hashgraph-online
- 1.5k skills
- 0 followers
- 1.6k repo stars
- 2 days ago last updated
- ▌ Vidseeds Projects · hashgraph-onlineUse for VidSeeds MCP project workflows - create a project from YouTube, list/get/snapshot, regenerate metadata (sync or async), translate metadata, apply thumbnails, and update per-platform config before publish.
- ▌ Skill Doc Delivery · hashgraph-online bundleConvert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables
- ▌ Brownfield Adoption · hashgraph-onlineStep-by-step process for adopting Cavekit on an existing codebase. Covers the 6-step brownfield process, bootstrap prompt design, spec validation against existing behavior, and the decision between brownfield adoption vs deliberate rewrite. Trigger phrases: "brownfield", "existing codebase", "add Cavekit to existing project", "adopt Cavekit", "layer kits on code", "retrofit kits"
- ▌ Graymatter Memory · hashgraph-online bundleRecall and maintain GrayMatter durable memory. When the user chooses primary memory, recall invariants and context before new tasks while connected and active; automatically preserve useful durable facts when authorized. Handle explicit remember, correct, or forget requests in either mode.
- ▌ Octopus Research · hashgraph-online bundleThorough research across multiple sources — use for complex topics needing broad synthesis
- ▌ Language Audit · hashgraph-onlineAudit all language versions of a site for parity and quality. Tags only → hreflang-check. "is the German site missing pages"
- ▌ Ab Test Results Readout · hashgraph-online bundleAnalyze and communicate A/B test results with metric readouts, subgroup analysis, data-quality checks, ad hoc investigation, visualization, and launch recommendations. Use when interpreting experiment results, preparing an A/B test report, explaining flat or mixed results, checking guardrails, segmenting test/control data, or turning experiment data into a product decision.
- ▌
- ▌ Django Targeted Mocking · hashgraph-online bundleMock Django test boundaries safely with override_settings, pytest settings, autospecced unittest.mock objects, output/input capture, requests-mock, VCR.py, outbound HTTP blocking, and time-freezing tools. Use when tests need to replace settings, HTTP calls, time, command output, stdin, or external services without broad fragile MagicMock patches.
- ▌ Unknown Coverage Review · hashgraph-online bundle完成した差分・PR・検証証拠に残る Unknown(未確認の前提・調査されていない影響・ 不足している証拠)を横断合成する evidence-sufficiency のメタ観点。個別 defect の 検出は既存 skill へ委譲し、本 skill は「そのリスク種別を調査した証拠が残っているか」 の meta 評価のみを行う。通常は finding verification 後の generic 合成ステップとして、 明示的 Security Audit では SecurityAuditCoverage 専用 profile として report-only で実行する。 残存 Unknown は既存 Unknown Coverage 構造へ出力し、新しい語彙・schema は作らない。
- ▌ Linkedin Humanizer · hashgraph-online bundleRemove AI tells from LinkedIn posts/comments: 2026 vocabulary density, reveal bridges, staccato fragments, stacked triads, performed sincerity. Tiered rewriter plus `--mode audit` LinkedIn post auditor and `--mode profile` voice builder. Not for drafting from scratch (use linkedin-post-writer) or beating AI detectors. Keywords: humanize, de-AI, post audit, post auditor, audit before posting.
- ▌ Agent Debug Fixer · hashgraph-online bundle中文调试修复技能。用于报错、测试失败、页面异常、功能不符合预期、需要定位根因并做最小修复时。触发语包括"进入调试模式""帮我修问题""报错了""测试失败""页面坏了""找根因"。
- ▌ Be Serious Review · hashgraph-online bundleUse when the user asks to review, audit, score, repair, or rewrite prose against the be-serious scholarly textbook register; when checking for slang, sycophancy, emoji, casual tone, marketing language, AI tics, or Chinese internet vernacular; or when drafting a formal alternative.
- ▌ Evolution Network · hashgraph-onlineCross-agent gene sharing protocol for exchanging validated evolution patterns between Claude sessions with trust downgrades and local revalidation.
- ▌
- ▌ International Vin · hashgraph-onlineDecode an international (non-US) VIN using the CarsXE API. Use this when a user provides a VIN from a European, Asian, or other non-US vehicle and wants to decode it.
- ▌ Krypton Execution · hashgraph-online bundleUse when executing an approved Krypton plan, GOAL.md, or implementation plan that already defines intent, ownership, contract, cutover, task boundaries, and acceptance evidence. Use for main-agent execution with explorer, plan-reviewer, reviewer, maintainer, or verifier gates.
