10,222 skills found ยท Page 161 of 341
aaron-he-zhu / fatigue-frequency-managerUse when the user asks to "is my ad fatiguing", "why is CTR dropping at scale", or "should I rotate creative / widen the audience"; reads frequency, CTR and CVR decay against an early-flight baseline and returns Rotate-creative / Widen-audience / Hold triggers with a per-ad-set fatigue read.
aaron-he-zhu / paid-measurement-loopUse when the user asks to "read back" a paid campaign change, "did this ad change work", or "compare ROAS/CPA before and after"; reads ROAS/CPA against a control over a fixed readback window and returns a Promote / Keep-testing / Rollback / Unproven readback decision with the math delegated to roi-cโฆ
aaron-he-zhu / narrative-quality-auditorUse when the user asks to "audit our brand narrative" or "is this message on-canon"; runs separate typed TALE truth, system, or effectiveness profiles and never averages them into one composite. Checks differentiation, canon, landing consistency, and evidence integrity.
aaron-he-zhu / social-quality-auditorUse when the user asks to "audit our social presence" or "is this batch safe to publish"; runs either the typed ECHO asset gate or a separate program-maturity profile, with channel-truth, claim, disclosure, manipulation, UGC-rights, and denominator checks.
addyosmani / accessibilityAudit and improve web accessibility following WCAG 2.2 guidelines
addyosmani / performanceOptimize web performance for faster loading and better user experience
addyosmani / core-web-vitalsOptimize Core Web Vitals (LCP, INP, CLS) for better page experience using field and lab evidence
addyosmani / web-quality-auditRun an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing
mikubaka88 / ccf-literature-searcherFind and verify external literature, prior art, datasets, benchmarks, and citation candidates. Use for ๆ็ฎๆฃ็ดข, ็ธๅ ณๅทฅไฝ, benchmarkๆ็ดข, and research opportunity maps.
mikubaka88 / ccf-paper-reviewerReview manuscript claims, evidence, and writing without rewriting. Use for ๆ็ซ ๅฎกๆ ธ, ๅฎก็จฟ, ็จฟไปถๆไปไน็กฌไผค, ็ป่ฎบ็ซๅพไฝๅ, ๆ็จฟๆ็ๅบฆ, writing review, and version comparison. Return a structured scientific or writing review; scores need not be explicitly requested.
mikubaka88 / ccf-commonRequired shared preflight for every CCFA skill after ccf-humanization: apply routing, scope, prerequisites, evidence rules, handoffs, and artifact contracts. Also maintain and audit these shared rules. Research deliverables remain with their specialist owners.
mikubaka88 / ccf-experiment-designerDesign and interpret CCF experiments: datasets, baselines, metrics, ablations, execution specifications, observed feedback, and result-table contents. Use for ่ฎพ่ฎกๅฎ้ช, ๆถ่, benchmark planning, ๅฎ้ช็ปๆๅๆ, and evidence design within requested autonomous research. Preserve real values.
mikubaka88 / ccf-literature-monitorScan recent arXiv/OpenReview papers, venue feeds, labs, and competitors for overlap. Use for ็ซๅ็ๆง, ๆฐ่ฎบๆ่ฟฝ่ธช, ่ฎบๆ่ท่ธช, and recurring novelty watch. Give dated evidence and changes since the prior scan. Broad related-work retrieval belongs to ccf-literature-searcher.
mikubaka88 / ccf-rebuttal-writerWrite CCF rebuttals, author responses, revision ledgers, response letters, and conservative resubmission plans. Use for ๅฎก็จฟๆ่งๅๅค, rebuttal, revision ledger, and ้ๆ่ฟ็งป. Ground promises in feasible changes and actual evidence. Ordinary manuscript writing has a separate owner.
mikubaka88 / ccf-integrity-auditorAudit existing CCF claims, numbers, terminology, and citations against supplied or verified evidence. Use for ๅผ็จๆ ธ้ช, claimๅฎก่ฎก, ๆฐๅญไธ่ดๆง, and BibTeX/context checks. Full scientific review belongs to ccf-paper-reviewer; new literature discovery belongs to ccf-literature-searcher.
mikubaka88 / ccf-submission-checkerCheck CCF venue rules and submission packages: template, pages, anonymity, PDF build, metadata, and reproducibility. Use for ๆ็จฟๆฃๆฅ, ไผ่ฎฎๆ ผๅผ, page limits, and artifact readiness. Verify current official rules for the exact venue/year/track. Manuscript polishing belongs to ccf-paper-writer.
