Docs & Writing

yigityildiz0 Bundle

Manual Caveman-style prose compressor for Markdown or plain-text memory and instruction files, with invariant validation, unified-diff preview, explicit approval, atomic replacement, and timestamped backup. Use only when explicitly invoked as $caveman-compress, /caveman-compress, 'Caveman compress', or an unambiguous Caveman memory-file compression request. Never activate for ordinary summarization, ZIP/archive compression, or generic file cleanup; never overwrite during preview. Turkish triggers: Caveman compress, mağara modu metin sıkıştırma.

yigityildiz0 Skill

Professional technical writing expertise for clear, audience-appropriate documentation. Use when producing user-facing docs, API guides, onboarding.

yigityildiz0 Bundle

Create OpenAPI/Swagger specifications, API reference documentation, endpoint descriptions, and usage examples. Use when documenting REST APIs, GraphQL.

yigityildiz0 Bundle

Generate comprehensive development logs from git history, documentation, and code artifacts. Use when creating project history, onboarding to unfamiliar.

yigityildiz0 Skill

Create or improve an operational runbook for recurring operations, incidents, maintenance, onboarding, or controlled recovery. Use for runbook, operational procedure, escalation guide, recovery steps, or on-call documentation. Turkish triggers: runbook hazırla, işletim adımları, olay müdahalesi ve geri alma, nöbet rehberi.

yigityildiz0 Bundle

Turn physiotherapy and rehabilitation lecture slides, PDFs, textbook pages, class notes, screenshots, cases, or learning objectives into an exam-ready study system. Use when the user asks to explain an FTR/physiotherapy topic, summarize course material, prepare for an exam, identify high-yield points, create tables, flashcards, active-recall questions, quizzes, case questions, OSCE stations, mnemonics, or a study plan; also recognize Turkish prompts such as "çalıştır", "anlat", and "not çıkar". Preserve source fidelity, separate supplied content from added clinical context, flag unreadable or missing material, and adapt depth to the learner's stated training level. Do not invent lecture content, present generated questions as real exam items, or provide patient-specific treatment under a study workflow.

yigityildiz0 Skill

Synthesize qualitative research, feedback, interviews, observations, support tickets, or study notes into traceable themes, evidence, uncertainty, and actionable opportunities. Use for research synthesis, analyze interviews, synthesize user feedback, affinity mapping, insight report, or research findings. Turkish triggers: birçok kaynağı sentezle, bulguları birleştir, çelişki ve kanıt gücü, sonuç çıkar.

yigityildiz0 Skill

Presentation-structure skill. Use when Codex should turn notes, ideas, or documents into a coherent deck with slide-by-slide flow.

yigityildiz0 Bundle

Create README files, installation guides, tutorials, quick starts, and user-facing documentation. Use when creating project documentation, onboarding.

yigityildiz0 Bundle

Creative direction for image prompts, presentation slides, and ideation. Use when asked to generate image prompts, design slide decks, brainstorm ideas.

yigityildiz0 Bundle

Initialize a complete Python project with standard structure, pyproject.toml, testing framework, and documentation. Use when starting a new Python project.

yigityildiz0 Bundle

Route any physiotherapy or rehabilitation request through the correct evidence and safety workflow. Use implicitly for Turkish or English prompts about fizyoterapi/FTR, physical therapy, rehabilitation, pain and function, therapeutic exercise, manual or device-based therapy, gait, balance, mobility, neurological/cardiorespiratory/MSK/pelvic/oncology rehabilitation, patient cases, tests, outcome measures, dose, prognosis, articles, guidelines, documentation, patient education, clinical terminology, or professional development. Turkish triggers: kanıta dayalı FTR, rehabilitasyon sorusu, fizyoterapi becerisi seç. Do not use for unrelated general fitness or medical questions when rehabilitation is not central.

jiayaoqijia Bundle

Trend and technical analysis. Use this skill ONLY when the user's query is exclusively about technical indicators or trend analysis for one coin with no other analysis dimensions. Trigger phrases: technical analysis, K-line, RSI, MACD, trend, support, resistance. If the query ALSO mentions fundamentals, risk, news, sentiment, or any other analysis dimension, use gate-info-research instead — it handles multi-dimension queries in a single unified report.

