harzva

@harzva source repo

251 skills
0 followers
6 hours ago last updated

▌
Roadmp Writer · harzva bundle
Use when writing, normalizing, splitting, auditing, or updating roadmp/roadmap Markdown files in the Just-DDL roadmpxx.md style: structured milestones, task files, checkbox governance, evidence-based completion, staged audits, candidate tables, assumptions, blockers, and Chinese production-roadmap prose.

0
installs
▌
Agentworkos Inventory · harzva
Scan and package-manage a local AgentWorkOS environment, including Codex skills, agent role cards, TERMS.md, AGENTS.md rules, local repositories, lockfiles, and sync drift. Use when the user asks to migrate machines, restore AI workspace context, package skills, or verify three-end sync.

0
installs
▌
Codex Loop · harzva bundle
Plan-driven recurring iteration for Codex without a native /loop command. Use when Codex should keep advancing the same project across repeated passes, read an active plan, inspect prior evolution notes, execute one bounded slice, write the next evolution note, prepare the next handoff, or run a periodic automation daemon that resumes the same Codex thread.

0
installs
▌
Team Reflective Loop · harzva bundle
Reflective supervisor and worker workflow for Codex-Managed-Agent team spaces. Use when working with .codex-team, assigning or reviewing mailbox tasks, checking blocked/stale/review work, maintaining failure_bank.json, creating bounded worker prompts, or preparing the next supervisor handoff.

0
installs
▌
Codex Spark Playbook · harzva bundle
Delegate small, bounded, non-multimodal implementation, review, README, docs, prompt, checklist, and mechanical-edit subtasks to codex-5.3-spark / gpt-5.3-codex-spark while keeping planning, final review, release decisions, publishing, device QA, visual inspection, and dangerous operations in the parent Codex session.

0
installs
▌
Cxspark · harzva bundle
Codex Spark shortcut skill for delegating small, bounded, non-multimodal coding, docs, README, prompt, checklist, review, or mechanical-edit tasks to a Spark sub-agent using gpt-5.3-codex-spark. Use when the user says cxspark, cx spark, Codex Spark shortcut, or asks to run a narrow task through Spark while the parent Codex session keeps planning, review, verification, publishing, and dangerous operations.

0
installs
▌
App Skills Suite · harzva bundle
Orchestrate Harzva app work across product UI, mobile and desktop implementation, local preview, emulator QA, release packaging, online update manifests, latest-download buttons, and safe overwrite-install behavior. Use when creating, redesigning, testing, releasing, or standardizing any app or app-like product.

0
installs
▌
Gitmarket Agent Search · harzva bundle
Discover trustworthy GitHub, Gitee, and GitCode repositories, Releases, installable assets, Codex skills, and MCP servers for AI-agent tasks. Use when an agent needs to find upstream software, compare release assets, inspect license/safety signals, locate skills/MCP integrations, or choose what to install or cite.

0
installs
▌
Repoatlas Repo Map · harzva bundle
Generate and query GitHub remote-to-local repository maps without requiring the RepoAtlas desktop app. Bundles gh-repo-cartographer for repository inventory, local checkout matching, compact maps, address-cache refreshes, and optional MCP lookup.

0
installs
▌
Gh Repo Cartographer · harzva bundle
Inventory locally configured GitHub accounts and repositories, map online GitHub repositories to local Git project folders, verify whether local branches match fetched upstream commits, batch-fetch GitHub Pages and release metadata, and produce Markdown/JSON reports for README optimization, repository cleanup, publishing audits, Pages matrices, release hubs, or account migration work. Use when the user asks to list all GitHub repos, find local project locations for GitHub repos, check local-vs-remote version status, audit README targets, collect Pages URLs/releases, or organize repos across Harzva/saihao/Just-Agent style managed accounts.

