lidge-jun/codexclaw / plugins/codexclaw/skills/dev-visualizer
cxc-dev-visualizer
VerifiedUse for visual explanations and documents. Triggers: diagrams, charts, interactive models, HTML reports, infographics, 시각화, 그려줘, 문서 만들어줘, 보고서, PDF 생성.
assets/exhibit-recipes.json
View on GitHub{
"schemaVersion": 1,
"recipes": [
{
"version": 1,
"id": "policy-assumption-map",
"domain": "policy",
"readerQuestion": "Which policy assumptions are evidenced, and which remain hypotheses?",
"prerequisites": [
"Each proposition is quoted or paraphrased from a named evidence source.",
"Evidence edges and hypothesis edges are classified separately."
],
"requiredFields": ["sourceRefs", "data", "uncertainty", "caption", "accessibleText", "edges"],
"allowedEvidence": ["policy-text", "administrative-record", "expert-interview"],
"calculation": null,
"method": {
"kind": "evidence-tracing",
"description": "Trace each assumption to evidence and mark unsupported links as hypotheses without assigning scores."
},
"encoding": {"kind": "assumption-map", "labelField": "label"},
"misleadingAlternatives": [
"Scoring interview themes without a measured scale.",
"Drawing every relationship as equally evidenced."
],
"failureCases": [
"An evidence edge has no source reference.",
"A hypothesis is described as an established mechanism."
],
"staticStrategy": "Use a proposition table followed by separate evidence and hypothesis edge lists."
},
{
"version": 1,
"id": "business-waterfall",
"domain": "business",
"readerQuestion": "Which measured components explain the change from baseline to outcome?",
"prerequisites": [
"Components use one unit and reconcile to the stated outcome.",
"Positive and negative contributions are independently sourced."
],
"requiredFields": ["sourceRefs", "data", "caption", "accessibleText"],
"allowedEvidence": ["audited-financial-record", "management-accounting-record"],
"calculation": {
"kind": "additive-bridge",
"description": "Add signed component changes to the baseline using unrounded values."
},
"method": null,
"encoding": {"kind": "waterfall", "labelField": "label", "valueField": "value"},
"misleadingAlternatives": [
"Mixing percentages and currency in one bridge.",
"Using a waterfall when components overlap."
],
"failureCases": [
"Components do not reconcile.",
"A residual is hidden by rounding."
],
"staticStrategy": "Use a signed contribution table with baseline, components, outcome, unit, and sources."
},
{
"version": 1,
"id": "business-sensitivity",
"domain": "business",
"readerQuestion": "How does a modeled result change under explicit input assumptions?",
"prerequisites": [
"The formula and baseline assumptions are visible.",
"Scenarios change one declared input at a time or disclose combined changes."
],
"requiredFields": ["sourceRefs", "data", "uncertainty", "caption", "accessibleText"],
"allowedEvidence": ["modeled-scenario", "management-accounting-record"],
"calculation": {
"kind": "scenario-model",
"description": "Apply each declared scenario to the same transparent baseline model."
},
"method": null,
"encoding": {"kind": "sensitivity", "labelField": "label", "valueField": "value"},
"misleadingAlternatives": [
"Presenting scenarios as forecasts.",
"Changing several hidden assumptions between scenarios."
],
"failureCases": [
"Assumptions are omitted.",
"Scenario values use different formulas."
],
"staticStrategy": "Use a scenario table with baseline, changed assumption, modeled result, and limitation."
},
{
"version": 1,
"id": "ux-journey-evidence",
"domain": "ux",
"readerQuestion": "Where does observed user friction occur in the journey?",
"prerequisites": [
"Journey stages come from observed sessions or transcripts.",
"Each friction statement points to evidence rather than a severity score invented by the author."
],
"requiredFields": ["sourceRefs", "data", "uncertainty", "caption", "accessibleText", "edges"],
"allowedEvidence": ["usability-session", "support-transcript", "field-observation"],
"calculation": null,
"method": {
"kind": "journey-evidence-synthesis",
"description": "Order sourced observations by task stage and distinguish observed handoffs from hypotheses."
