[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M749DQKTT58RTWRBTXGKVMMC":3,"skill-same:01M749DQKTT58RTWRBTXGKVMMC":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":15,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M749DQKTT58RTWRBTXGKVMMC","evidence-report",null,"Produce a standalone HTML report whose every claim is traced to its evidence. Use at a grilling convergence point, when reporting adversarial-review findings, at epic close-out, or whenever a decision, comparison, or set of findings needs to be presented to the user with sources they can check. Output is a single self-contained .html file in the repo, written in Traditional Chinese.","schola-cantorum\u002Fcantus","schola-cantorum","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F283400993?v=4","01M72671Q6RSVYYFN4JQ8QRSWT","01M72671QTZWY2WZ34AZF9AC3T",0,"MIT","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fevidence-report\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fevidence-report\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: evidence-report\ndescription: Produce a standalone HTML report whose every claim is traced to its evidence. Use at a grilling convergence point, when reporting adversarial-review findings, at epic close-out, or whenever a decision, comparison, or set of findings needs to be presented to the user with sources they can check. Output is a single self-contained .html file in the repo, written in Traditional Chinese.\n---\n\n# Evidence Report\n\nA report the user can audit. Every factual claim carries its source and a confidence tier, so the\nreader can tell what was verified from what was inferred without re-doing the work.\n\nReach for it when the output is a **decision, a comparison, or a body of findings** — the shapes\nwhere a reader needs to check the reasoning. Prose in the terminal is right for a status update.\n\n## Output contract\n\n- **One self-contained `.html` file.** All CSS and JS inline, images as `data:` URIs, **zero external\n  requests**. Standalone means it opens offline, from a file path, in five years.\n- **System font stack only.** A webfont CDN degrades silently offline, which discards the typography\n  the report was designed with. Use `-apple-system, \"Segoe UI\", \"PingFang TC\", \"Noto Sans TC\",\n  sans-serif` and a matching serif or mono stack for secondary roles.\n- **Location.** Epic-scoped: `.proj.specs\u002F\u003CNNNN-epic-slug>\u002Freports\u002F\u003Cslug>.html`. Project-scoped:\n  `.proj.specs\u002F_reports\u002F\u003Cslug>.html`. Committed.\n- **Language.** Traditional Chinese, Taiwan usage — see `docs\u002Fagents\u002Flanguage.md`. Technical terms\n  that Taiwan practice keeps in English stay in English.\n- **Naming.** Descriptive: `q1-pipeline-cadence.html`, not `report.html`. A rewrite becomes\n  `\u003Cslug>-v2.html`; keep the previous version.\n\n## The evidence table\n\nEvery report ends with a table listing each factual claim, its source, and its tier; every row maps\nto a claim made in the body. Three tiers,\nand the distinction between them is the point of the report:\n\n| Tier | Meaning |\n|---|---|\n| **已驗證** | Read the file, ran the command, saw the output. Cite `path:line` or the command. |\n| **推論** | Derived from verified facts, not directly observed. Say what it was derived from. |\n| **外部** | From the web or a document outside the repo. Cite the source. |\n\nTwo rules make the tiering worth trusting:\n\n- **Tier claims, not sentences.** If a paragraph mixes an observed fact with an inference, it holds\n  two claims and they get separate rows.\n- **State what the report does not claim.** A short section naming what is out of scope stops an\n  illustrative example from being read as a decision.\n\n## Structure\n\n1. **The answer first.** The recommendation or conclusion, before the reasoning.\n2. **The question restated.** What is actually being decided, and what depends on the answer.\n3. **The body.** Options, findings, or comparison — whatever the report is for.\n4. **The evidence chain.** Why the conclusion follows, as a traceable sequence rather than an\n   assertion.\n5. **The cost.** What the recommendation gives up. A report that lists only upside is not auditable.\n6. **The evidence table**, plus the out-of-scope note.\n7. **The decision the user has to make**, stated as a question they can answer in one line.