[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70FKYGVAEPDN9AF6F8PDY55":3,"skill-same:01M70FKYGVAEPDN9AF6F8PDY55":73},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M70FKYGVAEPDN9AF6F8PDY55","source-analysis",null,"Evaluate a single source across 7 structured fields (source type, authority, methodology, evidence quality, limitations, bias, bottom line) with an explicit citation recommendation.","jmlozano1990\u002FCowork-Starter-Kit","jmlozano1990","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F212240889?v=4","01M70FFEFRFH4C54MRVST1ZZFW","JmLozano","01M70FFEGEGDMH4RS95JKWH95M",6,"MIT","https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit\u002Fblob\u002Fmain\u002Fskills\u002Fsource-analysis\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"source analysis","source","analysis","type","can","single","bias","recommendation","for","evidence","line","how","critique","analyze","across","code","authority","claim","good","thinking","2026-11-10 10:12:30",false,"---\nname: source-analysis\ndescription: Evaluate a single source across 7 structured fields (source type, authority, methodology, evidence quality, limitations, bias, bottom line) with an explicit citation recommendation.\ntools: [claude-code]\ntrigger_examples:\n  - \"Evaluate \u002F critique \u002F analyze this paper\"\n  - \"How good is this source?\"\n  - \"Can I cite this?\"\n  - \"I'm thinking of citing [X] for [claim]\"\n---\n\n## When to use\n\nUse this skill when the user has a single source — a paper, article, book chapter, or preprint — and needs a structured evaluation of its credibility, authority, and citability. Source analysis produces a judgment, not a summary.\n\nDistinct from literature review and research synthesis: those skills work across multiple sources. Source analysis focuses entirely on one source and delivers a citation recommendation as its final output. Use it when the key question is \"Can I cite this? For what kinds of claims? With what caveats?\"\n\nIf the user shares multiple sources and wants comparison, prefer literature review or research synthesis instead.\n\n## Triggers\n\n- User says \"Evaluate \u002F critique \u002F analyze this paper\" or \"How good is this source?\" — highest-confidence direct invocation.\n- User pastes a single paper abstract or excerpt with no specific ask — proactively offer source analysis.\n- User asks \"Can I cite this?\" or \"Is this source any good?\" — offer source analysis with citation-recommendation framing.\n- User says \"I'm thinking of citing [X] for [claim]\" — offer source analysis with Bottom line tuned to the specific claim.\n\n## Instructions\n\n1. Read the provided source fully before beginning the evaluation.\n2. State the source type at the top of the output (Primary \u002F Secondary \u002F Tertiary) with a one-sentence justification so the user can recalibrate citation strategy before reading further.\n3. Complete all 7 fields in order. Do not skip or mark a field \"N\u002FA\" without explanation.\n4. **Source type** — Primary (original empirical data or argument), Secondary (review, synthesis, or commentary on primary sources), or Tertiary (meta-review of reviews, encyclopedias, textbooks). Justify in one sentence.\n5. **Authority** — author credentials, institutional affiliation, track record (h-index or key prior work if relevant), and domain fit. Note if the author is writing outside their primary field of expertise.\n6. **Methodology** — study design (empirical \u002F theoretical \u002F review \u002F meta-analysis), sample, and measures where applicable. Assess whether the method is appropriate for the main claim.\n7. **Evidence quality** — strength of evidence supporting the main claim. Does it converge with other studies or is it an isolated result? Note replication status if known.\n8. **Limitations** — distinguish what the author acknowledges and what the author omits. Every source has limitations; a complete analysis names both categories.\n9. **Bias assessment** — funding source, ideological framing, methodological narrowness, and motivated framing. State bias level explicitly (low \u002F moderate \u002F high) with reasoning.\n10. **Bottom line** — write a narrative judgment paragraph answering: Can this source be cited? For what kinds of claims? With what caveats? Apply the writing-profile rule from `## Writing-profile integration` to this paragraph.