HughYau

@hughyau source repo

35 skills
0 followers
3 hours ago last updated

▌
Learn · hughyau bundle
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment. Trigger for: - Explicit learning requests: teach, explain, ELI5, walk me through, quiz me, flashcards, "I'm rusty on"; definitions ("what is X") - Terse concept names implying "help me understand this": "Galois theory," "transformers, from scratch" - Confusion signals: "won't stick," "keep mixing these up," "not getting it" - Learning-path questions: prerequisites, sequencing, what to study before X - Conceptual questions about mechanisms, causes, or dynamics Don't trigger for: - Tasks: coding, writing, calculation, translation, factual lookup, news updates - Personal troubleshooting; resource/textbook recommendations - Claude's evaluative verdict: opinion prompts ("do you think X", "settle this", "honest take", "is X dead / still taken seriously") and interpretive takes ("was X really as harsh as people say")

0
installs
▌
Fable4sci · hughyau bundle
Transform dense technical, scientific, cybersecurity, computing, network, or life-science research questions into clear source-domain-neutral fables for non-specialists. Use when the user asks to allegorize, fable-ize, turn complex research into a metaphorical story, explain without jargon, produce both plain and more imaginative fable versions, or reduce listener association with the original field while preserving the reasoning structure.

0
installs
▌
Zuhui · hughyau bundle
Use when preparing research progress updates, advisor emails, lab meeting notes, or collaborator syncs from scattered evidence such as git history, notebooks, figures, and notes, especially when the output must adapt to audience, tone, and Chinese/English workflow.

0
installs
▌
Opensci Skill · hughyau bundle
opensci-skill

0
installs
▌
Scvi Tools · hughyau bundle
Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score differentially expressed genes per cluster. For spatial deconvolution / mapping use the cell2location, DestVI, or Tangram methods instead.

0
installs
▌
Skill Creator · hughyau bundle
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

0
installs
▌
Self Awareness · hughyau bundle
Claude Science's own session database schema and SDK surface for introspection via host.query(). Load this when you need to query your own conversation history, token usage, cost accounting, execution log, or artifact metadata beyond what host.frames()/host.artifacts() provide — e.g. "how many tokens has this session used", "what was my last tool call", "list every file I've written", "where are messages stored", "what tables can I query", "inspect frames.context_data", or any time you're about to PRAGMA-probe the Claude Science metadata DB to discover its schema.

0
installs
▌
Brian2 · hughyau bundle
Brian2

0
installs
▌
Pynibs · hughyau bundle
pyNIBS

0
installs
▌
Nilearn · hughyau bundle
Nilearn

0
installs
▌
Mne Python · hughyau bundle
MNE-Python for MEG/EEG/iEEG/fNIRS analysis pipelines, from loading raw signals to epoching, preprocessing, time-frequency analysis, inverse modeling, and reporting. Use when working with mne.create_info, mne.io.RawArray, mne.Epochs, mne.compute_covariance, mne.preprocessing.ICA, mne.time_frequency.psd_array_welch, mne.make_sphere_model, mne.Report, sensor/source-space workflows, or electrophysiology quality control.

0
installs
▌
Spikeinterface · hughyau bundle
SpikeInterface

0
installs
▌
PDF Explore · hughyau bundle
Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance of something across the whole document (datasets, benchmarks, citations, figures, table rows, accession numbers — including appendices). Parses the PDF once with a deterministic Python kernel: `pdf_pages` (pages as persistent text, or high-res images), `pdf_outline` (embedded TOC), `pdf_scan` (a lexical pre-filter that narrows a long doc to candidate pages), `pdf_grep` (regex sweep for exhaustive pattern extraction). You read the shortlist and do the relevance / summary / extraction judgment yourself. For PDF creation/manipulation, use reportlab/pypdf directly.