},
"encoding": {"kind": "journey", "labelField": "label"},
"misleadingAlternatives": [
"Converting a small interview sample into a numerical severity ranking.",
"Inferring dropout from a single quote."
],
"failureCases": [
"A stage has no evidence anchor.",
"Researcher interpretation is shown as direct observation."
],
"staticStrategy": "Use an ordered journey table with evidence references and a separate hypothesis note."
},
{
"version": 1,
"id": "ux-cohort-comparison",
"domain": "ux",
"readerQuestion": "How do measured outcomes differ between comparable cohorts?",
"prerequisites": [
"Cohorts use the same inclusion window and outcome definition.",
"The denominator for each comparison is explicit."
],
"requiredFields": ["sourceRefs", "data", "denominator", "uncertainty", "caption", "accessibleText"],
"allowedEvidence": ["product-analytics-export", "experiment-record"],
"calculation": {
"kind": "cohort-rate",
"description": "Compare measured cohort outcomes against the declared eligible population."
},
"method": null,
"encoding": {"kind": "cohort", "labelField": "label", "valueField": "value"},
"misleadingAlternatives": [
"Comparing cohorts with different windows.",
"Calling an observational difference causal."
],
"failureCases": [
"The denominator is absent.",
"Assignment or selection differences are hidden."
],
"staticStrategy": "Use an aligned cohort table with counts, common outcome definition, denominator, and uncertainty."
},
{
"version": 1,
"id": "science-intervals",
"domain": "science",
"readerQuestion": "What estimates and uncertainty intervals did the studies report?",
"prerequisites": [
"Every interval uses the same confidence or credible level.",
"Estimate, lower bound, upper bound, unit, and source are available."
],
"requiredFields": ["sourceRefs", "data", "uncertainty", "caption", "accessibleText"],
"allowedEvidence": ["peer-reviewed-study", "registered-analysis"],
"calculation": {
"kind": "interval-comparison",
"description": "Display reported point estimates with their reported lower and upper bounds without recomputing missing intervals."
},
"method": null,
"encoding": {"kind": "interval", "labelField": "label", "valueField": "value"},
"misleadingAlternatives": [
"Showing point estimates without uncertainty.",
"Treating overlapping intervals as a significance test."
],
"failureCases": [
"An interval does not contain its estimate.",
"Interval levels differ without disclosure."
],
"staticStrategy": "Use a study table with estimate, interval bounds, interval level, unit, and source."
},
{
"version": 1,
"id": "science-heterogeneity",
"domain": "science",
"readerQuestion": "Are the estimates compatible enough to summarize together?",
"prerequisites": [
"Population, intervention, outcome, and time window compatibility are assessed.",
"A pooled estimate is shown only when compatibility is declared."
],
"requiredFields": ["sourceRefs", "data", "uncertainty", "caption", "accessibleText"],
"allowedEvidence": ["peer-reviewed-study", "systematic-review-record"],
"calculation": {
"kind": "heterogeneity-review",
"description": "Compare estimates and compatibility metadata before any pooled summary."
},
"method": null,
"encoding": {"kind": "heterogeneity", "labelField": "label", "valueField": "value"},
"misleadingAlternatives": [
"Pooling incompatible outcomes.",
"Hiding study-level differences behind one mean."
],
"failureCases": [
"Compatibility is declared incompatible while pooled is true.",
"Study definitions are absent."
],
"staticStrategy": "Use a study comparison table and state whether pooling was performed and why."
},
{
"version": 1,
"id": "history-chronology-provenance",
"domain": "history",
"readerQuestion": "What happened in sequence, and which source supports each event?",
"prerequisites": [
"Dates retain their original precision.",
"Conflicting accounts remain visible instead of being silently reconciled."
],
"requiredFields": ["sourceRefs", "data", "uncertainty", "caption", "accessibleText", "edges"],
"allowedEvidence": ["primary-document", "archival-catalog", "scholarly-secondary-source"],
"calculation": null,
"method": {
"kind": "chronology-with-provenance",
"description": "Order sourced events while preserving date precision, provenance, and disputed interpretation."
},
"encoding": {"kind": "timeline", "labelField": "label"},
"misleadingAlternatives": [
"Converting an approximate date into an exact day.",
"Drawing temporal sequence as proof of causation."