0
installs
▌
Rebuttal Audit · harzva bundle
Audit and polish one-page academic rebuttals or author responses, especially LaTeX/PDF responses with reviewer IDs, strict page limits, compact evidence tables, reviewer-specific concerns, protocol or label-use ambiguity, cost evidence, negative-case framing, and strict short-tail-line/orphan-word checks. Use when Codex must check formatting, page fullness, orphan lines, reviewer coverage, cited evidence, rebuttal tone, or final submission readiness.

0
installs
▌
Rebuttal Leak Audit · harzva bundle
Audit academic rebuttals, author responses, LaTeX/PDF text, Markdown drafts, and OpenReview replies for leaked internal/developer notes, local paths, tool traces, private experiment logistics, advisor or AI feedback traces, non-reviewer-facing remarks, and wording that should be rewritten before showing reviewers or ACs. Use when checking whether rebuttal content accidentally exposes Codex/ChatGPT/Claude notes, teacher/advisor comments, TODOs, logs, shell commands, filesystem paths, “AC-facing” meta-language, draft-only reasoning, or score-strategy language.

0
installs
▌
Rebuttal Promo Image · harzva bundle
Create public-safe GitHub README promo banners and Xiaohongshu vertical cards for academic rebuttal skill suites. Use when promoting rebuttal-skill-suite, turning GitHub/README/web screenshots into Image2-style marketing graphics, preparing Xiaohongshu copy, or logging Xiaohongshu publication evidence.

0
installs
▌
Rebuttal Dashboard Data · harzva bundle
Build private and sanitized dashboard data for Rebuttal Skill Suite by scanning a project, paper, reviews, rebuttal drafts, evidence ledgers, gate outputs, and persona feedback, then producing a JSON snapshot that the static webview can load.

0
installs
▌
Everything Agent CLI To Claude Code · harzva bundle
Bring web-login, CLI-first AI capabilities back into a Claude Code or LikeCode-centered workflow. Use when you want to call Codex, Gemini, Qwen, or Grok as external workers from within Claude Code.

0
installs
▌
Usecli Grok · harzva bundle
Use Grok as an external CLI worker inside a Claude Code or LikeCode-centered workflow. Good for critical review and alternative perspectives. Requires GROK_API_KEY or equivalent local configuration.

0
installs
▌
Usecli Qwen · harzva bundle
Use Qwen as an external CLI worker inside a Claude Code or LikeCode-centered workflow. Good for secondary critique, math reasoning, and multilingual tasks. May require device authorization on first run.

0
installs
▌
Usecli Codex · harzva bundle
Use Codex as an external CLI worker inside a Claude Code or LikeCode-centered workflow. Good for implementation-oriented feedback, code-aware review, and execution-heavy coding tasks.

0
installs
▌
Usecli Gemini · harzva bundle
Use Gemini as an external CLI worker inside a Claude Code or LikeCode-centered workflow. Good for broad review, first-pass critique, and structured feedback.

0
installs
▌
Xhs Skill Suite · harzva bundle
Use when planning, creating, reviewing, publishing, or recording Xiaohongshu notes for GitHub repositories, AI tools, AgentOS stacks, MCP tools, and open-source developer projects. Routes to promo-card generation, content quality review, MCP publishing workflow, and publication ledger skills.

0
installs
▌
Github Xhs Promo Card · harzva bundle
GitHub Xiaohongshu Promo Card

0
installs
▌
Xhs Campaign Workflow · harzva bundle
Use when running an end-to-end Xiaohongshu campaign for GitHub repositories, AI tools, AgentOS stacks, MCP tools, or open-source projects from repo facts through images, copy review, optional MCP publishing, and local publication records.

0
installs
▌
Xhs Publication Ledger · harzva bundle
Use when recording Xiaohongshu drafts, publish attempts, successful notes, MCP results, image assets, repository links, and sanitized publication evidence in a local ledger.

0
installs
▌
Xhs Publisher MCP Workflow · harzva bundle
Use when publishing a Xiaohongshu note through the local Xiaohongshu MCP, checking login status, preparing MCP publish arguments, or recording sanitized publish results. Does not store credentials or login state.