0
installs
▌
Figure Style · hughyau bundle
Publication-grade figure correctness and legibility rules. Load before drawing any plot and call `apply_figure_style()` — sets a role-mapped font-size ladder, outward ticks, frameless legends, and 300-dpi output. The skill is a checklist, not a house look: data fidelity (claim-titles tested against every row, excluded data never enters summaries), label economy (floor and ceiling), colour threading, chart-choice-by-data-shape, layout, and a render-then-verify QA loop (bbox collision + per-panel perceptual check). Ships helpers: focal_palette, bar_with_points, strip_with_median, end_of_line_labels, panel_letter, set_frame, panel_crops. For multi-panel figures load `figure-composer`; for whole-paper figure arc load `paper-narrative`.

0
installs
▌
Paper Writing · hughyau bundle
Draft a CV/graphics conference paper section by section using outline-first writing — list the thinking down to sentence granularity in the user's own language first, then produce English prose. Ships LaTeX skeleton templates with real published examples (PVNet, Deep Snake, Neural Body, ManhattanSDF, DreamBooth) for abstract, introduction, technical-challenge framing, method, experiments, related work, conclusion and title, plus a fully worked four-granularity outline and the 11-step order the sections get written in. Use whenever the user is writing or planning any part of a paper, asks how to introduce a technical challenge or motivate a module, wants help with the paper's story, or asks which section to write next — and reach for it before writing any English paragraph, since drafting prose before the outline is the single most common cause of unfixable structure. Boundaries: deadline tracking and the submission schedule belong to research-project; if the text already exists and the complaint is that it re

0
installs
▌
Paper Revision · hughyau
Revise paper text in response to criticism — your own, an advisor's, or a reviewer's. Two halves that share one discipline: (1) fixing prose by encoding it back into a high-level outline, locating where the logic is missing or jumps, fixing it there, then decoding to English again, plus the sentence-flow test and paragraph-clarity checks; (2) writing a rebuttal, which first answers why each reviewer gave that score, classifies every concern into answerable-from-existing-content / needs-new-experiment / misunderstanding / genuine-limitation, then drafts per reviewer section in their own question order. Use whenever the user pastes text to improve, says the writing is unclear or doesn't flow, is working through comments on a draft, mentions receiving reviews or scores, or asks how to answer a weakness — and resist polishing sentences directly, because smooth prose over a broken outline is the hardest failure to detect later. Boundary: this fixes text that exists; if the question is whether the paper will surviv

0
installs
▌
Figure Composer · hughyau bundle
Compose one publication-grade multi-panel figure. Entry from a one-line claim + data files, OR from an existing figure via `derive_outline_prompt` (you read the PNG). Runs a per-figure loop: outline (12-col grid, per-panel ask + label_budget) → render each panel with `panel_task` (loading `figure-style`), one at a time or parallelized → tile + stamp letters with `compose_figure` → adversarial composite self-review with two-tier feedback (Tier-1 outline_revisions / Tier-2 per-panel violations) → regen affected panels, ≤3 rounds. Helpers: panel_task / compose_figure / compose_crops / composite_review_task / derive_outline_prompt. For one standalone plot use `figure-style`; for whole-paper figure ordering use `paper-narrative`.

0
installs
▌
Paper Narrative · hughyau bundle
Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. `paper_brief_prompt(abstract, captions)` hands you the prompt to write the brief yourself (pitch/vision/per-figure-claims); then you play a handling editor over the full deck and return hook_verdict (would Fig 1 make me send this for review?), arc (hook→mechanism→evidence→application), figure_moves (panels in the wrong figure), missing_panels (concrete analyses to RUN), kill_list, and boldest_defensible_fig1. Hands per-figure claims to `figure-composer`. Load when writing or revising a paper.