],
"failureCases": [
"An event has no source reference.",
"A disputed interpretation is presented as settled fact."
],
"staticStrategy": "Use a chronology table with date precision, event, provenance, and dispute note."
},
{
"version": 1,
"id": "operations-process-evidence",
"domain": "operations",
"readerQuestion": "Where do observed process handoffs create delay or rework?",
"prerequisites": [
"Steps and handoffs are observed or documented.",
"Proposed causes are marked as hypotheses until tested."
],
"requiredFields": ["sourceRefs", "data", "uncertainty", "caption", "accessibleText", "edges"],
"allowedEvidence": ["process-observation", "workflow-log", "standard-operating-procedure"],
"calculation": null,
"method": {
"kind": "process-tracing",
"description": "Trace documented steps and classify each connection as evidence or hypothesis."
},
"encoding": {"kind": "process", "labelField": "label"},
"misleadingAlternatives": [
"Treating the designed process as the observed process.",
"Assigning numerical efficiency scores without a measured scale."
],
"failureCases": [
"An observed handoff lacks a source.",
"A suspected cause is encoded as evidence."
],
"staticStrategy": "Use a step table and separate observed handoffs from causal hypotheses."
},
{
"version": 1,
"id": "operations-latency",
"domain": "operations",
"readerQuestion": "How does service latency vary across reported percentiles?",
"prerequisites": [
"Percentiles use one population, window, and unit.",
"The request count and observation period are stated."
],
"requiredFields": ["sourceRefs", "data", "denominator", "uncertainty", "caption", "accessibleText"],
"allowedEvidence": ["workflow-log", "monitoring-export"],
"calculation": {
"kind": "percentile-summary",
"description": "Report observed percentile values from the same request population without averaging percentiles."
},
"method": null,
"encoding": {"kind": "latency", "labelField": "label", "valueField": "value"},
"misleadingAlternatives": [
"Reporting only the mean for a skewed latency distribution.",
"Comparing percentiles from different time windows."
],
"failureCases": [
"The request denominator is missing.",
"Percentile labels and values come from different populations."
],
"staticStrategy": "Use a percentile table with value, unit, request count, observation window, and source."
}
],
"instances": [
{
"recipeId": "policy-assumption-map",
"sourceRefs": ["POL-TEXT-1", "POL-ADMIN-1"],
"evidenceType": "policy-text",
"data": {
"rows": [
{"id": "eligibility", "label": "Eligibility rule", "description": "The illustrative policy text limits eligibility to registered sites.", "sourceRefs": ["POL-TEXT-1"]},
{"id": "uptake", "label": "Expected uptake", "description": "The illustrative administrative record reports prior enrollment, not future uptake.", "sourceRefs": ["POL-ADMIN-1"]},
{"id": "capacity", "label": "Delivery capacity", "description": "No direct capacity measurement is supplied in this illustrative example.", "sourceRefs": ["POL-TEXT-1"]}
],
"analysis": {"claimType": "hypothesis", "design": "descriptive", "pooled": false, "poolingCompatibility": "not-applicable"},
"assumptions": ["The fictional records are used only to demonstrate evidence and hypothesis labels."]