\n11. Apply the BibTeX extension if the user supplies citation keys: use `@key` references throughout.\n\n## Output format\n\nPlain GitHub-flavored markdown in the chat.\n\n**Source type declaration (required, at top):** `**Source type:** [Primary\u002FSecondary\u002FTertiary] — one-sentence justification.`\n\n**7 fields as labeled list:** Each field rendered as a `**Field name:**` bold-label line, with field content on the same or following line. Fields 1–6 are typically 1–3 sentences each. Use complete sentences, not bullets, within each field.\n\n**Bottom line:** A standalone paragraph (typically 100 words or more) that delivers the citation recommendation. This is the interpretive payoff of the analysis.\n\nNo tables by default — the 7 fields are a fixed schema, not a comparison matrix. No Obsidian `[[wikilinks]]`. No JSON or YAML sidecar. Portable across academic writing tools and plain-text editors.\n\n## Quality criteria\n\n1. Source type (primary\u002Fsecondary\u002Ftertiary) stated explicitly at top with one-sentence justification.\n2. All 7 fields populated — no field skipped or marked \"N\u002FA\" without explanation.\n3. Authority field addresses credentials, domain fit, and track record — not just the author's name.\n4. Methodology field describes design, sample, and measures where applicable.\n5. Limitations section distinguishes author-acknowledged from author-omitted limitations.\n6. Bias assessment is explicit (low \u002F moderate \u002F high) with reasoning.\n7. Bottom line delivers a citation recommendation — answers \"can I cite this? for what? with what caveats?\"\n\n## Anti-patterns\n\n- Summarizing the source instead of evaluating it — a good summary is not source analysis.\n- Accepting the author's framing uncritically — analysis must surface what the author is not saying.\n- Ignoring methodology — citing a 30-subject pilot and a 3000-subject RCT as equivalently authoritative.\n- No authority assessment — failing to note when a source is outside the author's field of expertise.\n- No limitations surfaced — every source has limitations; if none are listed, the analysis is incomplete.\n- Conflating primary with secondary — treating a review paper's claim as though it were original evidence.\n- No explicit bottom-line judgment — analysis must end with a citation recommendation, not drift into summary.\n\n## Example\n\n**Input:** Baddeley (2000). \"The Episodic Buffer: A new component of working memory?\" *Trends in Cognitive Sciences*, 4(11), 417–423.\n\n**Output:**\n\n```markdown\n# Source analysis: Baddeley (2000) — The Episodic Buffer\n\n**Source type:** Secondary (theoretical review article extending a prior model).\n\n**Authority:** Alan Baddeley — emeritus professor, University of York; co-originator of the working-memory model (Baddeley & Hitch 1974); h-index >130; this paper is within the author's primary research domain and extends his own theoretical framework.\n\n**Methodology:** Theoretical paper — no new empirical data. Synthesizes prior empirical findings (cross-modal binding, prose recall, amnesiac integration performance) to motivate a new model component. Argument structure: (1) limits of the original 3-component model, (2) empirical anomalies the buffer resolves, (3) buffer properties.\n\n**Evidence quality:** Claims are consistent with the cited empirical record at the time. The episodic buffer proposal has since been adopted as standard in the working-memory literature (see Baddeley 2012 for follow-up). However, direct empirical evidence for the buffer as a structurally distinct component (vs. an emergent property of executive attention) remains contested.\n\n**Limitations acknowledged by author:** \"The nature of the buffer is still to be determined\" — Baddeley notes the proposal is a placeholder for integrating capacity. Limits on buffer capacity and its relationship to long-term memory are left as open questions.\n\n**Limitations omitted by author:** The paper does not engage seriously with attentional-focus alternatives (Cowan 1999) that can account for the same empirical anomalies without requiring a new structural component. The buffer is presented as the resolution; alternative models are mentioned only briefly.\n\n**Bias assessment:** Low-to-moderate. The author is extending his own model — mild theoretical commitment bias. No funding-source concerns. Publication venue (*Trends in Cognitive Sciences*) is reputable and peer-reviewed.