Claude Skills by thedixitjain

Use when deciding which hrm-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for a Human Resource Management (Wiley \"HRM\") submission. Routes — it does not replace — the specialized skills.

HuggingFace hf CLI: search/download/upload models, datasets.

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

Use when sharpening the theoretical contribution and the \"so what\" for a Human Relations (HR) manuscript once results exist. Frames the contribution; it does not develop the underlying theory or run analysis.

Use when running the final pre-submission preflight for Human Relations (HR) via ScholarOne — anonymization, the 13k word cap, SAGE Harvard style, abstract/keywords, AI and data-transparency declarations. Final checks; it does not draft content.

Use when building and auditing the exhibits for a Human Relations (HR) manuscript — qualitative data-structure and evidence tables, process models, and quantitative tables/figures. Improves the exhibits; it does not change the analysis or theory.

Use when building the theoretical engine for a Human Relations (HR) manuscript — mechanisms grounded in social theory, process vs. variance logic, constructs, and boundary conditions. Builds the argument; it does not choose methods or run analysis.

Use when deciding which humrel-* sub-skill to invoke next, or when sequencing manuscript work from topic through rebuttal for a Human Relations (HR) submission. Routes — it does not replace — the specialized skills.

Baseline the EFI System Partition and hunt malicious EFI binaries (ESPecter, BlackLotus, Bootkitty, Glupteba) by mounting the ESP, hashing and verifying boot loaders, scanning with YARA, and detecting anomalous non-EFI files.

Detect Cobalt Strike beacon network activity using default TLS certificate signatures (serial 8BB00EE), JA3/JA3S/JARM fingerprints, HTTP C2 profile pattern matching, beacon jitter analysis, and named pipe detection via Zeek, Suricata, and Python PCAP analysis.

'Hunt for DCOM-based lateral movement by detecting abuse of MMC20.Application, ShellBrowserWindow, and ShellWindows COM objects through Sysmon Event ID 1 (process creation) and Event ID 3 (network connection) correlation, WMI event analysis, RPC endpoint mapper traffic on port 135, and DCOM-specific parent-child process relationships. '

Detect DNS tunneling and data exfiltration by analyzing Zeek dns.log for high-entropy subdomain queries, excessive query volume, long query lengths, and unusual DNS record types indicating covert channel communication.

Detect domain fronting C2 traffic by analyzing SNI vs HTTP Host header mismatches in proxy logs and TLS certificate discrepancies using pyOpenSSL for certificate inspection

Proactively hunt for adversary abuse of legitimate system binaries (LOLBins) to execute malicious payloads while evading detection.

Detect process injection techniques (T1055) including CreateRemoteThread, process hollowing, and DLL injection via Sysmon Event IDs 8 and 10 and EDR process telemetry

Hunt for unusual network connections by analyzing outbound traffic patterns, rare destinations, non-standard ports, and anomalous connection frequencies from endpoints.

Hunt for web shell deployments on internet-facing servers by analyzing file creation in web directories, suspicious process spawning from web servers, and anomalous HTTP patterns.

Render MP4/WebM videos from HTML compositions.

Hyperliquid market data, account history, trade review.

Manages the project's testable hypotheses — surfacing new ones, refining existing ones, updating status, reviewing the full set, and assessing hypothesis state based on evidence gathered so far. Use when the conversation touches assumptions, risks, what to validate, hypotheses, interview prep, assessing which hypotheses are confirmed or invalidated, reviewing overall hypothesis health, or when the user questions whether something about their idea is true.

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

Use when reasoning about how an ICALP (EATCS) submission is evaluated, covering lightweight double-blind review, the separate Track A and Track B program committees, the asymmetric author interaction (Track B rebuttal vs Track A correctness-only contact), correctness-driven acceptance, the single accept/reject decision, and how ICALP's process differs from STOC/FOCS/SODA.

Use when designing or auditing ICASSP experiments across signal-processing modalities — matching the metric to the task law (WER, SI-SDR, PESQ/STOI, EER/minDCF, PSNR/SSIM, BER, RMSE), anchoring baselines to current strong methods and standard corpora, sweeping the operating condition, and reporting spread over runs within the four-page limit.

Use when deciding whether a project fits ICASSP, the IEEE Signal Processing Society flagship spanning all signal processing, and specifically for the ICASSP-versus-Interspeech routing decision for speech work, plus routing to ICIP, EUSIPCO, WASPAA, SPS journals, or ML venues by identifying the signal-processing primitive of the contribution.

Use when responding to IEEE ICDE reviews, whether drafting a rebuttal to reviewer concerns or preparing a revise-and-resubmit change document for an invited ICDE revision under the 4-week window, coordinating with area chairs, addressing systems-reviewer pushback on baselines and cost, and deciding what is feasible before the revision deadline.

Use when reasoning about the ICDM (IEEE International Conference on Data Mining) review machinery - the triple-blind mechanics, the Accept / Accept-as-Short / Reject outcome space, the mixed data-mining reviewer pool, PC Co-Chair decision-making, the traditional no-rebuttal posture, and how to read an ICDM decision packet.

Use when drafting ICLR OpenReview author discussion replies, revision notes, public comments, restricted comments, and responses to reviewer or AC concerns during the discussion period. Use when reviews land and you must decide what to answer publicly versus privately, how to log a discussion-period revision, or how to move a borderline score before the AC writes the meta-review for the permanent record.

