Refinex-Space
33 verified skills33 total stars
harness-dispatch
Use when executing a Harness plan that has independent tasks or problem domains suitable for delegated workers in the current session.
data-ai1
harness-bootstrap
Bootstrap or complete a repository's Harness Engineering control plane for agent-first development. Use when initializing or upgrading a new or existing frontend, backend, full-stack, monorepo, or library repository with root and local AGENTS.md, docs/ routing docs, docs/OBSERVABILITY.md, docs/exec-plans/tech-debt-tracker.md, execution-plan directories, generated Harness manifest files, and a repo-local `python3 scripts/check_harness.py` entrypoint. Especially relevant for prompts such as `初始化 Harness`, `为这个项目落地 Harness Engineering`, `搭建 AGENTS/docs/PLANS`, `给这个仓库建立 agent-first 控制面`, or `$harness-bootstrap`.
development1
harness-garden
Audit, repair, and continuously correct Harness Engineering drift in repositories that already have some form of agent control plane. Use when inspecting root and local AGENTS.md, docs/PLANS.md, docs/OBSERVABILITY.md, docs/exec-plans, generated Harness manifests, and repo-local `python3 scripts/check_harness.py`; then auto-fix low-risk drift, refresh stale managed files, and create a remediation execution plan for high-risk semantic rewrites. Especially relevant for prompts such as `检查这个项目的 Harness 是否健康`, `修复文档索引和 AGENTS 偏离`, `纠正 Harness 漂移`, `做 doc-gardening`, `做 Harness audit`, or `$harness-garden`.
development1
harness-plan
Use after an approved Harness spec to create a decision-complete, audit-oriented execution plan under docs/exec-plans/active/.
testing1
harness-finish
Use when Harness implementation work is complete and the agent must verify, archive the plan, update docs/PLANS.md, and offer exactly four finish options: local merge, push and PR, keep branch, or discard work. Requires `harness-verify` before presenting finish options and requires discard confirmation before any destructive cleanup.
testing1
harness-fix
Plan and execute bug fixes, regression repair, incident remediation, flaky-path debugging, and evidence-driven investigation in repositories that already use Harness Engineering control plane artifacts such as `docs/PLANS.md`, `docs/exec-plans/active`, `docs/OBSERVABILITY.md`, `docs/generated/harness-manifest.md`, and repo-local `python3 scripts/check_harness.py`. Use when the user reports a broken behavior and the agent should rewrite the bug report, run harness preflight, reproduce or bound the failure, create or update a fix plan, apply the smallest justified repair, add regression protection, sync `docs/PLANS.md`, and archive the plan deterministically. Especially relevant for prompts such as `$harness-fix`, `修复...`, `这个报错`, `为什么坏了`, or `排查回归`.
development1
harness-using
Use when starting any repository-work conversation that may involve Harness Engineering routing, control plane setup, drift repair, feature delivery, bug fixing, or completion verification. Invoke before clarifying questions or code changes whenever there is any reasonable chance a Harness skill applies. Especially relevant for prompts such as `初始化 Harness`, `控制面坏了`, `文档漂移了`, `做这个功能`, `修复这个 bug`, `排查回归`, or `确认现在能不能宣称完成`.
development1
harness-using
Use when starting any repository-work conversation that may involve Harness Engineering routing, control plane setup, drift repair, feature delivery, bug fixing, or completion verification. Invoke before clarifying questions or code changes whenever there is any reasonable chance a Harness skill applies. Especially relevant for prompts such as `初始化 Harness`, `控制面坏了`, `文档漂移了`, `做这个功能`, `修复这个 bug`, `排查回归`, or `确认现在能不能宣称完成`.
development1
harness-verify
Use when about to claim that repository work is complete, fixed, passing, or ready, especially after Harness feature work, bug fixes, drift repairs, or control plane updates. Require fresh verification evidence before any success claim, commit summary, or handoff message. Especially relevant for prompts such as `现在算完成了吗`, `确认修好了`, `测试应该过了`, `可以提交了吗`, or `帮我确认能不能宣称 ready`.
testing1
harness-verify
Use when about to claim that repository work is complete, fixed, passing, or ready, especially after Harness feature work, bug fixes, drift repairs, or control plane updates. Require fresh verification evidence before any success claim, commit summary, or handoff message. Especially relevant for prompts such as `现在算完成了吗`, `确认修好了`, `测试应该过了`, `可以提交了吗`, or `帮我确认能不能宣称 ready`.
testing1
mermaid-diagrams
Design, repair, and standardize Markdown-embedded Mermaid diagrams with syntax-safe, renderer-portable authoring and restrained visual taste. Use when Codex needs to create or fix Mermaid code for flowcharts, sequence diagrams, state diagrams, class diagrams, ER diagrams, timelines, or other Mermaid-backed technical visuals in Markdown, docs, ADRs, blog posts, architecture notes, or any writing workflow. Also use when another skill already decided that a diagram is needed and the remaining task is to turn that visual plan into clean Mermaid that avoids parser breakage, crowding, awkward layout, and decorative styling.