\n\n**Bottom line:** Citable as the canonical statement of the episodic buffer proposal. Appropriate for: (1) describing the 4-component working-memory model in its mature form, (2) grounding discussions of binding and integration in working memory. Caveat: when citing, acknowledge the buffer remains theoretically contested and Cowan's attentional-focus alternative should be mentioned in any thorough treatment.\n```\n\n## Writing-profile integration\n\nTwo-tier rule based on output section:\n\n- **Fields 1–6** (Source type, Authority, Methodology, Evidence quality, Limitations, Bias assessment): structured judgment — terse clauses, minimal prose. `context\u002Fwriting-profile.md` is not consulted; these fields are structured data.\n- **Bottom line:** Narrative judgment paragraph — full writing-profile consultation applies. Tone, sentence-length preferences, and pet peeves from `context\u002Fwriting-profile.md` apply to this paragraph only. The Bottom line typically exceeds 100 words, triggering the adapt-to-profile rule.\n\n## Example prompts\n\n- \"Analyze this paper: [paste abstract or filename].\"\n- \"Is this source credible and relevant to my research on [topic]?\"\n- \"Can I cite this for my claim about [X]?\"\n- \"What are the methodological strengths and limitations of this study?\"\n","## When to use\n\nUse this skill when the user has a single source — a paper, article, book chapter, or preprint — and needs a structured evaluation of its credibility, authority, and citability. Source analysis produces a judgment, not a summary.\n\nDistinct from literature review and research synthesis: those skills work across multiple sources. Source analysis focuses entirely on one source and delivers a citation recommendation as its final output. Use it when the key question is \"Can I cite this? For what kinds of claims? With what caveats?\"\n\nIf the user shares multiple sources and wants comparison, prefer literature review or research synthesis instead.\n\n## Triggers\n\n- User says \"Evaluate \u002F critique \u002F analyze this paper\" or \"How good is this source?\" — highest-confidence direct invocation.\n- User pastes a single paper abstract or excerpt with no specific ask — proactively offer source analysis.\n- User asks \"Can I cite this?\" or \"Is this source any good?\" — offer source analysis with citation-recommendation framing.\n- User says \"I'm thinking of citing [X] for [claim]\" — offer source analysis with Bottom line tuned to the specific claim.\n\n## Instructions\n\n1. Read the provided source fully before beginning the evaluation.\n2. State the source type at the top of the output (Primary \u002F Secondary \u002F Tertiary) with a one-sentence justification so the user can recalibrate citation strategy before reading further.\n3. Complete all 7 fields in order. Do not skip or mark a field \"N\u002FA\" without explanation.\n4. **Source type** — Primary (original empirical data or argument), Secondary (review, synthesis, or commentary on primary sources), or Tertiary (meta-review of reviews, encyclopedias, textbooks). Justify in one sentence.\n5. **Authority** — author credentials, institutional affiliation, track record (h-index or key prior work if relevant), and domain fit. Note if the author is writing outside their primary field of expertise.\n6. **Methodology** — study design (empirical \u002F theoretical \u002F review \u002F meta-analysis), sample, and measures where applicable. Assess whether the method is appropriate for the main claim.\n7. **Evidence quality** — strength of evidence supporting the main claim. Does it converge with other studies or is it an isolated result? Note replication status if known.\n8. **Limitations** — distinguish what the author acknowledges and what the author omits. Every source has limitations; a complete analysis names both categories.\n9. **Bias assessment** — funding source, ideological framing, methodological narrowness, and motivated framing. State bias level explicitly (low \u002F moderate \u002F high) with reasoning.\n10. **Bottom line** — write a narrative judgment paragraph answering: Can this source be cited? For what kinds of claims? With what caveats? Apply the writing-profile rule from `## Writing-profile integration` to this paragraph.\n11. Apply the BibTeX extension if the user supplies citation keys: use `@key` references throughout.