},
"units": "not-applicable",
"denominator": null,
"uncertainty": {"kind": "qualitative-limit", "description": "Future uptake and operational capacity are not measured."},
"caption": "Illustrative policy assumption map; evidence edges and hypotheses are intentionally distinct.",
"accessibleText": "The eligibility rule is documented. Prior enrollment informs but does not establish future uptake. Capacity remains unmeasured.",
"edges": [
{"from": "eligibility", "to": "uptake", "type": "evidence", "label": "The rule defines the population eligible to enroll.", "sourceRefs": ["POL-TEXT-1"]},
{"from": "uptake", "to": "capacity", "type": "hypothesis", "label": "Higher uptake may require additional delivery capacity.", "sourceRefs": []}
]
},
{
"recipeId": "business-waterfall",
"sourceRefs": ["BIZ-LEDGER-1"],
"evidenceType": "management-accounting-record",
"data": {
"rows": [
{"id": "baseline", "label": "Baseline operating result", "value": 420, "role": "baseline", "sourceRefs": ["BIZ-LEDGER-1"]},
{"id": "volume", "label": "Volume contribution", "value": 70, "role": "delta", "sourceRefs": ["BIZ-LEDGER-1"]},
{"id": "price", "label": "Price contribution", "value": 25, "role": "delta", "sourceRefs": ["BIZ-LEDGER-1"]},
{"id": "service", "label": "Service cost contribution", "value": -35, "role": "delta", "sourceRefs": ["BIZ-LEDGER-1"]},
{"id": "outcome", "label": "Outcome operating result", "value": 480, "role": "total", "sourceRefs": ["BIZ-LEDGER-1"]}
],
"analysis": {"claimType": "descriptive", "design": "descriptive", "pooled": false, "poolingCompatibility": "not-applicable"},
"assumptions": []
},
"units": "illustrative USD thousands",
"denominator": null,
"uncertainty": null,
"caption": "Illustrative operating-result bridge using fictional management-accounting values.",
"accessibleText": "A baseline of 420 increases by 70 and 25, then decreases by 35, all in illustrative thousands of US dollars.",
"edges": []
},
{
"recipeId": "business-sensitivity",
"sourceRefs": ["BIZ-MODEL-1"],
"evidenceType": "modeled-scenario",
"data": {
"rows": [
{"id": "low", "label": "Lower demand", "value": 310, "scenario": "620 thousand units at USD 0.50 margin", "sourceRefs": ["BIZ-MODEL-1"]},
{"id": "base", "label": "Baseline demand", "value": 360, "scenario": "720 thousand units at USD 0.50 margin", "sourceRefs": ["BIZ-MODEL-1"]},
{"id": "high", "label": "Higher demand", "value": 415, "scenario": "830 thousand units at USD 0.50 margin", "sourceRefs": ["BIZ-MODEL-1"]}
],
"analysis": {"claimType": "hypothesis", "design": "modeled", "pooled": false, "poolingCompatibility": "not-applicable"},
"assumptions": ["Result in USD thousands = demand in thousands of units multiplied by USD 0.50 margin per unit.", "Only demand changes across the three illustrative scenarios; fixed costs are excluded."]
},
"units": "illustrative USD thousands",
"denominator": null,
"uncertainty": {"kind": "assumption", "description": "Scenario outputs are model results, not forecasts or observations."},
"caption": "Illustrative demand sensitivity under a fixed fictional margin assumption.",
"accessibleText": "Modeled operating results are 310, 360, and 415 illustrative thousands of US dollars as demand moves from lower to baseline to higher.",
"edges": []
},
{
"recipeId": "ux-journey-evidence",
"sourceRefs": ["UX-SESSION-1", "UX-SUPPORT-1"],
"evidenceType": "usability-session",
"data": {
"rows": [
{"id": "discover", "label": "Discover eligibility", "stage": "Entry", "description": "Illustrative participants looked for eligibility before starting.", "sourceRefs": ["UX-SESSION-1"]},
{"id": "prepare", "label": "Prepare documents", "stage": "Preparation", "description": "Illustrative support records mention uncertainty about accepted documents.", "sourceRefs": ["UX-SUPPORT-1"]},
{"id": "submit", "label": "Submit application", "stage": "Submission", "description": "The supplied fictional sessions do not measure completion rate.", "sourceRefs": ["UX-SESSION-1"]}
],
"analysis": {"claimType": "hypothesis", "design": "observational", "pooled": false, "poolingCompatibility": "not-applicable"},
"assumptions": []
},
"units": "not-applicable",
"denominator": null,
"uncertainty": {"kind": "qualitative-limit", "description": "The small fictional session set does not estimate prevalence."},
"caption": "Illustrative journey evidence from fictional usability and support records.",
"accessibleText": "Observed evidence concerns eligibility discovery and document preparation. A link to submission completion remains a hypothesis.",
"edges": [
{"from": "discover", "to": "prepare", "type": "evidence", "label": "Participants moved from checking eligibility to gathering documents.", "sourceRefs": ["UX-SESSION-1"]},
{"from": "prepare", "to": "submit", "type": "hypothesis", "label": "Document uncertainty may reduce successful submission.", "sourceRefs": []}
]
},
{
"recipeId": "ux-cohort-comparison",
"sourceRefs": ["UX-ANALYTICS-1"],
"evidenceType": "product-analytics-export",
"data": {
"rows": [
{"id": "guided", "label": "Guided flow completions", "value": 62, "sourceRefs": ["UX-ANALYTICS-1"]},
{"id": "standard", "label": "Standard flow completions", "value": 48, "sourceRefs": ["UX-ANALYTICS-1"]}
],
"analysis": {"claimType": "associational", "design": "observational", "pooled": false, "poolingCompatibility": "compatible"},
"assumptions": ["Both fictional cohorts use the same seven-day completion window."]