0
installs
▌
Xhs Content Quality Reviewer · harzva bundle
Use before publishing Xiaohongshu notes to improve title, opening hook, body structure, hashtags, cover text, evidence quality, and compliance for GitHub repositories, AI tools, AgentOS stacks, MCP tools, and developer products.

0
installs
▌
Appui Design Skill · harzva bundle
Create polished mobile app UI concepts, high-fidelity single-screen prototypes, multi-screen app theme suites, design systems, screenshots, and matching source code for iOS, Android, and mobile web apps. Use when Codex is asked for app UI design, mobile screen concepts, app design case studies, UI inspiration research, README-ready screenshot galleries, source-linked UI catalogs, or HTML/CSS/React source for mobile app screens.

0
installs
▌
Readme Design · harzva bundle
Design and rewrite polished GitHub README homepages for repositories and profile READMEs, especially Chinese/English open-source projects. Use when the user asks to beautify, redesign, improve, package, market, add a README logo or wordmark, or make a README more professional, visual, persuasive, scannable, or GitHub Pages-like. Focus on README aesthetics, layout, badges, screenshots, logo/wordmark identity, project positioning, information architecture, and Markdown/HTML that renders well on GitHub.

0
installs
▌
Design Md Flow · harzva bundle
Install, select, adapt, and apply DESIGN.md design-system files as a repeatable AI frontend workflow. Use when the user mentions DESIGN.md, getdesign.md, awesome-design-md, Google Stitch DESIGN.md, brand-inspired UI generation, installing a design style into a project, or turning a design reference into a workflow skill for agents.

0
installs
▌
App Preview Lab · harzva bundle
Create local, browser-openable preview labs for packaged apps, including APK WebView previews, IPA or iOS concepts, desktop installer previews, and mobile UI state mirrors. Use when asked to avoid repeated package installation, preview app UI/content in HTML, compare Android/iOS/desktop shells, add theme or language toggles, or document release artifact previews.

0
installs
▌
Readme Showcase Screenshot · harzva bundle
Generate polished README-ready screenshots, GIFs, videos, hero composites, and interactive HTML preview galleries for local web, mobile preview, desktop preview, packaged-app preview, and documentation projects. Use when Codex needs to update README visuals, capture UI states, record product demos, standardize docs screenshots, build preview galleries, or make a GitHub project presentation stronger.

0
installs
▌
Android Release Emulator QA Skill · harzva bundle
Validate Android release APKs with a local emulator and adb: detect MuMu/Android emulator, install APKs, launch apps, capture screenshots, UI XML, logcat, SHA256, and release-artifact evidence, then report QA readiness. Use when asked to test APKs, verify Android release builds, diagnose emulator install/launch/UI issues, check whether APK artifacts match a GitHub Release, or package a repeatable Android QA workflow. Recommended Windows emulator download: https://mumu.163.com/360mumu/.

0
installs
▌
Make Windows Silky · harzva
Evidence-first Windows workbench smoothness and token-saver workflow. Use when the user asks to make a Windows workspace, local AI/product folder, release workspace, or desktop packaging loop smoother by reducing duplicate artifacts, missing release proof, encoding failures, repeated context loading, and project re-entry cost.

0
installs
▌
Loloop · harzva bundle
loloop

0
installs
▌
Zhihu Publish · harzva bundle
Use when the task is to publish a Zhihu article from Markdown using the local browser-automation pipeline in this repo. Covers the text-only publishing chain, the multimodal chain that uploads Markdown images into the Zhihu editor, cookie-based login checks, and choosing between the stable text script and the richer multimodal script.

0
installs
▌
Auto Dot Claude · harzva bundle
Use when a project needs a standard .claude workspace initialized or repaired incrementally. This skill audits the existing .claude folder, adds missing files and directories without overwriting existing rules/skills/settings, and can optionally evolve the structure over time for the current project.

