hashgraph-online
- 1.5k skills
- 0 followers
- 1.6k repo stars
- 2 days ago last updated
- ▌ MCP Builder 4 · hashgraph-onlineUse when creating a new MCP (Model Context Protocol) server, extending an existing one, or debugging tool discoverability/performance. Guides through research → implementation → test → eval phases with TypeScript-first guidance matching our stack. Trigger on phrases like "build an MCP server", "expose X as an MCP tool", "write MCP tools for Y", "integrate Z via MCP".
- ▌ Security 2 · hashgraph-online bundleReview code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks. Use when: asked whether code is safe to ship, even one small handler.
- ▌ Claude Code 2 · hashgraph-onlineUse when the user asks for help with Claude Code, the Claude Code CLI, Anthropic coding-agent workflows, prompts to hand off work to Claude Code, or troubleshooting Claude Code setup and terminal usage.
- ▌ Review Work 2 · hashgraph-onlineQuality gate: verify each acceptance criterion of a completed task/work unit, run quality checks, and create follow-up tasks for gaps. Use before merging or to audit delivered work. Invoked as /agiflow:review-work <work-unit-or-task>. Uses get_work_unit, get_task, update_task, create_task, create_task_comment.
- ▌ Strategic Compact 5 · hashgraph-online bundle上下文优化技能,通过 trigger-based 懒加载和 context composition awareness 自动重组长会话上下文。
- ▌ Eval Harness 8 · hashgraph-online bundle正式评估框架,实现 eval-driven development (EDD) 原则。 用于定义 pass/fail 标准、测量 pass@k 指标、创建回归测试套件。
- ▌ Database Designer 2 · hashgraph-onlineИспользуй только внутри активного Codex Project Autopilot-проекта, когда data-layer уже относится к плану автопилота.
- ▌ Anti UI Slop 4 · hashgraph-online bundleStop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use when designing, implementing, redesigning, critiquing, or pre-ship reviewing a web or iOS interface in Codex, Claude Code, Cursor, Copilot, or another coding agent. Trigger with "anti-ui-slop", "stop UI slop", "ground this UI in real screens", or "run the UI finish gate".
- ▌ Email Sequence 3 · hashgraph-online bundleDesign an ESP-ready email sequence: subjects, copy, timing, branching, deliverability. "build a welcome sequence"
- ▌ Prompt Optimizer 4 · hashgraph-onlineAnalyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.
- ▌ Skill Audit 2 · hashgraph-online bundleAudit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
- ▌ Context Engineering 2 · hashgraph-online项目级上下文工程框架:通过 PROJECT / REQUIREMENTS / ROADMAP / STATE 四层文档 为每个任务建立结构化上下文,控制 token 预算,防止上下文腐烂, 确保跨会话连续性。与 context-lifecycle 的 L0-L3 层互补。
- ▌ Tree Ring Memory 2 · hashgraph-onlineGuides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.
- ▌ Hook Development 2 · hashgraph-onlineUse when creating, modifying, or debugging Claude Code hooks — PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification. Covers the plugin `hooks/hooks.json` wrapper format vs. the user `settings.json` direct format, matchers, security patterns, `$CLAUDE_PLUGIN_ROOT` portability, lifecycle limitations, and debugging. Trigger on "add a hook", "validate tool use", "block dangerous commands", "enforce completion", "hook-based automation".
- ▌ Product Research 2 · hashgraph-onlineDeep Codex-native Amazon FBA product validation using LaunchFast MCP and the LegacyX criteria. Use when the user wants a serious viability review for a keyword, niche, or adjacent niche expansion.
- ▌ Frontmatter Guard 2 · hashgraph-onlineInjects the canonical vault frontmatter schema snippet into agent prompts before any vault-write task, preventing malformed YAML frontmatter in Obsidian notes. <example>Context: wave-executor is about to dispatch a vault-mirror agent that writes learning notes under ~/Projects/vault/40-learnings/. user: "dispatch vault-write agent" assistant: "Injecting frontmatter-guard snippet into agent prompt (vault scope detected). Required fields: id, type, created, updated. Enum type: note|daily|project|person|reference|idea|learning|session." <commentary>The wave-executor pre-dispatch hook calls detectVaultTaskScope() — the fileScope contains /Projects/vault/40-learnings/ so the guard triggers and the snippet is prepended to the agent system prompt.</commentary></example>
- ▌ Data Scraper Agent 4 · hashgraph-onlineBuild a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
- ▌
- ▌ Laravel Security 6 · hashgraph-onlineLaravel security best practices for authn/authz, validation, CSRF, mass assignment, file uploads, secrets, rate limiting, and secure deployment.
- ▌ Java Coding Standards 4 · hashgraph-onlineJava coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.
- ▌ Linkedin Post Writer 2 · hashgraph-online bundleDraft a new LinkedIn post from scratch using one of 20 2026 hook formulas (anaphora, R.I.P., time-anchor, curiosity-gap, contrarian, controlled A/B, false-binary, and more) plus a founders-edition angle library, picked by engagement goal (comments, reposts, likes, saves). Runs the humanizer pass and schedules via Publora on approval. Use to write a post, find a hook or proven format, or get founder-specific angles. Not for reviewing existing drafts (use linkedin-humanizer --mode audit).
- ▌ Ontoly Software Graph 3 · hashgraph-onlineUse Ontoly Software Graph evidence, CLI reports, MCP, and official Ontoly Agent Skills before searching source files when reviewing architecture, dependencies, request flows, configuration, impact, or security-sensitive ownership in JavaScript, TypeScript, Python, or Go repositories.
- ▌ Linkedin Profile Optimizer 2 · hashgraph-online bundleAudit and rewrite a LinkedIn profile end-to-end for 2026: headline, About 7-step, Featured, banner, photo, Experience metrics, Skills, custom URL, recommendations. Triggers on "review my profile", "rewrite my headline", "fix my About", "optimize banner", "profile audit", "LinkedIn bio". Converts resume-style profiles to ones that convert 3-5x better. Not for writing feed content (use linkedin-post-writer).
- ▌ Run 2 · hashgraph-onlineRun a full pipeline for a task. Orchestrates roles through stages (standalone or HOTL-integrated).
- ▌ Refactor 5 · hashgraph-online bundleRestructure or clean up code with no behavior change, proved by before-and-after checks. Use when: asked to clean up, extract, dedupe or simplify, even one function.
- ▌ Browser QA 4 · hashgraph-online自动化视觉测试与 UI 交互验证。部署功能后使用浏览器自动化验证关键页面、核心路径和发布前回归。 当任务需要真实浏览器验证渲染、导航、交互或前端上线风险时使用。
- ▌ Brooks Test 2 · hashgraph-online bundleTest quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow execution, poor readability. Triggers when: user asks about test quality, shares test files for review, or expresses frustration: "tests keep breaking whenever I change anything", "our tests take forever", "tests pass but bugs still reach production", or "we have too many mocks". Do NOT trigger for: writing new tests from scratch (use the regular test-writing workflow) or testing framework/syntax questions — this skill reviews an existing suite for structural quality problems, not individual test authoring.
- ▌ Query 2 · hashgraph-onlineUse when the user wants to query, analyze, or explore data through the Honeydew semantic layer. Covers structured queries and multi-step deep analysis.
- ▌ Claude API 3 · hashgraph-onlineAnthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.
- ▌
- ▌ Git Commit 2 · hashgraph-online bundle准备并执行高质量 Git 提交。当用户要求提交代码、帮忙 commit、生成提交信息、拆分原子提交,或说 commit this / split commits / skip verify 时触发。先读仓库规范,按真实 diff 和暂存状态生成 Conventional Commit;emoji 默认关闭,仅 `--emoji` 时放在冒号后。不适用于创建 PR/MR(用 git-merge-request)或只推送。
- ▌ Postmortem 2 · hashgraph-online bundleExplain why a change, incident or session went as it did, separating proven causes from coincidence. Use when: asked for a postmortem, retro or root-cause write-up.
- ▌ Verify 2 · hashgraph-onlinePre-merge verification gate. Build, test, and lint must all pass before marking done or shipping.
- ▌ Brooks Debt 2 · hashgraph-online bundleTech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refactoring roadmap — drawing on twelve classic engineering books. Triggers when: user asks about tech debt, refactoring priorities, what to clean up first, or asks "why is this so hard to change?", "what should we fix first?", or "how do I justify refactoring to management?". Do NOT trigger for: server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime — "health" in those contexts is infrastructure, not code quality. Also not for single-function refactoring questions.
- ▌ Laravel Tdd 6 · hashgraph-onlineTest-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.
- ▌ Context 2 · hashgraph-onlineWorking-state snapshot guidance. Restates task/files/decisions in one block so state survives context compaction. Compaction timing is the host's job.
- ▌ API Contract 2 · hashgraph-online bundle统一接口协议、请求响应、错误码、兼容性与上下游协作约束。 当架构师、前后端开发或 QA 需要锁定 API 合同时使用。
- ▌ Tdd Workflow 10 · hashgraph-online bundleUse this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
- ▌ UX Design 2 · hashgraph-onlineUse when the user asks for UX, product flow, user journey, wireframes, usability, conversion, onboarding, checkout, signup, navigation, forms, state design, dashboard workflows, command palettes, settings, permissions, long-running task progress, admin/internal tools, activation, retention, or making an app easier to use over time. Designs and audits user experience flows, information architecture, content hierarchy, forms, onboarding, dashboards, settings, empty/loading/error/permission/success states, recovery paths, and repeated-use product ergonomics before visual polish. Pair with platform UI skills after the UX flow is clear.
- ▌ Audit 3 · hashgraph-onlineAudit phase. Parallel review: code quality + security + tests. Semantic dedup of cross-mode findings. Outputs PASS/WARN/FAIL per dimension. Validates spec coverage.
- ▌ Brooks Review 2 · hashgraph-online bundlePR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on twelve classic engineering books. Triggers when: user asks to review code, check a PR, shares a diff or pastes code asking "does this look right?" / "any issues here?" / "ready to merge?", or asks for feedback on a function, class, or file. Also triggers when user mentions: code smells / refactoring / clean architecture / DDD / SOLID principles / Hyrum's Law / deep modules / tactical programming / conceptual integrity / Brooks's Law / Mythical Man-Month / second system effect. Do NOT trigger for: questions about how to write code from scratch, language syntax questions, or framework/tool questions where no existing code is shared.
- ▌ Code Reviewer 3 · hashgraph-online bundleReview completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.
- ▌ Bootstrap 2 · hashgraph-online bundleUse this skill when scaffolding the minimum repository structure required by session-orchestrator. Invoked automatically by the Bootstrap Gate when CLAUDE.md, Session Config, or bootstrap.lock is missing. Also available as /bootstrap for manual invocation. Three intensity tiers: fast (demos/spikes), standard (MVPs), deep (production/team).
- ▌ Implement 5 · hashgraph-online bundleMake the code change a ticket or bug report asks for, then prove it with the repo's own checks. Use when: told to fix, change or build something, such as "fix this bug".
- ▌ Codebase Recon 2 · hashgraph-onlineUse when entering an unfamiliar codebase, onboarding to a new project, or wanting to assess codebase health before reading code — analyzes git history to reveal hotspots, risk areas, team structure, and development momentum
- ▌ Python Patterns 6 · hashgraph-onlinePythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
- ▌ Audit 4 · hashgraph-onlineAudit phase. Parallel review: code quality + security + tests. Semantic dedup of cross-mode findings. Outputs PASS/WARN/FAIL per dimension. Validates spec coverage.
- ▌ Anti UI Slop 3 · hashgraph-online bundleStop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use when designing, implementing, redesigning, critiquing, or pre-ship reviewing a web or iOS interface in Codex, Claude Code, Cursor, Copilot, or another coding agent. Trigger with "anti-ui-slop", "stop UI slop", "ground this UI in real screens", or "run the UI finish gate".
- ▌ Documentation Information Architecture · hashgraph-online bundleAudit, organize, and redesign developer documentation information architecture, including content inventory, navigation, landing pages, sequences, hierarchies, webs, breadcrumbs, sidebars, metadata, redirects, migration, platform/tool selection, and maintainable IA decisions. Use when restructuring docs sites, improving findability, planning doc migration, evaluating docs tooling, or organizing large documentation sets.
- ▌ Prototyping Concept Throwaway Evolutionary · hashgraph-online bundleUse this skill when picking which kind of prototype to build for the question at hand — concept (exploratory), throwaway (testing one specific aspect), or evolutionary (incremental toward final). Trigger when planning a research method, when scoping a technical spike, or when deciding whether an MVP should evolve or be thrown away. Sub-aspect of `prototyping`; read that first.
- ▌ Progressive Disclosure Defaults And Tucking · hashgraph-online bundleUse this skill when deciding *what to surface* and *what to tuck* — the editorial choices behind progressive disclosure. Trigger when laying out a settings page, picking which form fields to show by default, deciding whether a section starts collapsed or open, or arguing about whether a feature deserves primary chrome or belongs in "Advanced." Sub-aspect of `progressive-disclosure`; read that first.
- ▌ Progressive Disclosure Disclosure Affordances · hashgraph-online bundleUse this skill when picking the *mechanism* for revealing tucked content — accordion vs. modal vs. tab vs. separate page vs. tooltip. Trigger when designing the UI for "More options," picking between an inline accordion and a side sheet, deciding whether a wizard step should be a modal or a separate page, or reviewing whether existing disclosure affordances are doing their job. Sub-aspect of `progressive-disclosure`; read that first.
- ▌ Learn 3 · hashgraph-onlineLog a marketing learning to the brand intelligence graph with confidence, deduplicated. "save this insight"
- ▌ Caveman 3 · hashgraph-onlineUltra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested. Integrated into Cavekit: enabled by default for build, inspect, and subagent phases via caveman_mode config. See scripts/bp-config.sh for caveman_mode and caveman_phases.
- ▌ Standup 2 · hashgraph-onlineQuick project status report synthesized from state files, artifacts, and git activity. No agent dispatch (<2s).
- ▌ Langfuse 2 · hashgraph-online bundleInvestigate AI traces, observations, exceptions, latency, sessions, prompts, datasets, annotation queues, and scores through Langfuse MCP. Use when the request names Langfuse or asks to diagnose recorded AI behavior.
- ▌ Discover 2 · hashgraph-onlineTrigger: vague/unfocused request or solution-without-problem. Also invoked via /discover command. Reframes goal before acting.
- ▌ Graphify 2 · hashgraph-online bundle将 Graphify 作为可选知识图谱能力接入,用于 brownfield 结构扫描、依赖路径分析与架构问答。 不替代 `/team-*` 主链;输出统一回落到 handoff 与 artifacts 证据。
- ▌ Premortem 2 · hashgraph-online bundleFind how a rollout plan could fail before committing to it. Use when: asked what could go wrong or to poke holes in a plan.
- ▌ Apple Design 2 · hashgraph-onlineUse when the user asks for SwiftUI, UIKit, AppKit, iOS, iPadOS, macOS, watchOS, visionOS, Liquid Glass, HIG, SF Symbols, App Store deliverables, Apple settings/forms, branded Apple apps, React Native iOS, Flutter Cupertino, or Electron/Tauri macOS shells. Builds Apple-platform apps across system-like SwiftUI, branded SwiftUI, React Native, Flutter Cupertino, and desktop web shells while preserving UX decisions, native idiom, desktop archetype, originality seed, state coverage, Dynamic Type, accessibility, and HIG/Liquid Glass rules. ALWAYS ask which track first. SKIP when the target is only Android, Windows, or web-in-browser.
- ▌ Create Skill 2 · hashgraph-onlineUse when the user wants to persist a preference, skill, or knowledge. Use when it would aid future val development to store a memory of how best to build something.
- ▌ Skill Router 2 · hashgraph-online bundleUse when the user explicitly asks to diagnose or improve Codex skill/plugin routing, determine which skill or plugin should handle a request, refresh or check a skill registry, investigate why a skill/plugin did not trigger, or review skill descriptions for trigger quality. Do not use for ordinary task execution when a concrete domain skill clearly applies, unless routing is ambiguous or the user asks for routing.
- ▌ Skill Builder 2 · hashgraph-online bundleCreate, repair, audit or consolidate agent skills (SKILL.md packages). Use when: writing or fixing a skill, its description or structure. Not for one-off lessons; use Memory.
- ▌ Cohort Analysis 2 · hashgraph-onlineRun cohort analysis: retention matrix and LTV by cohort. Churn scoring → churn-risk. "build a retention matrix"
- ▌ Project Discovery 2 · hashgraph-onlineИспользуй только внутри активного Codex Project Autopilot-проекта, когда пользователь уже запустил автопилот или в workspace есть .codex-agent в фазе discovery/planning.
- ▌ Onboard 6 · hashgraph-onlineUse when taking over an existing codebase that has no living document. Produces a factual record of what already exists.
- ▌ Cro 2 · hashgraph-online bundlePlan CRO for pages, forms and checkout with ICE-ranked fixes. One page → landing-page-audit. "reduce cart abandonment"
- ▌ Odw 2 · hashgraph-onlineDynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for a "workflow", says "ultracode", or hands you a task spanning many files/items that benefits from parallel agents.
- ▌ Feedback Loop Positive Vs Negative · hashgraph-online bundleUse this skill when designing system architecture or product mechanics that involve feedback loops at a higher level than UI state — recommendation engines, gamification, growth mechanics, engagement systems, or any system where one user action affects subsequent actions in compounding or stabilizing ways. Trigger when designing growth loops, retention features, or system dynamics; when reviewing a feature for unintended consequences; when discussing engagement vs. wellbeing tradeoffs. Sub-aspect of `feedback-loop`; read that first.
- ▌ Mental Model System Vs Interaction · hashgraph-online bundleUse this skill when distinguishing the two mental-model types — system models (how the user thinks the system works) and interaction models (how the user thinks they should use it). Trigger when designing onboarding (which model to teach), reviewing user confusion (which model is wrong), or building documentation (which model to explain). Sub-aspect of `mental-model`; read that first.
- ▌ Wayfinding Breadcrumbs And Context · hashgraph-online bundleUse this skill when designing the orientation chrome that tells users where they are — breadcrumbs, current-page indicators, page titles, header context, "you are here" markers, parent-link affordances. Trigger when designing a multi-level IA, when users complain "I lost track of where I was," when reviewing whether to add or remove a breadcrumb, or when picking between navigation patterns for hierarchical content. Sub-aspect of `wayfinding`; read that first.
- ▌ Game Geometry Representation Choice · hashgraph-onlineChoose the right geometric representation for game systems before implementing rendering, collision, procedural generation, editing, or conversion code. Use when deciding between meshes, SDFs, voxels, splines, parametric surfaces, fields, or hybrid geometry workflows for games.
- ▌ Reviewing Gitlab Mr Comments · hashgraph-online bundleUse when reviewing GitLab merge request comments via glab in the current repo, including extracting line ranges and code snippets from inline discussions, then deciding next actions with a checklist or plan before execution
- ▌ Rust Crate Publishing Readiness · hashgraph-online bundlePrepare Rust crates for publishing with Cargo metadata, versioning, README and license checks, package dry-runs, feature verification, docs.rs readiness, examples, changelog notes, and secret-safe release gates. Use before cargo publish, crate release PRs, or sharing a reusable Rust library.
- ▌ Recognition Recents And Suggestions · hashgraph-online bundleUse this skill when designing surfaces that accelerate repeat tasks through recents, frequently-used items, and contextual suggestions. Trigger when designing pickers used repeatedly, command palettes, navigation that should adapt to user behavior, or any surface where a returning user shouldn't have to retype their frequent destinations. Sub-aspect of `recognition-over-recall`; read that first.
- ▌ Skill Native Escalation Routing · hashgraph-online bundleUse when choosing native or multi-LLM handling for init, review, or security requests
- ▌ Linkedin Article Newsletter Writing · hashgraph-online bundlePlan, draft, repurpose, and audit LinkedIn articles and newsletters that demonstrate expertise and support a professional content strategy. Use when writing long-form LinkedIn articles, newsletter editions, article teasers, follow-me articles, issue plans, or post-to-newsletter repurposing.
- ▌ Developer Docs Audience Research · hashgraph-online bundleResearch developer documentation audiences by mapping user goals, learning objectives, business goals, developer traits, user questions, personas, user stories, journey maps, and friction logs. Use when planning docs for APIs, SDKs, platforms, CLIs, developer tools, onboarding guides, SaaS docs, or support-heavy docs before writing or restructuring content.
- ▌ Documentation Platform Selection · hashgraph-online bundleEvaluate documentation platforms and authoring tools by requirements, workflow fit, migration risk, content model, search, integrations, portability, support burden, and cost. Use when choosing docs-as-code, CMS, wiki, DITA, API reference, static-site, help-center, or custom docs tooling, planning a migration, or deciding whether tooling will fix documentation problems.
- ▌ Obsidian CLI Bases And Bookmarks · hashgraph-online bundleUse this skill when the user needs official desktop Obsidian CLI Bases or Bookmarks workflows, including base discovery, view/query operations, base item creation, and bookmark management. Keep this skill separate from general note CRUD, runtime admin, Sync/Publish, and devtools diagnostics.
- ▌ Interpreting Mod Author Instructions · hashgraph-onlineUse when deciding how to correctly download/install a Bethesda mod per the author's instructions — triggers "how do I install", "FOMOD choices", "which file to download", "author说明", "install instructions", "which variant", "按作者说明安装", "这个mod怎么装". NOT for deciding whether to include the mod (use evaluating-bgs-mods), load order editing (writing-bgs-load-order), record conflicts (xedit-conflict-audit), archive operations (using-bgs-archive), Papyrus work (using-bgs-papyrus), or translation/export tasks (using-bgs-translator).
- ▌ Developer Docs Technical Research · hashgraph-online bundleResearch product and feature facts for developer documentation by mapping source-of-truth owners, validating behavior hands-on, interviewing SMEs, and turning uncertainty into doc-ready notes. Use when feature specs are incomplete, implementation details need user-facing meaning, SMEs disagree, or docs require evidence before planning, drafting, release notes, API docs, tutorials, scenarios, or troubleshooting content.
- ▌ Wayfinding Physical Spatial Metaphors · hashgraph-online bundleUse this skill when deciding whether (and how) to borrow physical-world wayfinding metaphors for software — rooms, doors, paths, maps, landmarks. Trigger when designing app shells with multiple "spaces," when picking metaphors for navigation (workspace, channel, board, project), when reviewing skeuomorphic vs. flat navigation choices, or when the user mentions "feels like a maze" or "where's the front door of this app." Sub-aspect of `wayfinding`; read that first.
- ▌ Technical Manuscript Verification · hashgraph-online bundleVerify technical nonfiction manuscripts for runnable accuracy, including commands, configuration, code snippets, links, version drift, screenshots, prerequisites, security warnings, expected outputs, and reproducibility. Use when auditing self-hosting, DevOps, programming, infrastructure, data, security, or software tutorial drafts before beta reading, publication, or release.
- ▌ Form Follows Function Success Criteria · hashgraph-online bundleUse this skill when the team is in a form-vs-function debate and needs to step back to define what "success" actually means for the design. Trigger when stakeholders disagree about visual treatment, when a design feels off and no one can articulate why, or when reviewing a design against an unclear brief. Sub-aspect of `form-follows-function`; read that first.
- ▌ Forgiveness Confirmation And Prevention · hashgraph-online bundleUse this skill when the user must commit to an irreversible or high-stakes action and reversibility isn't enough — confirmation dialogs, type-to-confirm patterns, password re-entry, two-step authentication for destructive actions, and structural prevention that makes the wrong action impossible. Trigger when designing destructive flows for genuinely-irreversible commitments, when reviewing confirmation fatigue, or when picking between a single confirm dialog and a multi-step verification. Sub-aspect of `forgiveness`; read that first.
- ▌ Obsidian CLI Workspace And Navigation · hashgraph-online bundleUse this skill when the user needs official desktop Obsidian CLI workspace, vault, tab, navigation, and utility operations, including workspace save/load/delete, tab and recent-file handling, vault info/listing, random/unique note navigation helpers, web viewer, and wordcount. Keep this skill separate from note CRUD/tasks/properties/history, runtime admin, devtools diagnostics, and Sync/Publish operations.
- ▌ Launchfast Full Research Loop · hashgraph-onlineEnd-to-end Codex-native Amazon FBA research workflow using LaunchFast MCP. Use when the user wants a single report covering product research, IP risk, supplier sourcing, and PPC keyword intelligence. Requires `research_products`, `ip_check_manage`, `supplier_research`, and `amazon_keyword_research`.
- ▌ Experimentation Culture Rollout · hashgraph-online bundleRoll out an experimentation-friendly culture across product, engineering, data, and leadership teams. Use when introducing A/B testing to an organization, overcoming resistance to experiments, shifting teams away from launch-by-opinion, increasing experiment demand, defining rollout tactics, or creating an experimentation adoption plan.
- ▌ Experiment Sensitivity Optimization · hashgraph-online bundleImprove experiment sensitivity and reduce traffic or duration requirements. Use when choosing sensitive metrics, working with minimum detectable effect, reducing variants, applying capping metrics, CUPED, variance reduction, or deciding how to get trustworthy A/B test signal with fewer users.
- ▌ Finishing A Development Branch Lite · hashgraph-onlineUse when implementation is complete and you need to merge a worktree branch back into the original base branch with build/compile verification (no tests)
- ▌ Feedback Loop States And Latency · hashgraph-online bundleUse this skill when designing the visible states an interactive element passes through (idle / pending / success / error) and matching feedback timing to the user's perceptual thresholds. Trigger when designing button states, form-submit flows, file-upload progress, loading screens, or any interaction whose response time is variable. Sub-aspect of `feedback-loop`; read that first.
- ▌ Forgiveness Undo And Soft Delete · hashgraph-online bundleUse this skill when designing reversibility — undo systems, soft delete, archive-with-recovery, version history, "Undo Send" patterns, and any mechanism that lets a user step back from an action they regret. Trigger when designing destructive actions you want to be safe rather than friction-heavy, when picking between confirmation dialogs and undo toasts, when defining recovery windows, or when planning version-history features. Sub-aspect of `forgiveness`; read that first.
- ▌ Recognition Pickers And Palettes · hashgraph-online bundleUse this skill when designing pickers, dropdowns, comboboxes, autocompletes, command palettes, or any UI that lets the user select from a known set. Trigger when picking between a free-text field and a select; when designing a command palette; when reviewing why users keep typing wrong values into autocomplete inputs. Sub-aspect of `recognition-over-recall`; read that first.
- ▌ Local Sponsorship Link Building · hashgraph-online bundlePlan, prospect, evaluate, fulfill, and measure local sponsorship campaigns that build local visibility, relationships, and links through events, nonprofits, community organizations, and local publishers. Use when finding local sponsorship link opportunities, evaluating sponsorship packages, building local links through nonprofits or events, measuring sponsorship ROI, or using local relationships for SEO.
- ▌ Scaled Link Outreach Operations · hashgraph-online bundleOperate scaled link outreach with segmentation, templates, personalization variables, pilot batches, suppression lists, deliverability checks, reply diagnostics, compliance review, and campaign reporting. Use when planning bulk outreach, reviewing email operations, scaling a proven offer, or debugging low reply rates.
- ▌ Autonomous Project Orchestrator · hashgraph-onlineИспользуй только когда пользователь явно просит запустить Codex Project Autopilot, продолжить проект из .codex-agent или в текущем workspace уже есть активный .codex-agent.
- ▌ Eighty Twenty Time Team Leverage · hashgraph-onlineApply 80/20 leverage to time, talent, assistants, outsourcing, hiring, salespeople, and low-value work. Use when deciding what to delegate, outsource, stop doing, hire for, trial, or remove so high-value people spend more time on their strongest work.
- ▌ Developer Docs Editing Review · hashgraph-online bundleEdit and review developer documentation for technical accuracy, completeness, structure, clarity, brevity, peer feedback, technical review, technical verification, QA procedure testing, and feedback integration. Use when reviewing, editing, refactoring, or preparing developer docs for release, especially docs with procedures, examples, prerequisites, or high-risk technical claims.
- ▌ Documentation Quality Metrics · hashgraph-online bundleAudit and measure developer documentation quality using functional quality, structural quality, accessibility, purpose, findability, accuracy, completeness, clarity, concision, consistency, analytics, user goals, doc goals, and metric plans. Use when evaluating docs, designing documentation metrics, selecting dashboards, or linking docs work to user and business outcomes.