talhaMah56

@talhamah56 source repo

69 skills
0 followers
3 hours ago last updated

▌
Experiment Bridge · talhamah56
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.

0 installs
▌
Paper Claim Audit · talhamah56
Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh self-review pass — Claude re-reads the paper and raw results with none of its drafting/experiment context — to reduce (not eliminate) confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.

0 installs
▌
Paper Poster HTML · talhamah56 bundle
DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper poster", or asks to design/redo a research poster. Supersedes the retired LaTeX /paper-poster.

0 installs
▌
Research Pipeline · talhamah56
Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.

0 installs
▌
Resubmit Pipeline · talhamah56
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says "resubmit pipeline", "重投流程", "port paper to <new venue>", "resubmit to <venue>", "tighten paper for resubmission", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.

0 installs
▌
Data Visualization · talhamah56
Chart and plot data — pick the right chart type for the data shape, then generate Chart.js config or Plotly code. Use when asked to visualize a dataset, plot results, build a chart, or choose between chart types/libraries for quantitative data (as opposed to structural/technical diagrams — see technical-diagrams for those).

0 installs
▌
Idea Creator · talhamah56
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.

0 installs
▌
Loop Library · talhamah56 bundle
Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs. Use when a user asks to analyze a codebase for potential loops, mine coding-thread history for work done more than once, turn repeated engineering work into a loop, find or recommend a published loop, create a recurring agent workflow or automation cadence, turn an outcome into a bounded copy-ready loop, or review an existing loop for weak checks, unsafe authority, unbounded repetition, stale state, or unclear stopping behavior.

0 installs
▌
Paper Figure · talhamah56
Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.

0 installs
▌
Paper Slides · talhamah56
Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.

0 installs
▌
Kill Argument · talhamah56
Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.

0 installs
▌
Meta Optimize · talhamah56
Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.

0 installs
▌
Novelty Check · talhamah56
Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.

0 installs
▌
Paper Writing · talhamah56
Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.

0 installs
▌
Patent Review · talhamah56
Get a patent-examiner-perspective review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.

0 installs
▌
Plain Writing · talhamah56 bundle
Write and edit prose in the user's plain style: simple everyday words, complete sentences, no dashes, no jargon, no analogies, no filler, and full clear explanations. Use this whenever you draft or revise any prose for the user, such as documents, Notion pages, reports, summaries, README files, research notes, proposals, slide text, emails, or commit and PR descriptions. Also use it whenever the user asks to simplify, clean up, tighten, reword, or make writing clearer or easier to read. Default to this style for prose written for the user unless they ask for a different one. Do not apply it to code itself, only to the words around it.

0 installs
▌
Proof Checker · talhamah56
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via adversarial review (external cross-model reviewer backend when available, ultra reasoning; falls back to Claude self-review with no second model), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.

0 installs
▌
Read All Adrs · talhamah56
Read every ADR markdown file in the project's docs/adr/ folder so you have full context on past decisions. Use only when David explicitly calls it.

0 installs
▌
Research Wiki · talhamah56
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.

0 installs
▌
Slides Polish · talhamah56
Per-page self-review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic style leaks, fixes text-frame overflow, and catches per-slide layout drift. Trigger phrases: "polish slides", "slides 排版不对", "PPTX 字体太小", "和 Beamer 比一下", "per-page review".

0 installs
▌
Citation Audit · talhamah56
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.

0 installs
▌
Grant Proposal · talhamah56
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.

0 installs
▌
Idea Discovery · talhamah56
Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.

0 installs
▌
Training Check · talhamah56
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.

0 installs
▌
Camada Agentica · talhamah56
Use to propose and generate the project's agentic layer — rules (CLAUDE.md, settings.json), subagents (.claude/agents), skills (.claude/skills), and workflows/CI — tuned to the stack, tools, process, and domain. Proposes with justification and generates only what is approved. Runs standalone as the project evolves or new tools arrive. Trigger with /camada-agentica.