development1
office-docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
development1
office-pdf
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
content-media1
office-pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
documentation1
harness-feat
Plan and execute new feature work, capability delivery, and structured refactors in repositories that already use Harness Engineering control plane artifacts such as `docs/PLANS.md`, `docs/exec-plans/active`, `docs/OBSERVABILITY.md`, `docs/generated/harness-manifest.md`, and repo-local `python3 scripts/check_harness.py`. Use when the user gives a rough implementation goal and the agent should rewrite the task, run harness preflight, create or update a live execution plan, execute in small validated slices, sync `docs/PLANS.md`, and archive the plan deterministically. Especially relevant for prompts such as `$harness-feat`, `任务：实现...`, `新增...`, `重构...`, or `做这个功能`.
development1
harness-review
Use when requesting or performing review of the current diff, active Harness plan output, or a pull request, and when receiving review feedback that must be verified, evaluated, answered, and implemented item by item.
databases1
harness-fix
Own bug, regression, incident, and flaky-path repair inside a Harness Powers control plane. Use when repository work requires a bug brief, reproduction evidence, root-cause isolation, minimal fix, regression protection, plan archival, and handoff through harness-verify.
testing1
harness-feat
Own feature delivery, capability work, and structured refactors inside a Harness Powers control plane. Use when repository work needs preflight, sprint contract, active execution plan ownership, incremental implementation, TDD-informed verification, plan archival, and handoff through harness-verify.
development1
harness-frontend
Use this skill for tasks that produce user-facing interfaces: landing pages, marketing sites, dashboards, admin tools, web apps, prototypes, components, forms, or any HTML/CSS/JSX/Vue output users will see. Trigger even if the user doesn’t say “design” (e.g. “build a page”, “make a dashboard”, “create a form”, “scaffold UI”, “polish this”, “convert Figma”, or UI screenshots). Applies to both new builds and redesigns. In repository work, this is a frontend specialization layered under `harness-brainstorm`, `harness-feat`, or `harness-fix`, not a replacement for lifecycle ownership. The workflow is opinionated and taste-driven: identify surface type, run quick structured option selection with the user, define visual/content/interaction direction, apply the correct rule set (landing/app/dashboard/game), generate production-ready code, and validate both design quality and repo delivery readiness. Goal: avoid generic AI UI patterns and produce deliberate, high-quality, ship-ready interfaces.
tools1
harness-execute
Use to execute an active Harness plan from docs/exec-plans/active/ while updating checkboxes, evidence, verification, and completion handoffs.
testing1
harness-bootstrap
Bootstrap or complete a repository's Harness Engineering control plane for agent-first development. Use when initializing or upgrading a new or existing frontend, backend, full-stack, monorepo, or library repository with root and local AGENTS.md, docs/ routing docs, docs/OBSERVABILITY.md, docs/exec-plans/tech-debt-tracker.md, execution-plan directories, generated Harness manifest files, and a repo-local `python3 scripts/check_harness.py` entrypoint. Especially relevant for prompts such as `初始化 Harness`, `为这个项目落地 Harness Engineering`, `搭建 AGENTS/docs/PLANS`, `给这个仓库建立 agent-first 控制面`, or `$harness-bootstrap`.
development1
drift-doctor
Detect and fix drift in project AGENTS.md files and agent control plane. Use this skill whenever the user wants to audit, recalibrate, refresh, update, or fix their existing AGENTS.md files, or when they mention "drift", "stale AGENTS.md", "outdated agent instructions", "recalibrate", "sync agents", "audit control plane", "AGENTS.md is wrong/old/broken", or when they suspect their agent harness has fallen out of sync with the codebase. Also trigger when a user says things like "my agents keep making wrong assumptions", "Claude doesn't understand the new structure", "we refactored but the AGENTS.md is old", "check if my AGENTS.md is still accurate", or "update my agent docs". This skill is the companion to init-deep — init-deep creates the control plane from scratch, drift-doctor maintains it over time. Do NOT use for initial creation of AGENTS.md (use init-deep instead). Do NOT use for general code review or documentation updates unrelated to agent context.
development1
init-deep
Deep initialization of project AGENTS.md hierarchy and control plane for AI coding agents. Use this skill whenever the user wants to set up, initialize, bootstrap, or create AGENTS.md / CLAUDE.md files for their project, or when they mention "init-deep", "harness setup", "control plane", "agent context", "project initialization for agents", or want to make their codebase agent-ready. Also trigger when a user says things like "set up my repo for Claude Code", "make this project work better with agents", "create agent instructions", "bootstrap harness", or "initialize agent docs". This skill handles both existing large codebases (where hierarchical, module-scoped AGENTS.md files are needed) and new/small projects (where brainstorming with the user comes first). Do NOT use this skill for routine code changes, bug fixes, or general documentation — it is specifically for creating the structured agent control plane.
development1
code-comments
Use when adding, fixing, reviewing, or generating code comments, docstrings, Javadoc, JSDoc/TSDoc, rustdoc, SQL comments, or documentation comments for source, markup, configuration, or database files.
development1
tech-rewrite
Transform existing technical material of any quality — rough notes, meeting minutes, AI-generated drafts, legacy wikis, code comments, email threads, chat exports — into high-quality technical documentation. Use this skill whenever the user asks to rewrite, restructure, clean up, polish, formalize, turn notes into an article, improve a draft, or extract documentation from existing material. Companion to the tech-writing skill — tech-writing handles the blank-page case, tech-rewrite handles the case where source material already exists. The two skills share identical quality standards, so a rewrite must be indistinguishable from a from-scratch piece on the same topic. Default output language is Chinese with technical terms in English. This skill enforces a mandatory extraction-before-composition firewall because low-quality sources contaminate AI-rewritten output through specific mechanisms when the source is treated as a template rather than as raw intelligence.
development1
dev-java
Enforce production-grade Java development standards when writing, reviewing, or architecting Java code. Covers commenting, core Java idioms (Stream, collections, concurrency, generics), 23 GoF design patterns, SonarQube/Alibaba p3c/Lombok rules, Spring Boot MVC structure, Spring Cloud DDD microservices, MyBatis/JPA/transaction management, exception handling, logging, REST API design, testing, and security. Trigger whenever the user writes Java code, reviews Java code, designs a Spring Boot or Spring Cloud project, implements a design pattern, fixes code smells, discusses architecture, or asks about Java best practices. Also trigger when Java code is pasted for feedback or the user asks about package structure, DTO/VO/PO conventions, or coding standards.
development1
harness-brainstorm
Use before creative or behavioral changes to explore intent, constraints, options, and produce an approved Harness execution spec before planning.
data-ai1
harness-worktree
Use when starting Harness implementation work that needs an isolated git worktree, especially before executing an approved plan or beginning a scoped feature/fix branch. Select the repository's worktree directory, verify ignored project-local directories, create a `codex/`-prefixed branch by default, run setup and baseline checks, and prevent plan execution on main/master unless the user explicitly allows it.
development1
office-xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
development1
harness-frontend
Use this skill for tasks that produce user-facing interfaces: landing pages, marketing sites, dashboards, admin tools, web apps, prototypes, components, forms, or any HTML/CSS/JSX/Vue output users will see. Trigger even if the user doesn’t say “design” (e.g. “build a page”, “make a dashboard”, “create a form”, “scaffold UI”, “polish this”, “convert Figma”, or UI screenshots). Applies to both new builds and redesigns. In repository work, this is a frontend specialization layered under `harness-feat` or `harness-fix`, not a replacement for lifecycle ownership. The workflow is opinionated and taste-driven: identify surface type, run quick structured option selection with the user, define visual/content/interaction direction, apply the correct rule set (landing/app/dashboard/game), generate production-ready code, and validate both design quality and repo delivery readiness. Goal: avoid generic AI UI patterns and produce deliberate, high-quality, ship-ready interfaces.
tools1
harness-garden
Audit, repair, and continuously correct Harness Engineering drift in repositories that already have some form of agent control plane. Use when inspecting root and local AGENTS.md, docs/PLANS.md, docs/OBSERVABILITY.md, docs/exec-plans, generated Harness manifests, and repo-local `python3 scripts/check_harness.py`; then auto-fix low-risk drift, refresh stale managed files, and create a remediation execution plan for high-risk semantic rewrites. Especially relevant for prompts such as `检查这个项目的 Harness 是否健康`, `修复文档索引和 AGENTS 偏离`, `纠正 Harness 漂移`, `做 doc-gardening`, `做 Harness audit`, or `$harness-garden`.
development1
tech-planner
Plan a complete technical blog series with cognitively sequenced articles, each containing a self-sufficient writing prompt. Use this skill whenever the user asks to plan, outline, or architect a multi-article technical blog series on any technology topic (frameworks, languages, databases, infrastructure tools, protocols, design patterns, etc.). Also trigger when the user mentions "系列博客规划", "技术系列文章", "blog series planning", "article series outline", or asks to break a broad technical topic into a structured sequence of articles. This skill covers the full pipeline from research through knowledge graph construction to series architecture design. Do NOT use for writing a single article (that is tech-writing's job), for general content calendars, or for non-technical blog planning.
tools1
tech-writing
Write a single rigorous mid-to-long-form technical blog article from a user topic, writing intent, draft prompt, or tech-planner handoff. Use this skill for professional engineering articles, architecture explainers, mechanism deep dives, production postmortems, technology comparisons, framework/API analysis, and article drafting requests that require a falsifiable thesis, concrete technical anchors, diagrams, and anti-AI-slop validation. Do NOT use for multi-article series planning, general content calendars, marketing copy, API reference documentation, or short social posts.
development1