},
"units": "completed accounts",
"denominator": {"value": 80, "unit": "eligible accounts per cohort", "label": "Illustrative eligible population in each cohort"},
"uncertainty": {"kind": "sampling-error", "description": "No random assignment is claimed; selection differences may explain part of the association."},
"caption": "Illustrative observational cohort comparison; the difference is not labeled causal.",
"accessibleText": "In fictional cohorts of 80 eligible accounts each, 62 guided-flow accounts and 48 standard-flow accounts completed within seven days.",
"edges": []
},
{
"recipeId": "science-intervals",
"sourceRefs": ["SCI-STUDY-A", "SCI-STUDY-B"],
"evidenceType": "peer-reviewed-study",
"data": {
"rows": [
{"id": "study-a", "label": "Illustrative Study A", "value": 1.4, "lower": 0.8, "upper": 2.0, "sourceRefs": ["SCI-STUDY-A"]},
{"id": "study-b", "label": "Illustrative Study B", "value": 0.9, "lower": 0.3, "upper": 1.5, "sourceRefs": ["SCI-STUDY-B"]}
],
"analysis": {"claimType": "associational", "design": "randomized", "pooled": false, "poolingCompatibility": "unknown"},
"assumptions": []
},
"units": "illustrative outcome points",
"denominator": null,
"uncertainty": {"kind": "confidence-interval", "description": "Both fictional intervals are shown as reported 95 percent confidence intervals.", "lower": 0.3, "upper": 2.0},
"caption": "Illustrative study estimates with fictional 95 percent confidence intervals.",
"accessibleText": "Study A estimates 1.4 with interval 0.8 to 2.0. Study B estimates 0.9 with interval 0.3 to 1.5. Values are illustrative.",
"edges": []
},
{
"recipeId": "science-heterogeneity",
"sourceRefs": ["SCI-REVIEW-1", "SCI-REVIEW-2"],
"evidenceType": "systematic-review-record",
"data": {
"rows": [
{"id": "trial-one", "label": "Illustrative trial one", "value": 1.2, "description": "Fictional adult population, outcome measured after four weeks.", "sourceRefs": ["SCI-REVIEW-1"]},
{"id": "trial-two", "label": "Illustrative trial two", "value": 2.1, "description": "Fictional adult population, outcome measured after twelve weeks.", "sourceRefs": ["SCI-REVIEW-2"]}
],
"analysis": {"claimType": "associational", "design": "randomized", "pooled": false, "poolingCompatibility": "incompatible"},
"assumptions": ["The fictional outcomes use materially different follow-up windows, so no pooled estimate is shown."]