0
installs
▌
Research Project · hughyau bundle
Set up, take over, reorganize, and maintain a research project directory so the work stays iterable across months and across agent sessions. Ships four scripts — explore_project.py (read-only survey of an unfamiliar messy project: what it is, what's active, what's stale, versioned duplicates, and the questions to ask the user), migrate.py (applies a user-approved reorganization plan; dry-run by default, moves and archives only, has no delete operation, writes an undo script), init_project.py (canonical layout + PROJECT.md single source of truth, and the dated submission schedule when given a deadline), and project_status.py (audits any directory for unfilled decisions, stale state, deadline vs. writing progress, experiment-log health, and stops hard when the topic scores as already-solved). Use whenever a user starts a project, hands you an existing research folder that wasn't built to this structure, asks to tidy or restructure a project, asks where things stand or what to do next, resumes after a break, men

0
installs
▌
Literature Review · hughyau bundle
Find, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.

0
installs
▌
Paper Self Review · hughyau
Adversarially review a paper before submission and predict exactly what reviewers will attack, using the five-category rejection checklist (contribution, writing clarity, result strength, experimental coverage, method soundness) plus a claim-to-evidence audit. Produces a findings report with a verdict per item, not vague impressions. Use whenever the user asks if a paper is ready, what reviewers will say, whether the contribution is enough, whether they will get rejected, or asks you to review someone else's submission — and run it proactively before any submission deadline, because the checklist routinely surfaces a missing ablation or an unsupported abstract claim while there is still time to fix it. Boundary: this predicts what gets attacked and produces the findings list; actually rewriting what it finds is paper-revision. 中文触发：自评审、review论文、审稿、会不会被拒、contribution够不够、投稿前检查、adversarial writing、帮我看看这篇论文。

0
installs
▌
Research Ideation · hughyau bundle
Decide what research problem to attack and how to attack it — the two halves of想idea. Applies a hard four-case novelty gate (cases 1-2 mean a well-established solution exists and the work must not proceed), ranks candidate problems by importance, then derives a pipeline-level method by stripping the surface symptom to the real technical challenge and combining techniques from a challenge-insight tree. Returns a filled scorecard with a go / change-topic verdict, not an opinion, and ships a fully worked example scorecard showing the granularity each cell needs. Use whenever the user floats an idea, picks a direction, asks whether something is novel or already done, asks how to solve a failure case, proposes stacking two existing methods, or asks you to implement a research idea — especially that last one, since implementing an already-solved problem is the most expensive mistake this methodology names. Pairs with literature-review for the retrieval the gate depends on. 中文触发：选题、想idea、这个题值不值得做、有没有创新空间、novelty够不够、

0
installs
▌
Research Experiment · hughyau bundle
Design experiments that decide something, and diagnose failing ones by driving from surface symptom to root technical cause before changing anything. Treats improving a method as SGD on the idea, where the root-cause analysis IS the gradient — so it outputs a ranked candidate-cause table with a falsifying experiment for each, never a list of things to try, and ships a fully worked example diagnosis to show the granularity. Also covers minimum-viable exploratory design (binary feasibility criterion, one-day version), what comparison/ablation/demo experiments a paper needs, and which harder data to push to. Use whenever the user reports bad results, a method that doesn't work, metrics dropping after a change, asks what to run next, or asks which ablations a paper needs — and use it BEFORE proposing hyperparameter tweaks, because an unverified guess about the cause is a random gradient that burns a whole cycle. 中文触发：实验不work、效果不好、掉点了、做什么实验、实验设计、消融、ablation、baseline、调不出来、为什么不收敛、要不要试试调参、做什么demo。

0
installs
▌
Research Methodology · hughyau
Entry point and router for pengsida's research methodology (CV/graphics, CCF 优博). Carries the lifecycle map, the five decision rules that override defaults when they conflict, the anti-pattern table, and routing to the six methodology skills and the five bundled execution skills. Load this first when the request spans stages, when it is unclear where in the lifecycle the user is, or when the user asks you to implement or pursue an idea with no evidence it cleared the novelty gate — those are exactly the requests that look narrow from outside and cost months when mis-scoped. When the request unambiguously names one stage — a failing experiment, a paragraph that reads badly, a rebuttal to write — go straight to that skill instead; routing through here would add a hop without adding a decision. 中文触发：科研流程、研究方法论、怎么做科研、做一篇论文、科研卡住了、不知道该干什么、这个项目该怎么推进。