jiayaoqijia Bundle

Use this skill to 'broadcast transaction', 'send tx', 'estimate gas', 'simulate transaction', 'check tx status', 'track my transaction', 'get gas price', 'gas limit', 'broadcast signed tx', 'transaction hash confirmed on-chain', '交易哈希是否上链', '是否确认', or mentions broadcasting transactions, sending transactions on-chain, gas estimation, transaction simulation, tracking broadcast orders, or checking transaction status. Covers gas price, gas limit estimation, transaction simulation, transaction broadcasting, and order tracking across XLayer, Solana, Ethereum, Base, BSC, Arbitrum, Polygon, and 20+ other chains. Do NOT use for swap quote or execution - use okx-dex-swap instead. Do NOT use for general programming questions about transaction handling. Do NOT use when the user says only a single word like 'gas' or 'broadcast' without specifying a chain, transaction, or any other context.

jiayaoqijia Bundle

Market overview. Use this skill ONLY when the user's query is exclusively about overall market conditions with no specific coin analysis. Trigger phrases: how is the market, market overview, what is happening in crypto. If the query ALSO mentions a specific coin to analyze, risk to check, technicals to review, or any other analysis dimension, use gate-info-research instead — it handles multi-dimension queries in a single unified report.

jiayaoqijia Bundle

Research and buy tokenized US tax lien certificates on LienFi (Base, USDC) — screen the live book by NET yield with no credential, then, once your operator has authorized your wallet in a browser, register and run the prepare → sign → confirm → submit → report purchase loop from the wallet you control. LienFi signs only the price; every transaction leaves your wallet.

pku-yuangroup Bundle

Quality control for IMC/MIBI data across pixel, channel, image, slide, and batch levels, covering Poisson-count SNR (cell-level Gaussian-mixture and empty-channel comparison), spillover-matrix QC (the three physical sources), drift and the missing EQ-bead analog, acquisition artifacts, and sample-of-origin batch effects. Use when deciding whether to keep or drop a channel, ROI, or slide, distinguishing a dim antibody from a failed one, reading a spillover matrix, or diagnosing batch-driven clustering before analysis.

pku-yuangroup Bundle

Loads spatial transcriptomics data from Visium, Visium HD, Xenium, MERFISH/MERSCOPE, CosMx, Slide-seq/Curio, and Stereo-seq into AnnData or SpatialData using spatialdata-io and Squidpy. Use when deciding which platform class is in hand (imaging/in-situ vs sequencing/capture), which reader matches the platform (spatialdata_io.xenium/merscope/cosmx vs squidpy.read.visium/vizgen/nanostring), whether to work from the per-transcript molecule table (the re-segmentable source of truth) or the segmentation-derived per-cell matrix (quality-filtered, inherits all segmentation error), whether a molecule table even exists (spot platforms have none), and how to keep coordinate frames and units (pixel vs micron) registered to histology.

pku-yuangroup Bundle

Identify spatially coherent tissue domains (regions like cortical layers, tumor vs stroma) in Visium, Visium HD, Xenium, MERFISH, Slide-seq, and Stereo-seq data with Squidpy, BANKSY, BayesSpace, STAGATE, and GraphST. Use when distinguishing a domain (a region with many cell types) from a cell type (one cell's identity) and a niche (local cell-type composition); choosing a domain method by tissue geometry (laminar/continuous vs high-resolution imaging vs non-contiguous); tuning the spatial-weight knob (BANKSY lambda, BayesSpace smoothing, SpaGCN histology weight, GNN graph radius) to avoid over-smoothing into blobs or under-smoothing into salt-and-pepper; choosing the number of domains k as a biological decision with k+-1 sensitivity; and reading the Yuan 2024 benchmark with the DLPFC continuous-laminar caveat.