0 installs
▌
Claims Drafting · talhamah56
Draft patent claims for an invention. Use when user says "撰写权利要求", "draft claims", "写权利要求书", "claim drafting", or wants to create patent claims. The core skill of the patent pipeline.

0 installs
▌
Patent Pipeline · talhamah56
Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says "写专利", "patent pipeline", "专利申请", "draft patent", "写权利要求书", or wants to draft a complete patent application.

0 installs
▌
Research Prompt · talhamah56
Write a single-paragraph Deep Research prompt to hand to a human researcher (or a deep-research AI). Use when the user wants a research brief, a "deep research prompt", a one-paragraph task for a researcher, or asks "what should our researcher look for". Produces ONE tight paragraph with full context, numbered sub-questions, and per-finding output format.

0 installs
▌
Research Refine · talhamah56
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative review (Claude self-review by default). Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

0 installs
▌
Research Review · talhamah56
Get a deep critical review of research from a reviewer backend (Claude self-review by default, or Codex/manual if configured). Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.

0 installs
▌
Result To Claim · talhamah56
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A fresh Claude self-review pass evaluates results against intended claims and routes to next action (pivot, supplement, or confirm) when no external reviewer model is available. Use after experiments finish — before writing the paper or running ablations.

0 installs
▌
Ablation Planner · talhamah56
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.

0 installs
▌
Auto Review Loop · talhamah56
Auto Review Loop: Autonomous Research Improvement

0 installs
▌
Experiment Audit · talhamah56
Audit experiment integrity before claiming results. Uses adversarial review (external cross-model reviewer backend when available, Claude self-review otherwise) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.

0 installs
▌
Update Changelog · talhamah56
Read this skill before updating changelogs

0 installs
▌
Teach · talhamah56 bundle
Teach the user a new skill or concept, within this workspace.

0 installs
▌
Mapear · talhamah56
Use to map an existing (brownfield) codebase and produce docs/architecture/assessment.md — stack, architecture, implicit bounded contexts, maturity across the 5 axes, debts/risks, and historical decisions to become retroactive ADRs. Re-running updates the assessment. Runs standalone when the codebase changes or to analyze an unfamiliar repo. Trigger with /mapear.

0 installs
▌
Grill Me · talhamah56
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

0 installs
▌
Rebuttal · talhamah56
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.

0 installs
▌
Setup CI · talhamah56
Use to create or adjust the CI/CD pipeline that materializes the SDD gates — lint, static analysis (type-check/complexity/SAST), tests (unit/integration/acceptance) and coverage from docs/engineering/TESTING.md, with coverage and static analysis published as artifacts, plus the "PR fails without an approved spec" rule. Detects GitHub Actions / GitLab CI / other. Generates the file only with approval. Trigger with /setup-ci.

0 installs
▌
Diagramar · talhamah56
Use in discovery to draw the HIGH-LEVEL architecture in Mermaid — context diagram (C4 L1), containers (C4 L2), and the bounded contexts map (DDD). It reads vision, context-map, design, and assessment, and generates/updates docs/architecture/diagrams.md. It keeps a high level, with no implementation detail. Trigger with /diagramar.

0 installs
▌
Clarificar · talhamah56
Use for a GRILLING SESSION — a relentless interview that turns diffuse intent into shared understanding before building. It walks the decision tree ONE question at a time, resolving dependencies between choices, always with a recommended answer; it explores the codebase/docs instead of asking when the answer already exists. Ideal at the spec gate (testable ACs / Definition of Ready) and the design gate (hard-to-reverse decision). It produces an understanding summary that feeds product.md/design.md/spec.md. Trigger directly with /clarificar.

0 installs
▌
Meta Apply · talhamah56
Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with a reviewer jury (self-review, with a much weaker guarantee, when no other model is configured — see below) and human approval at landing. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.

0 installs
▌
Paper Plan · talhamah56
Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.

0 installs
▌
Paper Talk · talhamah56
End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: "做 talk", "做 PPT 全流程", "talk pipeline", "end-to-end slides", "做演讲", "conference talk full workflow". Use when the user wants the complete talk artifact, not just a slide deck.