0
installs
▌
Contradiction Analysis · hughyau bundle
矛盾分析法：把复杂问题拆成若干对立面，找出规定其他矛盾的主要矛盾及其主要方面，判定对抗性 / 非对抗性，并据此选择处理方式。当问题头绪多、多个因素互相牵制、优先级不清、根因不明、反复修不好、trade-off 说不清时触发；直接执行类任务或用户已定方案时不触发。 English: Contradiction analysis. Decompose a tangled problem into opposing forces, isolate the principal contradiction and its dominant side, classify it as antagonistic or non-antagonistic, and choose the response accordingly. Trigger on unclear priorities, unknown root causes, recurring failures, or trade-offs that resist explanation; skip for direct execution or when the user has already chosen the solution.

1
install
▌
Criticism Self Criticism · hughyau bundle
批评与自我批评：在工作完成、阶段验收、收到批评或同类错误反复出现时，对成果和过程做诚实、具体、基于事实的审视，输出可执行的改进项，并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗"；任务刚开始或只是单步查询时不触发。 English: Criticism and self-criticism. After delivery, at a review checkpoint, on receiving criticism, or when the same mistake recurs, examine the result and the process honestly and concretely, produce actionable fixes, and accept valid criticism without defensiveness. Triggers include review, retrospective, audit, "check this for problems", "are you sure"; skip at the start of a task or for one-step lookups.

1
install
▌
Practice Cognition · hughyau bundle
实践认识论：把方案、假说或判断放回实践中检验，按「实践 → 认识 → 再实践」螺旋迭代，并在开始前写明循环终止条件。当你提出了假说要验证、一次尝试失败要复盘再来、发现自己只想不做或只做不想时触发；一次性输出、答案可直接查阅、还没形成假说（先调查）时不触发。 English: Practice-cognition loop. Test a hypothesis or plan in practice, learn from the result, and iterate in a rising spiral with an explicit stop condition. Trigger when a plan needs validation, an attempt failed and must be retried, or you notice thinking without doing (or doing without thinking); skip for one-shot outputs, lookup questions, or before any hypothesis exists.

1
install
▌
Spark Prairie Fire · hughyau bundle
星火燎原：从零起步、资源极少时，先评估客观条件，选定一个能站稳、能复用、能扩展的"根据地"（最小切入点），扎根后再逐步扩张，拒绝四处出击的流寇主义。当启动新项目、做 MVP / pilot、面对宏大目标不知从何下手、或做了很多零散事却没有积累时触发；项目已有稳固基础、只是修改现有系统时不触发。 English: Spark a prairie fire. When starting from almost nothing, assess the conditions, choose one base area (a minimal foothold that can hold, be reused, and expand), dig in, then grow step by step instead of scattering effort. Trigger for new projects, MVPs, pilots, daunting goals with no obvious first step, or busy work that accumulates nothing; skip when a solid base already exists or the task modifies an existing system.

1
install
▌
Investigation First · hughyau bundle
调查研究：在下判断、做决策、给建议之前，先用第一手材料弄清现状，产出「事实 / 推断 / 未知」三栏调查结论。当上下文不完整、证据薄弱、领域陌生、用户说"先别动手"、或你发现自己在凭印象作答时触发；已充分调查后的执行阶段不要重复触发。 English: Investigate before judging. Gather firsthand facts and produce a fact / inference / unknown ledger before any recommendation. Trigger when context is incomplete, evidence is thin, the domain is unfamiliar, the user says "look first", or you notice yourself answering from impression; skip when investigation is already done and the task is pure execution.