pku-yuangroup Bundle

Extracts per-cytosine methylation calls from aligned bisulfite/EM-seq reads with bismark_methylation_extractor (Bismark BAM) or the aligner-agnostic MethylDackel/BISCUIT (bwa-meth BAM), producing the beta value M/(M+U) as a coverage file, bedGraph, or genome-wide cytosine report across CpG/CHG/CHH context. Covers conversion-rate QC as the first gate, the 5mC vs 5hmC summed caveat, variant-aware calling so a C/T SNP does not masquerade as unmethylation, paired-end --no_overlap double-counting, symmetric CpG dyad collapse, and the 0-based vs 1-based coordinate trap. Use when extracting methylation levels from a bisulfite/EM-seq alignment, choosing an extractor for a non-Bismark BAM, QC-ing conversion efficiency, or producing coverage/cytosine-report input for testing. For long-read MM/ML modification calling see long-read-sequencing/nanopore-methylation; for the upstream BAM see bismark-alignment; for per-CpG statistics see differential-cpg-testing.

pku-yuangroup Bundle

Maps cell-cell communication and ligand-receptor co-expression in spatial transcriptomics (Visium, Xenium, MERFISH, CosMx, Slide-seq) with Squidpy ligrec, COMMOT, stLearn, CellChat-spatial, and NicheNet. Use when choosing a method by whether spatial distance is actually modeled (squidpy ligrec is space-blind cluster-permutation vs COMMOT optimal-transport is distance-aware vs stLearn neighborhood vs CellChat-spatial filter) and by secreted-vs-contact-dependent range; choosing the ligand-receptor database knowingly because it drives the result as much as the algorithm; guarding against segmentation-spillover circularity that fabricates short-range hits; treating every ligand-receptor score as a co-expression hypothesis on a confidence ladder, not validated signaling; correcting for thousands of pair-by-cell-type-pair permutation tests; and recognizing that a targeted imaging panel rarely contains the relevant ligands and receptors so a "no communication" call is uninformative.

pku-yuangroup Bundle

Estimates per-spot cell type composition of spatial transcriptomics mixtures (Visium, Slide-seq, Stereo-seq) from an scRNA-seq reference with cell2location, RCTD, SPOTlight, stereoscope, SpatialDWLS, or reference-free STdeconvolve. Use when deciding whether a platform even needs deconvolution (the resolution fork -- a 55um Visium spot is a 1-10-cell MIXTURE -> deconvolve, but a Xenium/MERFISH/CosMx cell is already single -> segment instead, and running deconvolution there invents fractions that do not exist); choosing cell2location (absolute abundance) vs RCTD/SPOTlight/stereoscope/SpatialDWLS (proportions only) by output and runtime; matching the scRNA reference to tissue and condition (the reference IS the result -- a missing cell type is silently misassigned to its nearest neighbor with no error flag); and handling compositional outputs that sum to 1 with CLR/ILR rather than naive per-type t-tests.

pku-yuangroup Bundle

Plots spatial transcriptomics expression, clusters, and annotations on tissue using Squidpy and Scanpy. Use when choosing the plotter and spot size by platform fork (sc.pl.spatial / sq.pl.spatial_scatter with real scalefactors and capture diameter for spot/capture data like Visium and Slide-seq, versus molecule/segmentation overlays for imaging/FOV data like Xenium, MERFISH, and CosMx); getting the histology coordinate-frame transform right (micron<->pixel, scalefactors) so points land on the image; and avoiding the honest-visualization traps where interpolation/KDE manufactures spatial pattern not in the data, oversized markers fake tissue coverage, jet and other non-uniform colormaps distort structure, and non-metric UMAP/tSNE distances are misread as spatial conclusions.

pku-yuangroup Bundle

Reconstructs single cells from sub-cellular spatial capture units (Visium HD 2um bins, Stereo-seq DNB spots, Slide-seqV2 beads) by aggregating bins UP into cells rather than deconvolving a mixture DOWN. Use when choosing a bin size and recognizing the sparsity-vs-mixture dilemma (2um bins are too sparse to cluster, but binning to 8/16um re-creates the multi-cell mixture deconvolution was meant to escape); deciding between morphology-driven cell reconstruction (Bin2cell -- StarDist/Cellpose nuclei on a registered H&E/DAPI image, then assign 2um bins to nuclei) and fixed-bin aggregation by whether a co-registered cell image exists; recognizing this as the INVERSE of deconvolution (bin UP, not mix DOWN -- this is the AMBIGUOUS regime of the resolution fork); and handling each platform (Visium HD has an image so reconstruct, Slide-seqV2 has no per-bead image so aggregate or deconvolve, Stereo-seq depends on a registered stain).