0
installs
▌
Full Unpackd Rep · harzva
Use when the task is to unpack a local reference repository into a Chinese structural topic page, update site navigation, stamp dates, and leave behind a reusable deconstruction note for the repo.

0
installs
▌
Gen Zhihu Article · harzva
Gen Zhihu Article

0
installs
▌
Skill Auto Evolve · harzva
Automatically fix, enhance, and optimize other skills when problems occur. Use when a skill fails or produces unexpected results. Prevents similar issues in the future.

0
installs
▌
Hot Topic Curation · harzva bundle
Use when the task is to build or maintain a repo-local 热门话题/AI日报专项, aggregate multiple public hot-topic sources such as AIbase Daily or RSS feeds, normalize them into a reusable snapshot, route the findings into the best existing site hotspot pages, and keep the hot-topic hub updated over time.

0
installs
▌
Keyword Site Topic · harzva bundle
Use when the task is to take a user-provided keyword, search the web for relevant articles, summarize and cluster the findings, choose the most appropriate existing `site/` topic or hotspot page in this project, and draft a publish-ready Markdown article with explicit image prompt placeholders or Mermaid notes.

0
installs
▌
Zhihu Copy Diagnose · harzva bundle
Diagnose a Zhihu Markdown draft before publishing. Use when a Zhihu article needs a final copy audit for AI-flavored phrasing, professionalism, readability, and evidence strength, especially before calling zhihu-publish.

0
installs
▌
Skillsmp Find Install · harzva
Use when the user wants to find a suitable SKILL.md-based skill from SkillsMP, compare candidates, verify the upstream GitHub repository, and optionally install it into Claude Code or Codex skill directories with the local installer script.

0
installs
▌
Wechat Article To Site · harzva
WeChat Article to Site Page

0
installs
▌
Repo Release Governance · harzva
Use when working on learn-likecc and the task involves new requirements, roadmap updates, README updates, git commits, GitHub Pages updates, or release/version changes. Ensures every new requirement is written into plan files, unfinished work remains in TODO sections, and release/git/pages handling follows the repo workflow without the user needing to restate it each time.

0
installs
▌
Github Repo Search Download · harzva bundle
Use when the user wants to search GitHub repositories by keyword, inspect ranked candidates, compare likely matches, and optionally clone the selected repository into a specified local directory. Good for prompts like “帮我搜 GitHub 上相关仓库”, “帮我找并下载一个相关仓库”, “搜索 GitHub 上的项目然后拉到 reference”, or “按关键词找仓库并 clone 到指定位置”.

0
installs
▌
Curate External Feed Topics · harzva bundle
Curates foreign tech blogs (e.g. Daily Dose of Data Science Substack) via RSS, classifies items into learn-likecc RAG vs Agent “技术热点” sub-topics, drafts Chinese summaries with attribution, and appends rows to the site HTML tables. Use when the user asks to ingest Daily Dose of DS, Substack feeds, auto-fetch hot topics, translate articles for topic-rag-hot or topic-agent-hot, or refresh external curated content for the course site.

0
installs
▌
Verify · harzva bundle
Verify Skill

0
installs
▌
Ieee Writing · harzva bundle
Draft, rewrite, and audit IEEE journal manuscripts via compact suite fragments for journals, components, evidence, structure, and official-source checks.

0
installs
▌
Ieee Citation · harzva bundle
Audit IEEE citations, reference integrity, missing related work, and bibliography consistency without fabricating sources.

0
installs
▌
Ieee Response · harzva bundle
Prepare IEEE reviewer-response letters, revision matrices, rebuttal plans, and change summaries with source-grounded compliance checks.

0
installs
▌
Ieee Reviewer · harzva bundle
Simulate IEEE journal reviewers and identify novelty, evidence, experiment, formatting, and integrity risks with compact module routing.

0
installs
▌
Ieee Submission · harzva bundle
Prepare IEEE submission-package checklists, cover letters, declarations, rights/license checks, and final-file reminders with live verification warnings.