0 installs
▌
Slurm Jobs · talhamah56
Write, submit, debug, and tune SLURM batch jobs for deep learning training on an HPC cluster. Covers sbatch script directives (--gres/--gpus-per-node, --cpus-per-task, --mem, --time, --array, --signal), single-node multi-GPU and multi-node torchrun/DDP launch under srun, hyperparameter sweeps with job arrays, atomic checkpointing with requeue-on-preemption, and post-mortem diagnosis with sacct/seff/squeue. Use this when the user mentions sbatch, srun, salloc, squeue, scancel, sacct, seff, sinfo, scontrol, SLURM_ARRAY_TASK_ID, SLURM_JOB_NODELIST, MASTER_ADDR, "job pending", "job got killed at the time limit", "OOM on the cluster", "requeue", "node-local scratch", "$SLURM_TMPDIR", "module load", or asks to turn a local training script into a cluster job, run a sweep on the cluster, or figure out why a job failed/pended/wasted its allocation. For the Qizhi platform specifically, use the qzcli skill instead — this skill is for generic SLURM.

0 installs
▌
Figure Spec · talhamah56 bundle
Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.

0 installs
▌
Paper Write · talhamah56 bundle
Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

0 installs
▌
Render HTML · talhamah56 bundle
Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says "渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html", or wants a polished web-rendered view of a Markdown artifact.

0 installs
▌
Skill Security Auditor · talhamah56 bundle
Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this skill safe", "scan skill for security", "check skill before install", "skill security check", "skill vulnerability scan".

0 installs
▌
Research Refine Pipeline · talhamah56
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.

0 installs
▌
Auto Paper Improvement Loop · talhamah56
Autonomously improve a generated paper via adversarial review (GPT-5.6-Sol xhigh when a cross-model backend is available, Claude self-review otherwise) → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.

0 installs
▌
Image Preprocessing And Tiling · talhamah56
Build and debug image preprocessing pipelines for deep learning when images are large, multi-channel, or scientifically calibrated - satellite/aerial GeoTIFF, Sentinel/Landsat multispectral stacks, whole-slide pathology (SVS/NDPI/OpenSlide), CT/MRI volumes, or any raster too big for the GPU. Use when the task mentions tiling, patching, sliding window, chip extraction, stride/overlap, seams when stitching predictions, reassembling tiles into a full-scene mask, normalization statistics, per-channel mean/std, percentile clipping, nodata poisoning stats, albumentations, image+mask augmentation, additional_targets, class imbalance in segmentation, empty/background tiles, slow DataLoader num_workers on Windows, worker seeding and reproducible augmentation, or converting a dataset to memmap numpy / WebDataset / LMDB / zarr. Also use when a segmentation or dense-prediction model trains fine but produces grid-shaped seams, all-background outputs, or scores far worse at inference than in validation.

0 installs
▌
Folder Specific Claude And Agents Md · talhamah56
Create a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped context. Use when David asks to create a CLAUDE.md for a folder, write folder instructions, or add agent context to a directory.

0 installs
▌
Medical Imaging Io · talhamah56
Load, convert, verify, and preprocess medical imaging data (DICOM, NIfTI, NRRD) for PyTorch/MONAI deep learning, and de-identify it safely. Use this when working with .dcm / DICOMDIR / .nii / .nii.gz / .mha / .nrrd files, pydicom, nibabel, SimpleITK, dcm2niix, or MONAI transforms; when converting a DICOM series to NIfTI; when a CT volume's intensities look wrong or Hounsfield-unit windowing / RescaleSlope / RescaleIntercept is involved; when volumes appear flipped or mirrored, or RAS vs LPS / affine / qform / sform orientation is in question; when resampling anisotropic voxel spacing to isotropic or writing Spacingd/Orientationd/ScaleIntensityRanged pipelines; when building a 3D segmentation or classification dataloader for CT/MRI/PET; and whenever PHI, de-identification, anonymization, defacing, burned-in annotations, IRB, or HIPAA come up in an imaging context.