lgrappag Skill

Capture and report crash dumps for debugging

withoneai Skill

Api2Pdf through One

withoneai Skill

PDFMonkey through One

withoneai Skill

WordPress through One

jiayaoqijia Bundle

Analyze one or many crypto wallets by address — holdings, batch realized/unrealized P&L, win rate, trading history, performance stats, specific token balance, and tokens created by a developer wallet (with ATH market cap and DEX graduation status) via GMGN API on Solana, BSC, Base, or Ethereum. Use when user asks about wallet holdings, P&L (including comparing up to 100 wallets), win rate, what tokens a dev has launched, the highest ATH token a dev ever created, or wants a wallet report to decide whether to copy-trade or follow.

rudironsoni Bundle

Rulesync CLI tool documentation - unified AI rule file management for various AI coding tools

yigityildiz0 Bundle

Draft accurate, traceable physiotherapy documentation from supplied facts. Use for initial evaluation, visit/daily note, re-examination/progress report, discharge or episode summary, referral, consultation, handoff, goal and outcome tracking, ICF or SOAP-style notes, patient education, consent, adverse events, and plan changes. Trigger on fizyoterapi notu, epikriz, değerlendirme formu, SOAP, taburculuk. Never invent, backdate, authenticate, submit billing, or create a final legal record; codes may only be a verified draft for authorized review. Protect health data and verify local requirements.

yigityildiz0 Bundle

Automatically diagnose and solve personal technology, app, device setup, compatibility, configuration, purchase, and troubleshooting questions across Windows, macOS, Android, iPhone/iPad/watch ecosystems, smart-home accessories, displays, peripherals, storage, networking, remote access, scanning/PDF utilities, backups, and cross-device workflows. Use for setup/error screenshots and prompts such as "how do I", "why is this not working", "compatible?", or Turkish equivalents such as "nasıl yaparım", "neden çalışmıyor", "bağlanmıyor", "uyumlu mu", and "hangi ayar". Verify current versions and official instructions; add current pricing evidence for purchase/value questions.

yigityildiz0 Bundle

Initialize a complete JavaScript/TypeScript project with package.json, testing framework, bundler configuration, and documentation. Use when starting.

yigityildiz0 Bundle

Automatically support physiotherapy and rehabilitation requests involving a patient case, symptoms, injury, surgery, clinical examination, differential hypotheses, red flags, ICF, goals, prognosis, outcome measures, rehabilitation exercise/session/home programs, progression, patient education, SOAP/clinical documentation, clinical English, or professional development. Trigger on contextual Turkish such as "vakayı analiz et", "bu hastaya ne yapılır", "FTR vakası", "fizyoterapi değerlendirmesi", or "rehabilitasyon programı". Integrate safety, evidence, reasoning, measurement, planning, communication, and reassessment. Do not trigger on general fitness, bodybuilding, or ordinary exercise without a patient, impairment, rehabilitation, or physiotherapy context; use physio-study-coach for course/exam material. Do not diagnose remotely, replace examination, issue clearance, or give patient-specific high-risk treatment when context or authority is missing.

yigityildiz0 Bundle

Read, translate, and deeply teach English physiotherapy and rehabilitation language without losing scientific detail. Use for an English article, abstract, guideline, report, table, clinical note, acronym, or term; Turkish contextual explanation; sentence-by-sentence reading; academic/statistical language; or physiotherapy terminology. Trigger on İngilizce FTR, makale çevirisi, terim, kısaltma, ne demek, contextual translation. Preserve numbers, uncertainty, methods, and official instrument names. Translation is not endorsement.

yigityildiz0 Bundle

Generate architecture documentation, ADRs (Architecture Decision Records), design documents, and technical specifications. Use when documenting system.