\u002FVolkovIlia\u002Fdeadlion-studio\u002Fblob\u002Fmain\u002Fplugins\u002Fdeadlion\u002Fskills\u002Fui-verify\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7EMBHXM6HQGPJ2J0BEVEEZ3","testing","Test strategy and execution: test-first, isolated unit tests, then integration, then regression; tests assert behaviour, boundaries and errors, never wiring or mock echoes; make test and test.sh for programs, fixture tests for contracts; memory-safe fixtures for large suites. Use when writing tests, choosing what to test, or when a test suite is slow, flaky or runs out of memory.","https:\u002F\u002Fgithub.com\u002FVolkovIlia\u002Fdeadlion-studio\u002Fblob\u002Fmain\u002Fplugins\u002Fdeadlion\u002Fskills\u002Ftesting\u002FSKILL.md",[],[]]