Use when explaining or planning around the ICLR review process, including OpenReview public review, AC/SAC roles, reviewer questions, discussion, revisions, final recommendations, and ethics escalation. Use when deciding whether to reply publicly or privately, how a permanently visible review thread shapes strategy, when to upload an allowed revision, or when to escalate a defective review to the AC for the current cycle.

Use when auditing an ICLR main-conference submission for OpenReview readiness, double-blind anonymity, page limits, reciprocal reviewing, LLM-use disclosure, dual-submission policy, supplementary material, and desk-reject risk.

Use when organizing ICLR appendices, supplementary files, anonymous code/data, revised PDFs, private links, and discussion-period updates under OpenReview rules. Use when deciding what stays in the main text versus the appendix, how to label a discussion-period revision so reviewers find changes fast, or how to package anonymous artifacts that remain part of the permanent public record after acceptance.

Use when deciding whether a project is a strong ICLR submission, should be reframed for ICLR, or should be routed to NeurIPS, ICML, AAAI, AISTATS, ACL, CVPR, KDD, or another venue. Use when a project lacks a clear representation-learning insight, when an application result needs a learning contribution to fit ICLR, or when weighing ICLR's deep-learning center of gravity against a better-matched venue.

Use when explaining or diagnosing the ICML review process, including OpenReview, reciprocal reviewing, reviewer/AC behavior, review dimensions, author response, one-round discussion, LLM-review policy, ethics flags, and public review records.

Use when drafting an IEEE ICSME author response during the double-anonymous author-response period, covering the early-decision cut that decides whether you respond at all, answering the PC's specific \"Response Recommended\" questions with existing evidence, staying anonymous, and doing it in one round with no Major Revision safety net.

Darwinian idea evolution engine — toss rough ideas onto an evolution island, let them compete, crossbreed, and mutate through structured rounds to surface your strongest concepts.

| Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, create author people page, and cross-link. Use when the user shares a link or says \"read this\", \"save this\", \"think about this\".

| Trace one idea's evolution through the brain: first mention, best articulation, related concepts, reversals, contradictions, abandoned branches, and the current live version. Use for single-idea conceptual lineage, not broad concept-map synthesis or structured entity metrics.

Generate diverse solution candidates with category-spanning ideation methods and rotation. Use when stuck on a design or fighting repetitive LLM output.

Idempotent Redundancy

One sentence - what this skill does and when to invoke it

'Execute Ideogram secondary workflows: edit (Magic Fill), remix, upscale, describe, and reframe. Use when modifying existing images, applying style transfer, upscaling, or building image-to-image pipelines. Trigger with phrases like \"ideogram edit image\", \"ideogram remix\", \"ideogram upscale\", \"ideogram inpaint\", \"ideogram magic fill\", \"ideogram reframe\". '

'Configure Ideogram across development, staging, and production environments. Use when setting up multi-environment deployments, configuring per-environment keys, or implementing environment-specific Ideogram configurations. Trigger with phrases like \"ideogram environments\", \"ideogram staging\", \"ideogram dev prod\", \"ideogram environment setup\", \"ideogram multi-env\". '

Use when auditing an IEEE S&P (Oakland) submission for HotCRP readiness, including the registration freeze with ORCID matching, the 13-page/18-page compsoc format, anonymization, the Ethics Considerations field, SoK checkbox, conflict declarations, and the desk-reject triggers specific to S&P cycles.

Use when an International Economic Review (IER) decision letter or referee report needs a response strategy and a revision plan. Triages comments and structures the response letter to a rigor-leaning, theory-tilted review; it does not invent new results.

Use when anticipating referee objections before submitting an International Economic Review (IER) manuscript, or when reading the room of an IER review. Maps the likely objections by archetype and pre-empts them; it does not draft the response letter (see ier-rebuttal).

Use when exhibits in an International Economic Review (IER) manuscript are dense, do not carry the argument, or do not present structural/theory results well. Makes each exhibit answer one question; it does not generate the data.

Use when deciding which ier-* sub-skill to invoke next, or when sequencing manuscript work from topic through rebuttal for an International Economic Review (IER) manuscript. Routes — it does not replace — the specialized skills.

Use when drafting IJCAI or IJCAI-ECAI author responses under the official one-page template, concise-response guidance, no-new-results constraints, code-link restrictions, factual-error triage, pressing-question triage, and confidential unethical-review channel.

Use when explaining or planning around IJCAI or IJCAI-ECAI two-phase review, summary rejection, PC/SPC/AC/SAC roles, author response visibility, reviewer confidentiality, conflict-of-interest policy, ethics checks, and decision dynamics.

Use when preparing IJCAI or IJCAI-ECAI supplementary material, technical appendices, ZIP files, proofs, derivations, data, source code, and resubmission files under deadline, format, size, anonymity, and reviewer-discretion constraints.

Use when deciding whether an AI project is a strong IJCAI or IJCAI-ECAI fit, comparing main track versus special tracks, Survey Track, AIJ/JAIR expedited-publication potential, or alternative AI venues such as NeurIPS, ICML, ICLR, AAAI, AISTATS, UAI, COLT, KDD, CVPR, ACL, or ICRA.