0
installs
▌
Ieee Paper Miner · harzva bundle
Mine the lawful template-paper corpus for section structure, figure/table/caption patterns, and reviewer-risk lessons without copying protected text.

0
installs
▌
Ieee Skill Suite · harzva bundle
Context-safe IEEE journal manuscript skill-suite with routing for writing, review, response, figure/table, citation, submission, official-source checks, and paper-template mining.

0
installs
▌
Ieee Figure Table · harzva bundle
Audit and improve IEEE figures, tables, captions, result reporting, and visual consistency using compact component fragments.

0
installs
▌
Elsevier Writing · harzva bundle
Draft, rewrite, and audit Elsevier journal manuscripts via compact suite fragments for journals, components, evidence, structure, and official-source checks.

0
installs
▌
Elsevier Citation · harzva bundle
Audit Elsevier citations, reference integrity, missing related work, and bibliography consistency without fabricating sources.

0
installs
▌
Elsevier Response · harzva bundle
Prepare Elsevier reviewer-response letters, revision matrices, rebuttal plans, and change summaries with source-grounded compliance checks.

0
installs
▌
Elsevier Reviewer · harzva bundle
Simulate Elsevier journal reviewers and identify novelty, evidence, experiment, formatting, and integrity risks with compact module routing.

0
installs
▌
Elsevier Highlights · harzva bundle
Create and audit Elsevier Highlights, graphical-abstract briefs, and short submission assets with Guide-for-Authors verification reminders.

0
installs
▌
Elsevier Submission · harzva bundle
Prepare Elsevier submission-package checklists, cover letters, declarations, rights/license checks, and final-file reminders with live verification warnings.

0
installs
▌
Elsevier Paper Miner · harzva bundle
Mine the lawful template-paper corpus for section structure, figure/table/caption patterns, and reviewer-risk lessons without copying protected text.

0
installs
▌
Elsevier Skill Suite · harzva bundle
Context-safe Elsevier journal manuscript skill-suite with routing for writing, review, response, figure/table, highlights, citation, submission, official-source checks, and paper-template mining.

0
installs
▌
Elsevier Figure Table · harzva bundle
Audit and improve Elsevier figures, tables, captions, result reporting, and visual consistency using compact component fragments.

0
installs
▌
Tac Writing · harzva bundle
IEEE Transactions on Automatic Control: control theory, systems, stability, optimization, estimation, and rigorous proofs.

0
installs
▌
Tai Writing · harzva bundle
IEEE Transactions on Artificial Intelligence: artificial intelligence methods, systems, learning algorithms, and applied AI validation.

0
installs
▌
Tip Writing · harzva bundle
IEEE TIP: image processing, restoration, enhancement, compression, analysis, computational imaging.

0
installs
▌
Tmi Writing · harzva bundle
IEEE TMI: medical imaging, image reconstruction, segmentation, diagnosis assistance, quantitative imaging.

0
installs
▌
Tmm Writing · harzva bundle
IEEE TMM: multimedia analysis, multimodal learning, retrieval, generation, interaction.

0
installs
▌
Tro Writing · harzva bundle
IEEE Transactions on Robotics: robotics algorithms, perception, planning, control, manipulation, field validation.

0
installs
▌
Tsp Writing · harzva bundle
IEEE TSP: signal processing theory, algorithms, estimation, detection, optimization.

0
installs
▌
Twc Writing · harzva bundle
IEEE Transactions on Wireless Communications: wireless communication systems, MIMO, networks, resource allocation, 6G-related methods.

0
installs
▌
Ieee Table · harzva bundle
IEEE Table: submission-ready tables, editable table text, caption logic, notes, abbreviations, and non-duplicative presentation.

0
installs
▌
Jbhi Writing · harzva bundle
IEEE JBHI: biomedical and health informatics, clinical AI, digital health systems.

0
installs
▌
Pami Writing · harzva bundle
TPAMI / PAMI: computer vision, pattern analysis, machine learning, recognition, representation learning.

0
installs
▌
Tase Writing · harzva bundle
IEEE T-ASE: automation science, manufacturing systems, logistics, robotics for automation, decision/control systems.

0
installs
▌
Tcyb Writing · harzva bundle
IEEE Transactions on Cybernetics: cybernetics, computational intelligence, machine learning, control, human-machine systems.

0
installs
▌
Tgrs Writing · harzva bundle
IEEE TGRS: geoscience and remote sensing, earth observation, hyperspectral/SAR/optical analysis.

0
installs
▌
Tifs Writing · harzva bundle
IEEE TIFS: information forensics, security, privacy, biometrics, trustworthy media.

0
installs
▌
Tkde Writing · harzva bundle
IEEE TKDE: data engineering, knowledge discovery, databases, graph mining, information retrieval.

0
installs
▌
Tpel Writing · harzva bundle
IEEE TPEL: power electronics, converters, control, reliability, hardware experiments, and energy systems.

0
installs
▌
Tvcg Writing · harzva bundle
IEEE TVCG: visualization, visual analytics, graphics, VR/AR, human-centered visual computing.

0
installs
▌
Ieee Figure · harzva bundle
IEEE Figure: figures, panels, visual evidence, resolution/readability, accessibility, and text-reference order.

0
installs
▌
Tcomm Writing · harzva bundle
IEEE Transactions on Communications: communication theory, wireless systems, coding, networking, signal processing for communications.

0
installs
▌
Tcsvt Writing · harzva bundle
IEEE TCSVT: video technology, image/video coding, multimedia systems, visual signal processing.

0
installs
▌
Tnnls Writing · harzva bundle
IEEE TNNLS: neural networks, learning systems, optimization, theory, adaptive systems.

0
installs
▌
Pr Writing · harzva bundle
Pattern Recognition: pattern recognition, computer vision, machine learning, statistical recognition.

0
installs
▌
Ieee Caption · harzva bundle
IEEE Caption: figure and table captions, legends, abbreviation expansion, symbol explanation, and standalone interpretability.

0
installs
▌
Kbs Writing · harzva bundle
Knowledge-Based Systems: knowledge-based AI, reasoning, decision support, data-driven intelligence.

0
installs
▌
Prl Writing · harzva bundle
Pattern Recognition Letters: concise pattern recognition articles and letters.

0
installs
▌
Ieee Abstract · harzva bundle
IEEE Abstract: abstract drafting, compression, claim discipline, and contribution evidence alignment.

0
installs
▌
Ieee Appendix · harzva bundle
IEEE Appendix: appendices, extended derivations, extra tables, and material that should not interrupt the main paper.

0
installs
▌
Ieee Equation · harzva bundle
IEEE Equation: equation formatting, notation consistency, numbered equations, and mathematical readability.

0
installs
▌
Cmpb Writing · harzva bundle
Computer Methods and Programs in Biomedicine: biomedical software, methods, computational systems, validation, and reproducible implementations.

0
installs
▌
Cviu Writing · harzva bundle
Computer Vision and Image Understanding: computer vision, image understanding, scene analysis, perception systems.

0
installs
▌
Eaai Writing · harzva bundle
Engineering Applications of Artificial Intelligence: AI methods with engineering application value, validation, deployment constraints, and practical impact.

0
installs
▌
Eswa Writing · harzva bundle
Expert Systems With Applications: AI methods with practical decision-support or expert-system applications.

0
installs
▌
Ieee Polishing · harzva bundle
IEEE Polishing: technical English polishing for IEEE-style manuscripts.

0
installs
▌
Jvcir Writing · harzva bundle
Journal of Visual Communication and Image Representation: visual communication, image/video representation, compression, retrieval, and media analysis.

0
installs
▌
Ieee Conclusion · harzva bundle
IEEE Conclusion: conclusion concision, contribution recap, implications, and no-new-claim discipline.

0
installs

251 published skills · page 1 of 3