1
install
▌
Protracted Strategy · hughyau bundle
持久战略：面对长期、复杂、短期不可能速胜的任务，客观评估态势，划分战略防御 / 相持 / 反攻三阶段，判定当前所处阶段，设置阶段转换条件，并在困难阶段仍给出局部进攻点。当任务跨多个会话或多轮迭代、资源暂时不足、或出现"想放弃"与"一把梭"两种情绪时触发；任务能在当前会话完成时不触发。 English: Protracted strategy. For long-horizon work that cannot be won quickly, assess the situation objectively, divide the effort into defense / stalemate / counter-offensive stages, name the current stage and its exit condition, and always identify a local offensive even while accumulating. Trigger when work spans many sessions or iterations, resources are temporarily short, or you notice either defeatism or a rush to finish; skip when the task fits in the current session.

1
install
▌
Workflows · hughyau
工作流组合：当一个任务明显需要多件思想武器接力时，提供四种标准组合模式（新项目启动、复杂问题攻坚、方案迭代优化、阶段复盘），定义调用顺序、每步交接物和终止条件。触发信号包括从零启动、疑难攻坚、迭代优化、阶段复盘；单一 skill 就够用时不触发。 English: Workflow patterns. When a task clearly needs several skills in sequence, pick one of four standard patterns (project kickoff, hard-problem assault, iterative improvement, stage retrospective) that fix the order, the handoff artifact between steps, and the stop condition. Skip when a single skill suffices.

1
install
▌
Arming Thought · hughyau
求是方法论的入口与总原则。在每次新的顶层会话开始时加载一次，用「实事求是」约束全部判断，并只在明确适用时把任务路由到对应的方法论 skill；被派遣执行单一具体任务的子 agent 直接跳过。 English: Entry point and governing principle of the Qiushi methodology. Load once at the start of a top-level session to enforce "seek truth from facts" and route to a downstream skill only when it clearly helps. Delegated sub-agents on narrow tasks should skip it.

1
install
▌
Overall Planning · hughyau bundle
统筹兼顾：当多个目标、指标或利益方相互制约、优化一项会伤害另一项时，识别全部辩证关系对，检查片面性，为每对关系定出当前阶段的侧重与底线，评估系统性影响，并设失衡预警。触发信号包括 trade-off、目标冲突、速度 vs 质量、短期 vs 长期、"顾此失彼"；只有单一目标、用户已定取舍、或属硬性二选一时不触发。 English: Overall planning. When several goals, metrics, or stakeholders constrain each other and optimizing one harms another, map every dialectical pair, check for one-sidedness, set the current emphasis and floor for each pair, assess system-wide effects, and define imbalance alarms. Triggers include trade-offs, goal conflicts, speed vs quality, short vs long term; skip for single-goal work, decisions the user already made, or hard either/or constraints.

1
install
▌
Concentrate Forces · hughyau bundle
集中兵力：多件事同时争抢时间、注意力或预算时，列出全部待办，选定唯一主攻目标并公开锁定，彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发；只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。 English: Concentrate forces. When several tasks compete for time, attention, or budget, enumerate them, lock onto a single main target, finish and verify it completely, then move on. Trigger when priorities sprawl, effort is scattered, or you must decide what to do first; skip when there is one task, tasks are independent and parallel, or the user explicitly wants them advanced together.

1
install
▌
Mass Line · hughyau bundle
群众路线：从持有真实情况的多方（用户、使用者、代码库、日志、运行结果）收集分散意见，系统化为方案，再带回去对齐与检验，循环改进。当多方意见分歧、需要汇总零散反馈、方案要拿回给真实使用者确认、或你发觉自己在闭门造车时触发；信息源单一且完整、处于执行阶段时不触发。 English: Mass line. Collect scattered input from everyone who holds ground truth (users, operators, codebase, logs, runtime results), synthesize it into a coherent plan, take it back for alignment and validation, and iterate. Trigger when inputs conflict, feedback must be consolidated, a plan needs sign-off from real users, or you sense you are designing in isolation; skip when there is a single complete source and the work is pure execution.

1
install

35 published skills