\n\n## Output format\n\nPlain GitHub-flavored markdown in the chat.\n\n**Source type declaration (required, at top):** `**Source type:** [Primary\u002FSecondary\u002FTertiary] — one-sentence justification.`\n\n**7 fields as labeled list:** Each field rendered as a `**Field name:**` bold-label line, with field content on the same or following line. Fields 1–6 are typically 1–3 sentences each. Use complete sentences, not bullets, within each field.\n\n**Bottom line:** A standalone paragraph (typically 100 words or more) that delivers the citation recommendation. This is the interpretive payoff of the analysis.\n\nNo tables by default — the 7 fields are a fixed schema, not a comparison matrix. No Obsidian `[[wikilinks]]`. No JSON or YAML sidecar. Portable across academic writing tools and plain-text editors.\n\n## Quality criteria\n\n1. Source type (primary\u002Fsecondary\u002Ftertiary) stated explicitly at top with one-sentence justification.\n2. All 7 fields populated — no field skipped or marked \"N\u002FA\" without explanation.\n3. Authority field addresses credentials, domain fit, and track record — not just the author's name.\n4. Methodology field describes design, sample, and measures where applicable.\n5. Limitations section distinguishes author-acknowledged from author-omitted limitations.\n6. Bias assessment is explicit (low \u002F moderate \u002F high) with reasoning.\n7. Bottom line delivers a citation recommendation — answers \"can I cite this? for what? with what caveats?\"\n\n## Anti-patterns\n\n- Summarizing the source instead of evaluating it — a good summary is not source analysis.\n- Accepting the author's framing uncritically — analysis must surface what the author is not saying.\n- Ignoring methodology — citing a 30-subject pilot and a 3000-subject RCT as equivalently authoritative.\n- No authority assessment — failing to note when a source is outside the author's field of expertise.\n- No limitations surfaced — every source has limitations; if none are listed, the analysis is incomplete.\n- Conflating primary with secondary — treating a review paper's claim as though it were original evidence.\n- No explicit bottom-line judgment — analysis must end with a citation recommendation, not drift into summary.\n\n## Example\n\n**Input:** Baddeley (2000). \"The Episodic Buffer: A new component of working memory?\" *Trends in Cognitive Sciences*, 4(11), 417–423.\n\n**Output:**\n\n```markdown\n# Source analysis: Baddeley (2000) — The Episodic Buffer\n\n**Source type:** Secondary (theoretical review article extending a prior model).\n\n**Authority:** Alan Baddeley — emeritus professor, University of York; co-originator of the working-memory model (Baddeley & Hitch 1974); h-index >130; this paper is within the author's primary research domain and extends his own theoretical framework.\n\n**Methodology:** Theoretical paper — no new empirical data. Synthesizes prior empirical findings (cross-modal binding, prose recall, amnesiac integration performance) to motivate a new model component. Argument structure: (1) limits of the original 3-component model, (2) empirical anomalies the buffer resolves, (3) buffer properties.\n\n**Evidence quality:** Claims are consistent with the cited empirical record at the time. The episodic buffer proposal has since been adopted as standard in the working-memory literature (see Baddeley 2012 for follow-up). However, direct empirical evidence for the buffer as a structurally distinct component (vs. an emergent property of executive attention) remains contested.\n\n**Limitations acknowledged by author:** \"The nature of the buffer is still to be determined\" — Baddeley notes the proposal is a placeholder for integrating capacity. Limits on buffer capacity and its relationship to long-term memory are left as open questions.\n\n**Limitations omitted by author:** The paper does not engage seriously with attentional-focus alternatives (Cowan 1999) that can account for the same empirical anomalies without requiring a new structural component. The buffer is presented as the resolution; alternative models are mentioned only briefly.\n\n**Bias assessment:** Low-to-moderate. The author is extending his own model — mild theoretical commitment bias. No funding-source concerns. Publication venue (*Trends in Cognitive Sciences*) is reputable and peer-reviewed.