0 installs
▌
Paper Illustration · talhamah56 bundle
Generate publication-quality AI illustrations for academic papers. Default renderer is Gemini (Paperbanana) image generation; an alternate codex-image2 renderer (local Codex app-server bridge) is available for users without Gemini API access — see "Alternate Renderer: codex-image2". Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.

0 installs
▌
Technical Diagrams · talhamah56
Generate technical/structural diagrams — flowcharts, sequence/class/ER/state/gantt diagrams, architecture and API-flow diagrams, database schemas, network diagrams, org charts, user-journey maps, mindmaps, process flows, and ASCII-art sketches. Use when asked to diagram an architecture, pipeline, schema, workflow, state machine, or system relationship, or to pick between Mermaid/Graphviz/D2/PlantUML for a diagram.

0 installs
▌
Writing Guidelines · talhamah56
Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

0 installs
▌
Integrity Forensics · talhamah56
Run the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the auditor said about it) against a paper via a SHA-pinned thin launcher — then convert the verdict into a typed policy gate (BLOCK/WARN/NO_NEW_BLOCKER) and an append-only obligations ledger. Use when user says "integrity forensics", "forensic audit this paper", "投稿前自查诚信", "审这篇论文的诚信", or says "anti-autoresearch" when the upstream repo's own skills are not installed. Also invoked by /paper-writing (submission self-forensics, default ON), /peer-review (forensic appendix), /resubmit-pipeline.

0 installs
▌
Geospatial Raster Io · talhamah56
Read, write, align, and normalize geospatial raster and vector data for ML training. Use when working with GeoTIFF/.tif/.tiff, COG, NetCDF/.nc, HDF5/.h5/.hdf, Zarr, shapefiles/.shp/GeoJSON, or the libraries rasterio, xarray, rioxarray, geopandas, fiona, pyproj, GDAL, gdalwarp. Triggers on tasks like "load this GeoTIFF", "tile a raster into patches", "reproject to EPSG:32633", "why is my normalization broken", "nodata / -9999 / NaN in my imagery", "align my label mask to my image", "rasterize these polygons", "burn shapefile into a label raster", "Sentinel-2 bands / SCL cloud mask / BOA offset", "Landsat Collection 2 scale factor", "QA_PIXEL bitmask", "open_mfdataset time stack", "chunk a NetCDF with dask", "compute per-band mean/std for a satellite dataset", or "install GDAL/rasterio on Windows". Also use when a model trains but predictions have black borders, when class counts don't match the legend, or when two rasters "look aligned" but produce garbage.

0 installs
▌
Handoff Conversation · talhamah56
Compact the current conversation into a single, detailed handoff message — everything that happened, why it happened, and what's left — output in a code block so it can be copy-pasted into a fresh agent session. Use when hitting context limits, switching focus, ending a work session, or partitioning a task across fresh contexts.

0 installs
▌
Idea Discovery Robot · talhamah56
Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.

0 installs
▌
Interview Cheatsheet · talhamah56
Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.

0 installs
▌
Patent Novelty Check · talhamah56
Assess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.

0 installs
▌
Agent Self Scheduling · talhamah56
Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers external clocks (Claude Code, Codex, Pi) vs Hermes' built-in scheduler.

0 installs
▌
Handoff Session State · talhamah56
Use when PAUSING/ending a work session (records the current state in docs/STATE.md to resume later) or when RESUMING (reads docs/STATE.md and the active spec and reassembles the context, proposing the next step). Keeps continuity between sessions of humans and agents. Trigger with /handoff-session-state.

0 installs
▌
Invention Structuring · talhamah56
Structure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.

0 installs
▌
Specification Writing · talhamah56
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.

0 installs
▌
Effective Agent Skills · talhamah56
How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this whenever a skill (Claude Skill, Agent Skill, SKILL.md) is being created, edited, reviewed, or debugged. Use when the user says "create a skill", "new skill", "update this skill", "improve a skill", "why isn't my skill triggering", or anything else involving authoring or editing SKILL.md files.

0 installs

69 published skills