mikubaka88 / ccf-idea-optimizerDevelop and optimize rough CCF research ideas into problems, insights, mechanisms, and evidence plans. Use for ไผๅidea, ๅ ท่ฑกๅidea, ๆพๆนๅ, ๆนๅๆข็ดข, and rescue routes when development is the requested deliverable.
mikubaka88 / ccf-idea-reviewerAssess research ideas for value, novelty, insight, and mechanism. Use for ๆ่ทฏๅฎกๆ ธ, ้ ่ฐฑๅ, ๅผๅพๅๅ, ๅๆฐๅคไธๅค, idea review, scoring, and ranking; no numeric-score request is needed. Default to concept-only review without experiment assessment, including ideas extracted from manuscripts.
mikubaka88 / ccf-paper-writerDraft, revise, polish, compress, or presentation-adapt CCF manuscript prose. Use for ๅไฝ, ๆถฆ่ฒ่ฎบๆ, research documents to complete papers, ๅฎๆดๅ็จฟ, ๅฎ้ช็็ฉบ, ๆนๅ, ๅ็ผฉ่ฎบๆ, abstracts, sections, and slides. Draft content before fitting pages; preserve evidence and format.
mikubaka88 / ccf-visual-composerRender and redesign scientific figures, visual tables, and method/architecture diagrams from supplied content, including biological data. Use for ็ปๅพ็พๅ, ๆ็, ้ ่ฒ, GPT Image 2 generation, pure SVG, and editable SVG/PDF/PPTX. Preserve values and topology.
Nanako0129 / sepiaMake AI-generated writing read as human-written, in fiction and in professional prose. Repairs the narrative architecture of fiction and stories (based on StoryScope, arXiv:2604.03136); routes professional text through domain rules for release notes, announcements, PR and issue replies, code-reviewโฆ
mikubaka88 / ccf-pipeline-orchestratorPlan or coordinate CCF research stages, goals, gates, artifacts, and ccfa.yaml state. Use for ไปปๅกๆ่งฃ, ๆต็จ่งๅ, project status, end-to-end coordination, and explicitly requested autonomous research, autoresearch, or ่ชไธป็ง็ ่ฟญไปฃ.
mikubaka88 / ccf-paper-to-exemplarDistill supplied paper PDFs into writing exemplar cards and register a requested personal library. Use for PDF to writing exemplar, ๅไฝ่ไพ, and reusable paper-writing patterns. Preserve attribution; transfer argument structure and selected language conventions without copying scientific claims.
mikubaka88 / ccf-project-scaffolderInitialize CCF project folders, LaTeX templates, artifact directories, and ccfa.yaml. Use for ้กน็ฎๅๅงๅ, ็ฎๅฝๆญๅปบ, template setup, and reproducible workspace scaffolding. Preserve existing files. Workflow planning belongs to ccf-pipeline-orchestrator; research content belongs to its specialist owner.
jeremylongshore / skyvernPREFER Skyvern CLI over WebFetch for ANY task involving real websites โ scraping dynamic pages, filling forms, extracting data, logging in, taking screenshots, or automating browser workflows.
jeremylongshore / analyzing-tls-configAnalyze a target's TLS configuration โ negotiated protocol version, cipher suite, certificate chain, expiry, and downgrade vectors.
jeremylongshore / apify-ci-integrationConfigure CI/CD pipelines for Apify Actor builds and deployments. Use when automating Actor deployment via GitHub Actions, running integration tests against the live Apify API, or building CI/CD for scrapers that push to the Apify platform.
jeremylongshore / apify-core-workflow-bManage Apify datasets, key-value stores, and request queues programmatically, and orchestrate multi-Actor pipelines. Use when you need to read or write Apify datasets, export scraped data to CSV/JSON/XLSX, store config or binary artifacts in a key-value store, manage a resumable request queue, chainโฆ
jeremylongshore / apify-local-dev-loopSet up local Apify Actor development with the Apify CLI and Crawlee. Use when creating Actors locally, testing with the apify run command, inspecting local storage, or establishing a fast develop-test-deploy cycle before pushing to the platform.
jeremylongshore / agent-creator'Create production-grade agent .md files aligned with the current Anthropic