\n\nMatch length to the decision: cover the substance, and merge sections 2–4 when they would only\nrestate each other, and add no filler sections or extra summaries. The answer, the cost, the\nevidence table and the out-of-scope note always appear.\n\n## Design\n\nDesign the page for its subject. The report is read once, carefully, by one person deciding\nsomething — that calls for typographic hierarchy, considered spacing, and a deliberate palette, not\ndecoration.\n\n- **Encode information in structure.** Numbered markers belong on an actual sequence; a severity\n  stripe belongs on something with severity. A structural device that encodes nothing is noise.\n- **Pick the neutral.** A grey biased slightly toward the accent reads as chosen; a pure mid-grey\n  reads as a default.\n- **Spend boldness once.** One accent, used where the reader's attention should land — usually the\n  recommendation. Everything else stays quiet.\n- **Both themes.** Define the full light palette on bare `:root`, redefine the tokens under\n  `@media (prefers-color-scheme: dark)`, and set an explicit `background` on `body`. A colour whose\n  only definition sits inside a media query renders one theme's text on the other theme's ground.\n- **Wide content scrolls in its own container.** Tables and diagrams get `overflow-x: auto`; the page\n  body never scrolls sideways.\n- **Avoid the generated look.** Cream grounds with a serif display and terracotta accent, an\n  off-white page background, near-black with one acid-green pop, purple-to-blue gradient heroes,\n  Inter or Space Grotesk as the safe face, emoji as section markers, everything centred, rounded\n  cards with an accent rail, italic accent words in headings, numbered \"01\u002F02\u002F03\" section labels,\n  monospace eyebrow labels, pill-shaped badges or buttons. Where the user names a direction, follow\n  it exactly.\n\n## Handing it over\n\nEach tier must be honest: an inference labelled 已驗證 is the one failure that makes the whole report\nworthless. Give the user the file path.\n","# Evidence Report\n\nA report the user can audit. Every factual claim carries its source and a confidence tier, so the\nreader can tell what was verified from what was inferred without re-doing the work.\n\nReach for it when the output is a **decision, a comparison, or a body of findings** — the shapes\nwhere a reader needs to check the reasoning. Prose in the terminal is right for a status update.\n\n## Output contract\n\n- **One self-contained `.html` file.** All CSS and JS inline, images as `data:` URIs, **zero external\n  requests**. Standalone means it opens offline, from a file path, in five years.\n- **System font stack only.** A webfont CDN degrades silently offline, which discards the typography\n  the report was designed with. Use `-apple-system, \"Segoe UI\", \"PingFang TC\", \"Noto Sans TC\",\n  sans-serif` and a matching serif or mono stack for secondary roles.\n- **Location.** Epic-scoped: `.proj.specs\u002F\u003CNNNN-epic-slug>\u002Freports\u002F\u003Cslug>.html`. Project-scoped:\n  `.proj.specs\u002F_reports\u002F\u003Cslug>.html`. Committed.\n- **Language.** Traditional Chinese, Taiwan usage — see `docs\u002Fagents\u002Flanguage.md`. Technical terms\n  that Taiwan practice keeps in English stay in English.\n- **Naming.** Descriptive: `q1-pipeline-cadence.html`, not `report.html`. A rewrite becomes\n  `\u003Cslug>-v2.html`; keep the previous version.\n\n## The evidence table\n\nEvery report ends with a table listing each factual claim, its source, and its tier; every row maps\nto a claim made in the body. Three tiers,\nand the distinction between them is the point of the report:\n\n| Tier | Meaning |\n|---|---|\n| **已驗證** | Read the file, ran the command, saw the output. Cite `path:line` or the command. |\n| **推論** | Derived from verified facts, not directly observed. Say what it was derived from. |\n| **外部** | From the web or a document outside the repo. Cite the source. |\n\nTwo rules make the tiering worth trusting:\n\n- **Tier claims, not sentences.** If a paragraph mixes an observed fact with an inference, it holds\n  two claims and they get separate rows.\n- **State what the report does not claim.** A short section naming what is out of scope stops an\n  illustrative example from being read as a decision.\n\n## Structure\n\n1. **The answer first.** The recommendation or conclusion, before the reasoning.\n2. **The question restated.** What is actually being decided, and what depends on the answer.