},
"units": "illustrative standardized effect",
"denominator": null,
"uncertainty": {"kind": "qualitative-limit", "description": "Outcome timing differs; the estimates are displayed separately and not pooled."},
"caption": "Illustrative heterogeneous estimates shown separately because declared compatibility is insufficient.",
"accessibleText": "Two fictional trial estimates are 1.2 and 2.1. They are not pooled because the outcome windows differ.",
"edges": []
},
{
"recipeId": "history-chronology-provenance",
"sourceRefs": ["HIST-LETTER-1", "HIST-CATALOG-1"],
"evidenceType": "primary-document",
"data": {
"rows": [
{"id": "proposal", "label": "Proposal recorded", "date": "Spring 1912 (illustrative)", "description": "A fictional letter proposes a regional archive.", "sourceRefs": ["HIST-LETTER-1"]},
{"id": "catalog", "label": "Catalog entry created", "date": "1913 (illustrative)", "description": "A fictional catalog entry records the archive collection.", "sourceRefs": ["HIST-CATALOG-1"]},
{"id": "influence", "label": "Influence on later practice", "date": "After 1913 (illustrative)", "description": "The supplied fictional sources do not establish later influence.", "sourceRefs": ["HIST-CATALOG-1"]}
],
"analysis": {"claimType": "hypothesis", "design": "historical", "pooled": false, "poolingCompatibility": "not-applicable"},
"assumptions": []
},
"units": "calendar date with preserved precision",
"denominator": null,
"uncertainty": {"kind": "qualitative-limit", "description": "The proposal date is season-level, and later influence is not established."},
"caption": "Illustrative chronology preserving fictional date precision and provenance.",
"accessibleText": "A fictional proposal appears in spring 1912 and a fictional catalog entry in 1913. Later influence remains a hypothesis.",
"edges": [
{"from": "proposal", "to": "catalog", "type": "evidence", "label": "The catalog entry follows the proposal in the fictional record.", "sourceRefs": ["HIST-LETTER-1", "HIST-CATALOG-1"]},
{"from": "catalog", "to": "influence", "type": "hypothesis", "label": "The collection may have influenced later archival practice.", "sourceRefs": []}
]
},
{
"recipeId": "operations-process-evidence",
"sourceRefs": ["OPS-OBS-1", "OPS-LOG-1"],
"evidenceType": "process-observation",
"data": {
"rows": [
{"id": "intake", "label": "Request intake", "description": "Illustrative requests enter one queue.", "sourceRefs": ["OPS-OBS-1"]},
{"id": "review", "label": "Manual review", "description": "The fictional workflow log records returns for missing fields.", "sourceRefs": ["OPS-LOG-1"]},
{"id": "approve", "label": "Approval", "description": "The supplied fictional records do not isolate the cause of review delay.", "sourceRefs": ["OPS-LOG-1"]}
],
"analysis": {"claimType": "hypothesis", "design": "observational", "pooled": false, "poolingCompatibility": "not-applicable"},
"assumptions": []
},
"units": "not-applicable",
"denominator": null,
"uncertainty": {"kind": "qualitative-limit", "description": "Observed rework is documented, but its cause is not isolated."},
"caption": "Illustrative operations process with observed and hypothetical links separated.",
"accessibleText": "Requests move from intake to manual review and approval. Returns for missing fields are observed; their role in approval delay remains a hypothesis.",
"edges": [
{"from": "intake", "to": "review", "type": "evidence", "label": "Requests enter manual review after intake.", "sourceRefs": ["OPS-OBS-1"]},
{"from": "review", "to": "approve", "type": "hypothesis", "label": "Missing-field rework may contribute to approval delay.", "sourceRefs": []}
]
},
{
"recipeId": "operations-latency",
"sourceRefs": ["OPS-LAT-1"],
"evidenceType": "monitoring-export",
"data": {
"rows": [
{"id": "p50", "label": "P50", "value": 180, "percentile": 50, "sourceRefs": ["OPS-LAT-1"]},
{"id": "p95", "label": "P95", "value": 620, "percentile": 95, "sourceRefs": ["OPS-LAT-1"]},
{"id": "p99", "label": "P99", "value": 1100, "percentile": 99, "sourceRefs": ["OPS-LAT-1"]}
],
"analysis": {"claimType": "descriptive", "design": "descriptive", "pooled": false, "poolingCompatibility": "not-applicable"},
"assumptions": ["All fictional percentiles use the same seven-day request population."]
},
"units": "milliseconds",
"denominator": {"value": 24000, "unit": "requests", "label": "Illustrative seven-day request population"},
"uncertainty": {"kind": "qualitative-limit", "description": "The fictional export summarizes one seven-day window and does not establish future performance."},
"caption": "Illustrative service-latency percentiles from one fictional seven-day monitoring export.",
"accessibleText": "For 24,000 fictional requests, latency is 180 milliseconds at P50, 620 at P95, and 1,100 at P99.",
"edges": []
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |