← all publishers

huajiexiewenfeng

@huajiexiewenfeng source repo

Report this profile Claim this profile

• 48 skills
• 0 followers
• 1 day ago last updated

1. ▌
   Agent Global Context · huajiexiewenfeng bundle

   Use when personal long-term memory may materially improve an important decision, personalized writing or collaboration, learning or research planning, growth review, or cross-task continuation; when evaluating whether a project or technology fits the user's research direction; when the user requests durable personal recall or storage; or when AGC maintenance is requested. Skip self-contained factual or mechanical tasks.
   0
   installs
2. ▌
   Artifact Radar · huajiexiewenfeng bundle

   Use when the user asks to see, find, list, open, review, or click files generated or modified in the current session, including Markdown, Word, Excel, PowerPoint, PDF, images, HTML, CSV, JSON, archives, or other agent-created deliverables with timestamps and clickable links.
   0
   installs
3. ▌
   Codex Reset Credits · huajiexiewenfeng bundle

   查询并用中文展示 Codex 重置次数、每次重置的剩余时间、过期时间，以及过期前 1 天和过期前 1 小时的提醒时间。Use when the user asks how many Codex reset credits, reset次数, rate-limit reset credits, credits expiry times, reminder times, or how long each Codex reset credit has before expiration.
   0
   installs
4. ▌
   Codex Session Recovery · huajiexiewenfeng bundle

   Use when Codex Desktop sessions, threads, sidebar history, project conversations, or local session lists are missing after an update or restart, only one conversation is visible, sessions need to be restored for a workspace, or the user asks to repair Codex session_index/state/global-state/cwd metadata. This skill audits and restores local Codex session metadata safely.
   0
   installs
5. ▌
   Course Designer · huajiexiewenfeng bundle

   Use when the user wants to design a personalized learning course before tracking it: clarify a learning goal or North Star, turn a vague study intention into a staged curriculum, create a sprint/day learning map, define outputs and verification standards, or produce a course package that can later be imported into learning-companion. Trigger on requests like "帮我定制课程", "我想学 X 该怎么规划", "帮我确认 North Star", "设计一个 90 天/150 天学习计划", "生成可导入 learning-companion 的课程", or similar course-design and self-learning planning requests.
   0
   installs
6. ▌
   Learning Companion · huajiexiewenfeng bundle

   Use when the user wants to manage a long-term learning plan, create or update a learning dashboard, track study progress across sessions, receive study reminders, record "下课", review learning status, continue a study plan, view learning progress or refresh a static learning dashboard, or asks the assistant to teach or explain today's learning content.
   0
   installs
7. ▌
   Project Feature Dev · huajiexiewenfeng bundle

   Use when the user says develop:feature, wants to implement a feature or new requirement in the current project, or wants project-local docs/ai-coding context and team coding rules loaded before development.
   0
   installs
8. ▌
   Project Context Init · huajiexiewenfeng bundle

   Use when the user says develop:init, wants to initialize or refresh project AI coding context, scan the current project source code, read existing AI-generated docs as supporting context, or generate project-local docs/ai-coding files.
   0
   installs
9. ▌
   Obsidian Wiki Init · huajiexiewenfeng bundle

   Use this whenever the user wants to initialize, adopt, map, onboard, or set rules for an Obsidian vault as an LLM Wiki. Trigger on requests like "initialize Obsidian LLM Wiki", "adopt this vault", "create a knowledge center", "generate a knowledge map", "scan my vault", "guide me step by step", or "set Obsidian wiki rules". This skill creates structure, inventories existing content, generates an onboarding roadmap, and guides the user toward the first ingest batch. It must not move or delete existing user files.
   0
   installs
10. ▌
    Obsidian Wiki Query · huajiexiewenfeng bundle

    Use this whenever the user asks questions that should be answered from an Obsidian LLM Wiki or personal knowledge base. Trigger on requests like "基于当前 wiki 回答", "according to my knowledge base", "从 Obsidian 里找", "summarize from my wiki", "generate an outline from my knowledge base", or "what do my notes say about...". This skill reads wiki pages first and only falls back to raw/source material when needed.
    0
    installs
11. ▌
    Obsidian Wiki Doctor · huajiexiewenfeng bundle

    Use this whenever the user wants to diagnose, validate, score, report on, or explain the health or maturity of an Obsidian LLM Wiki, including prompts like "run Obsidian Wiki Doctor", "诊断 wiki", "给 wiki 打健康分", "出中文健康报告", "看看初始化后有没有用", or questions about whether poor query quality is caused by wiki structure. This skill is read-only and never repairs files.
    0
    installs
12. ▌
    Obsidian Wiki Ingest · huajiexiewenfeng bundle

    Use this whenever the user wants to ingest, import, index, summarize, organize, or turn Obsidian notes or external folders into an Obsidian LLM Wiki. Trigger on requests like "整理这个目录", "把这个目录做成 wiki", "ingest this file", "scan these external folders", "bring these documents into my knowledge base", or "archive this approved file". External files are path-indexed by default; confirmed single files may use deterministic archive-import.
    0
    installs
13. ▌
    Obsidian Wiki Runtime · huajiexiewenfeng bundle

    Shared deterministic runtime dependency for the Obsidian LLM Wiki workflow skills. Use only when another obsidian-wiki skill needs root resolution or Doctor commands.
    0
    installs
14. ▌
    Obsidian Wiki Maintain · huajiexiewenfeng bundle

    Use this whenever the user wants to repair, fix, patch, update, or apply approved structural fixes to an Obsidian LLM Wiki. Route diagnosis, validation, scoring, and health reports to obsidian-wiki-doctor first. This skill is for applying confirmed structure and safety repairs, not knowledge Q&A.
    0
    installs
15. ▌
    Learning Coach · huajiexiewenfeng

    Use only when the current user request directly invokes `$thinking-skills:learning-coach` or combines a direct invocation command with the exact canonical name `learning-coach`. Do not activate from ordinary domain intent, depth language, mention, evaluation, modification, quoted data, prior turns, or component handoff.
    0
    installs
16. ▌
    Content Creator · huajiexiewenfeng bundle

    Use when the user is developing articles, essays, posts, newsletters, scripts, talks, titles, outlines, arguments, audience positioning, drafts, or content structure.
    0
    installs
17. ▌
    Skill Evaluator · huajiexiewenfeng

    Use when reviewing a Thinking Skills failure, golden case candidate, user feedback about a skill response, eval result, routing mistake, unsafe behavior, overly long output, too many questions, jargon exposure, regression risk, or when deciding how to improve or preserve a skill.
    0
    installs
18. ▌
    Thinking Router · huajiexiewenfeng

    Use when a user request needs intent classification, especially when domain work, host-native technical work, or ordinary conversation could each fit.
    0
    installs
19. ▌
    Emotional Support · huajiexiewenfeng bundle

    Use when the user expresses anxiety, sadness, shame, self-blame, burnout, overwhelm, relationship pain, emotional confusion, distress, crisis signals, or asks to understand feelings and needs.
    0
    installs
20. ▌
    Benchmark Assistant · huajiexiewenfeng

    Use when the user wants to run Thinking Skills benchmarks, test a skill, check regressions, generate benchmark prompts, score saved benchmark responses, update or compare the benchmark dashboard, add a benchmark case, interpret benchmark results, or decide what to patch after a benchmark failure.
    0
    installs
21. ▌
    Conversation Review · huajiexiewenfeng

    Use when the user asks for self-review, Dolores mode, conversation review, skill trace audit, failure analysis, eval gap detection, improvement-loop suggestions, failure case or golden case status, or skill feedback dashboard.
    0
    installs
22. ▌
    Technical Deep Dive · huajiexiewenfeng

    Use only when the current user request directly invokes `$thinking-skills:technical-deep-dive` or combines a direct invocation command with the exact canonical name `technical-deep-dive`. Do not activate from ordinary domain intent, depth language, mention, evaluation, modification, quoted data, prior turns, or component handoff.
    0
    installs
23. ▌
    Article Visual Director · huajiexiewenfeng bundle

    Use whenever the user wants to plan, generate, validate, or insert a coherent set of visuals for an existing or substantially complete Markdown article, especially a technical article for CSDN or WeChat Official Accounts. Covers article covers, concept illustrations, process diagrams, architecture diagrams, visual style selection, image prompts, approval gates, and non-destructive Markdown integration. Do not use as the primary skill for early article ideation or drafting, or for a standalone diagram that is not part of an article.
    0
    installs
24. ▌
    Hr Agent Copilot · huajiexiewenfeng bundle

    Use when the user asks for general HR recruiting assistance without naming a specific child skill, or wants to continue an existing HR hiring workflow whose next stage must be selected.
    0
    installs
25. ▌
    Devops Package Copilot · huajiexiewenfeng bundle

    Use this skill when acting as the DevOps Agent Copilot to package/build local projects from natural language, especially Chinese requests like "打包某个项目", "再打一次", "换个版本打包", or "打全部模块". The skill discovers project-local docs/docker-build-*.md rules, reuses session-scoped packaging context including the last confirmed version, asks only for missing critical values, avoids repeated confirmation for ordinary follow-up builds in the same session, runs existing local scripts, and summarizes build artifacts or failures.
    0
    installs
26. ▌
    Devops Release Copilot · huajiexiewenfeng bundle

    Use this skill when acting as the DevOps Agent Copilot for release preparation after images are built, especially requests like "发布 v1.3.1", "准备 v1.3.1 部署目录", "更新 docker compose", "同步镜像号", "把刚打包的镜像更新到 compose", or "检查 application 环境变量并补到 compose". The skill prepares versioned release directories from a version number, creates missing target version folders, copies docker-compose YAML from the nearest previous version when needed, maps packaged tar/manifest image tags to deployment files, updates Docker Compose YAML safely, compares application configuration placeholders with compose environment variables, verifies diffs, and summarizes release handoff artifacts without deploying or pushing unless explicitly requested.
    0
    installs
27. ▌
    Hr Resume Screening Copilot · huajiexiewenfeng bundle

    Use when the user wants to screen resumes, is preparing to screen resumes, asks what materials or inputs are required for screening, wants PDF resumes analyzed, compares candidates against a JD, ranks or scores candidates, or requests an interview recommendation list.
    0
    installs
28. ▌
    Project Develop Copilot · huajiexiewenfeng bundle

    Use when the user wants project development help from natural intent, including Chinese prompts for 项目开发、项目文档、跨项目关系、跨项目任务分发、项目图谱仓库、Base Graph、需求、bug、日志、评审、继续, or routing into project lifecycle skills.
    0
    installs
29. ▌
    Technical Visual Companion · huajiexiewenfeng bundle

    Use this skill whenever the user asks to turn a confirmed technical design into a polished offline static HTML visual, including architecture, system boundaries, service interactions, sequence flows, deployment topology, state transitions, failure recovery, or multiple complementary technical diagrams. Do not use it to invent or complete an unconfirmed design, build a product UI, or produce Mermaid, slides, PDF, or PNG-only output.
    0
    installs
30. ▌
    Hr Candidate Detail Report Copilot · huajiexiewenfeng bundle

    Use this skill when the user asks for candidate details, score reasons, personnel detail reports, strengths and weaknesses, education/company/stability analysis, risk analysis, or why candidates were ranked in a certain order after resume screening. This skill explains candidate fit in detail and should usually follow hr-resume-screening-copilot.
    0
    installs
31. ▌
    Hr Interview Question Generator Copilot · huajiexiewenfeng bundle

    Use this skill when the user has selected interview candidates and asks for interview questions, interview focus areas, reference answers, follow-up probes, risk verification points, weak-answer signals, or candidate-specific technical interview plans. This skill should generate targeted questions based on the JD and each candidate's resume claims.
    0
    installs
32. ▌
    Project Fix · huajiexiewenfeng bundle

    Use when diagnosing or fixing a project bug, error, failed test, regression, incident, log symptom, or unexpected behavior with scoped project context and LLM Wiki bug summaries.
    0
    installs
33. ▌
    Project Init · huajiexiewenfeng bundle

    Use when initializing or refreshing a project-local LLM Wiki, adopting a repository, discovering modules, preparing tool bridges, or migrating legacy docs/ai-coding context into the project development context structure.
    0
    installs
34. ▌
    Project Query · huajiexiewenfeng

    Use when answering, discussing, locating, or synthesizing project questions from a project-local `.llm-wiki`, including cross-project refs, related requirements, bugs, source proxies, working-context pages, design docs, artifacts, dashboard state, and development notes without starting implementation.
    0
    installs
35. ▌
    Project Finish · huajiexiewenfeng bundle

    Use when finishing verified project work, syncing actual changes back to LLM Wiki, updating requirement or bug status, recording verification, and preparing handoff.
    0
    installs
36. ▌
    Project Ingest · huajiexiewenfeng bundle

    Use when adding PRDs, links, Markdown, PDF, Word, logs, meeting notes, customer feedback, or temporary project materials into a project LLM Wiki as batch-organized source proxies, full source copies when appropriate, manifests, and ingest index entries.
    0
    installs
37. ▌
    Project Review · huajiexiewenfeng bundle

    Use when reviewing project changes for code risk, test gaps, requirement consistency, scope drift, stale context, LLM Wiki sync, tool-bridge consistency, or readiness before commit, PR, or merge.
    0
    installs
38. ▌
    LLM Wiki Doctor · huajiexiewenfeng

    Use when checking, scoring, diagnosing, or explaining a project-local .llm-wiki health state, LLM Wiki Doctor output, wiki maturity score, empty wiki skeletons after project init, Project Graph evidence warnings, or llm_wiki_doctor pre-commit/CI failures.
    0
    installs
39. ▌
    Project Develop · huajiexiewenfeng bundle

    Use when developing or changing a project requirement, feature, API/protocol behavior, or code path with project-local context; use before implementation whenever a change needs a requirement/doc anchor, scoped context, acceptance criteria, or `.llm-wiki` Flow Record.
    0
    installs
40. ▌
    Project Maintain · huajiexiewenfeng

    Use when checking, auditing, repairing, linting, or maintaining a project-local `.llm-wiki` or Base Graph Project Graph fleet, especially when requirements, working-context pages, Project Graph edges/candidates, cross-project refs, Base Graph catalog/registry links, artifacts, dashboards, module indexes, Flow Records, logs, links, handoff entries, or wiki visibility may be missing, stale, orphaned, inconsistent, unsafe, or hard to find.
    0
    installs
41. ▌
    Project Base Init · huajiexiewenfeng

    Use when initializing or refreshing an independent Base Graph repository for Project Develop Copilot, including Chinese prompts like 初始化 Base Graph、项目图谱仓库、跨项目导航层、注册业务项目、多项目 .llm-wiki 总目录, without treating the Base repo as a business project.
    0
    installs
42. ▌
    Project Task Dispatch · huajiexiewenfeng bundle

    Use when the user asks PDC to distribute, monitor, review, or manage work across saved Codex Projects that belong to one Base Graph reality project. Uses peer Codex Project Sessions, not Agent Team Subagents.
    0
    installs
43. ▌
    Project Graph Auto Edge · huajiexiewenfeng

    Use when turning Project Graph candidates into source-backed edge proposals through Base Graph lookup and local/remote read-only verification, including Chinese prompts like 自动生成 edge proposal, 自动登记边候选, auto-edge, or 通过 base-graph 找项目类方法但先给人确认.
    0
    installs
44. ▌
    Project Graph Visualize · huajiexiewenfeng bundle

    Use when the user asks to generate, rebuild, refresh, update, preview, or validate an interactive HTML visualization of a Base Graph or Project Graph, including “生成 Base Graph 可视化”, “刷新 Project Graph HTML”, “更新 graph.html”, “查看整个跨项目关系图”, and similar graph/dashboard requests.
    0
    installs
45. ▌
    Project Session Extract · huajiexiewenfeng

    Use when extracting, summarizing, distilling, reviewing, or importing historical chat/session context into a project .llm-wiki as recallable Session Digests first, including pasted conversations, transcript files, exported AI sessions, colleague chats, old agent handoffs, or conversation summaries; promote selected digest items into requirements, bugs, Flow Records, or dashboard only after explicit user confirmation.
    0
    installs
46. ▌
    Project Graph Human Edge · huajiexiewenfeng

    Use when a human confirms, rejects, or manually enters Project Graph edges and cross-ref pins, including Chinese prompts like 人工登记 edge, human-edge, 确认 proposal, 手动登记跨项目关系, or 接受/拒绝 edge proposal.
    0
    installs
47. ▌
    Project Graph Candidates Scan · huajiexiewenfeng

    Use when scanning the current project-local .llm-wiki or source tree for potential Project Graph relationship candidates, including Chinese prompts like 扫描 candidates, project-graph candidates scan, 自动扫描候选关系, or 发现缺失跨项目关系.
    0
    installs
48. ▌
    Codex Token Usage · huajiexiewenfeng bundle

    Use when the user asks to count, audit, compare, or report local Codex Desktop or CLI token usage, including daily token counts, total or net usage, cache hit rate, peak periods, or an offline HTML usage dashboard.
    1
    install