\n\n**Bottom line:** Citable as the canonical statement of the episodic buffer proposal. Appropriate for: (1) describing the 4-component working-memory model in its mature form, (2) grounding discussions of binding and integration in working memory. Caveat: when citing, acknowledge the buffer remains theoretically contested and Cowan's attentional-focus alternative should be mentioned in any thorough treatment.\n```\n\n## Writing-profile integration\n\nTwo-tier rule based on output section:\n\n- **Fields 1–6** (Source type, Authority, Methodology, Evidence quality, Limitations, Bias assessment): structured judgment — terse clauses, minimal prose. `context\u002Fwriting-profile.md` is not consulted; these fields are structured data.\n- **Bottom line:** Narrative judgment paragraph — full writing-profile consultation applies. Tone, sentence-length preferences, and pet peeves from `context\u002Fwriting-profile.md` apply to this paragraph only. The Bottom line typically exceeds 100 words, triggering the adapt-to-profile rule.\n\n## Example prompts\n\n- \"Analyze this paper: [paste abstract or filename].\"\n- \"Is this source credible and relevant to my research on [topic]?\"\n- \"Can I cite this for my claim about [X]?\"\n- \"What are the methodological strengths and limitations of this study?\"\n",{"name":5,"tools":44,"description":7,"trigger_examples":46},[45],"claude-code",[47,48,49,50],"Evaluate \u002F critique \u002F analyze this paper","How good is this source?","Can I cite this?","I'm thinking of citing [X] for [claim]","main","3b46ce1bf0dafc2b8ad69a72e13e73aa538fb297","skills\u002Fsource-analysis",1,"https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit","https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit\u002Freleases\u002Flatest","https:\u002F\u002Fgithub.com\u002Fjmlozano1990","2026-11-01 23:54:10",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add jmlozano1990\u002FCowork-Starter-Kit --skill source-analysis",{"tool":65,"command":66},"bunx","bunx skills add jmlozano1990\u002FCowork-Starter-Kit --skill source-analysis",{"tool":68,"command":69},"pnpm","pnpm dlx skills add jmlozano1990\u002FCowork-Starter-Kit --skill source-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit\u002Fblob\u002Fmain\u002Fskills\u002Fsource-analysis\u002FSKILL.md",true,[],[74,84,93,101,109,118],{"skillNo":75,"name":76,"nameZh":6,"description":6,"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":39},"01M70FMH5856SZTHFW424V3KKV","my-shopping-helper","https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbrownfield\u002Fstale-skills\u002F.claude\u002Fskills\u002Fmy-shopping-helper\u002FSKILL.md",[],[80,81,82,83],"my shopping helper","my","helper","shopping",{"skillNo":85,"name":86,"nameZh":6,"description":6,"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":39},"01M70FMGA74PSF54WDPJ6DW74F","self-upgrade","https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbrownfield\u002Fmode-b\u002F.claude\u002Fskills\u002Fself-upgrade\u002FSKILL.md",[],[90,91,92],"self upgrade","self","upgrade",{"skillNo":94,"name":95,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":39},"01M70FMFER555AGCQMMABCGVP4","self-archive","https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbrownfield\u002Fmode-b\u002F.claude\u002Fskills\u002Fself-archive\u002FSKILL.md",[],[99,100,91],"archive","self archive",{"skillNo":102,"name":103,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":39},"01M70FMEKRATA5GX89TW5GTB62","self-apply","https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbrownfield\u002Fmode-b\u002F.claude\u002Fskills\u002Fself-apply\u002FSKILL.md",[],[107,108,91],"self apply","apply",{"skillNo":110,"name":111,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":39},"01M70FMDB1Z8JDVC1645B4PJFP","pull-updates","https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbrownfield\u002Fmode-b\u002F.claude\u002Fskills\u002Fpull-updates\u002FSKILL.md",[],[115,116,117],"pull updates","updates","pull",{"skillNo":119,"name":120,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":128,"publishedAt":39},"01M70FMCEMGNPHHRDPH3DXAYSW","email-drafting","https:\u002F\u002Fgithub.com\u002Fjmlozano1990\u002FCowork-Starter-Kit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbrownfield\u002Fmode-b\u002F.claude\u002Fskills\u002Femail-drafting\u002FSKILL.md",[123],{"categoryNo":124,"categoryName":125,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[129,130,131],"email","drafting","email drafting"]