\n3. **The body.** Options, findings, or comparison — whatever the report is for.\n4. **The evidence chain.** Why the conclusion follows, as a traceable sequence rather than an\n   assertion.\n5. **The cost.** What the recommendation gives up. A report that lists only upside is not auditable.\n6. **The evidence table**, plus the out-of-scope note.\n7. **The decision the user has to make**, stated as a question they can answer in one line.\n\nMatch length to the decision: cover the substance, and merge sections 2–4 when they would only\nrestate each other, and add no filler sections or extra summaries. The answer, the cost, the\nevidence table and the out-of-scope note always appear.\n\n## Design\n\nDesign the page for its subject. The report is read once, carefully, by one person deciding\nsomething — that calls for typographic hierarchy, considered spacing, and a deliberate palette, not\ndecoration.\n\n- **Encode information in structure.** Numbered markers belong on an actual sequence; a severity\n  stripe belongs on something with severity. A structural device that encodes nothing is noise.\n- **Pick the neutral.** A grey biased slightly toward the accent reads as chosen; a pure mid-grey\n  reads as a default.\n- **Spend boldness once.** One accent, used where the reader's attention should land — usually the\n  recommendation. Everything else stays quiet.\n- **Both themes.** Define the full light palette on bare `:root`, redefine the tokens under\n  `@media (prefers-color-scheme: dark)`, and set an explicit `background` on `body`. A colour whose\n  only definition sits inside a media query renders one theme's text on the other theme's ground.\n- **Wide content scrolls in its own container.** Tables and diagrams get `overflow-x: auto`; the page\n  body never scrolls sideways.\n- **Avoid the generated look.** Cream grounds with a serif display and terracotta accent, an\n  off-white page background, near-black with one acid-green pop, purple-to-blue gradient heroes,\n  Inter or Space Grotesk as the safe face, emoji as section markers, everything centred, rounded\n  cards with an accent rail, italic accent words in headings, numbered \"01\u002F02\u002F03\" section labels,\n  monospace eyebrow labels, pill-shaped badges or buttons. Where the user names a direction, follow\n  it exactly.\n\n## Handing it over\n\nEach tier must be honest: an inference labelled 已驗證 is the one failure that makes the whole report\nworthless. Give the user the file path.\n",{"name":5,"description":7},"main","3adbc786c457728f54420f3e73a321bb7e36bc15",".claude\u002Fskills\u002Fevidence-report","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus","https:\u002F\u002Fcantus.rtfm.diy\u002F","https:\u002F\u002Fgithub.com\u002Fschola-cantorum","2026-11-12 21:57:12",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add schola-cantorum\u002Fcantus --skill evidence-report",{"tool":37,"command":38},"bunx","bunx skills add schola-cantorum\u002Fcantus --skill evidence-report",{"tool":40,"command":41},"pnpm","pnpm dlx skills add schola-cantorum\u002Fcantus --skill evidence-report","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fevidence-report\u002FSKILL.md",true,[45],{"path":46,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":15},"LICENSE","许可证",1086,[50,58,66,74,82,90],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":54,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M749FSZ1CYNNSNXWVK8EGMTV","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":62,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M749FPQ8PE36Y9TBJ7KJES81","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwizard\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M749FM7AEMTHHC0VY7QTZRAR","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwayfinder\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M749FJE84F5E51DEQZZJZWV1","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwait-what\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M749F6YBDZPACWPC4JGSFSNH","to-tickets","Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fto-tickets\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M749F4SYDPQ8NRMWM0RG5HAN","to-spec","Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fto-spec\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fschola-cantorum\u002Fcantus\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fto-spec\u002FSKILL.md",[],[]]