- ▌ Model Exploration · hashgraph-onlineUse when exploring Honeydew semantic layer, discovering entities/fields, setting up workspace and branch context, or querying data. For creating metrics use metric-creation skill. For creating attributes use attribute-creation skill.
- ▌ Django Outside In Tdd · hashgraph-online bundleDrive Django features with outside-in and double-loop TDD: user story, Selenium or functional test, focused Django unit/integration tests, minimal implementation, and refactor. Use when starting or changing Django behavior with tests-first workflow, red/green/refactor, working-state-to-working-state refactors, or deciding which layer should own the next test.
- ▌ Write Executable Plan · hashgraph-online bundleUse when you have a PRD or design spec and need a bite-sized, executable implementation plan that any agent can follow without re-deriving structure. Produces `docs/plans/YYYY-MM-DD-<feature>.md` with per-task Files block, complete code per step (no placeholders), and exact verification commands. Rejects "TBD", "TODO", "add error handling", "similar to Task N".
- ▌ Dev Design Context · hashgraph-online bundleEstablish or update persistent product and visual design guidance in .design-context.md. Use for initial design setup, a deliberate design-direction reset, or explicit 设计上下文 requests. Discover existing users, components, tokens, assets, and constraints before asking about material gaps. Does not implement UI; ordinary UI work does not require repeating this setup.
- ▌ Expectation Effect · hashgraph-online bundleApply the Expectation Effect — the principle that prior expectations measurably change a person's perception of a product or experience. Use when shaping the framing of new features, designing onboarding, choosing visual cues that signal premium vs. budget, or diagnosing why two functionally identical features feel different to users. Expectations are set by visual cues (premium materials, polished typography), language (precise, confident copy), social proof, price, and prior brand exposure. Setting expectations too high creates disappointment; too low and the product reads as mediocre. The skill is calibrating what to promise.
- ▌ Figure Ground Cues · hashgraph-online bundleApply specific visual cues to control figure-ground perception — shadow, elevation, scale, contrast, saturation, opacity, and texture. Use when designing layered interfaces, focus states, hover treatments, or any context where one element should clearly stand forward against others. Each cue contributes a portion of the figure-ground signal; combining cues strengthens the effect. The skill is selecting and calibrating cues for the desired level of separation.
- ▌ Gestalt Similarity · hashgraph-online bundleApply the Gestalt principle of Similarity — elements that share visual attributes (color, shape, size, orientation) are perceived as belonging together, regardless of their physical proximity. Use when grouping related items in a list, status indicators, dashboard cards, navigation, or any context where you want the user to perceive certain items as a set. Similarity is one of the strongest grouping cues; it works even when proximity says otherwise. Color is the strongest similarity cue, then size, then shape; orientation is weakest.
- ▌ Hicks Law Defaults · hashgraph-online bundleUse this skill when the question is what to *pre-select* in a list of options — radio groups, dropdowns, configuration UIs, plan pickers, sign-up flows, settings. A strong default is the highest-leverage Hick's Law mitigation: most users accept the default, paying almost no decision cost. Trigger when picking what's selected on first load, when stakeholders argue "shouldn't we let the user choose?", when designing wizards or onboarding, or when a UI has many options but most users want the same one. Sub-aspect of `hicks-law`; read that first if you haven't already.
- ▌ Htmx Interactivity · hashgraph-online bundleCoordinate htmx with lightweight browser-side interactivity. Use when adding Alpine.js, _hyperscript, local UI state, custom events, dialogs, transitions, keyboard behavior, or browser-only state around htmx swaps in a server-rendered app.
- ▌ Iconic Resemblance · hashgraph-online bundleApply iconic resemblance — designing or choosing icons that visually look like what they represent. Use when picking icons for actions or objects with strong visual referents (camera, clock, lock, calendar), evaluating whether a custom icon is communicating, or testing whether your icon set actually conveys meaning to your audience. Resemblance is the strongest form of icon recognition because it requires no prior learning; it fails when the function has no visual referent or when the audience doesn't recognize the object being depicted.
- ▌ Interaction Router · hashgraph-online bundleUse this skill whenever a design task involves what users *can do* and what happens when they do it — affordances, feedback, errors, undo, confirmation, target sizing, keyboard handling, modal vs. non-modal decisions, destructive actions, validation. Trigger when the user mentions buttons, forms, validation, error states, loading states, drag-and-drop, undo, confirmation dialogs, keyboard shortcuts, target sizes, "users keep deleting things," misclicks, or "should this be a popover or a dialog." Framework-agnostic. Routes the model to the right interaction principle in this plugin.
- ▌ Javascript UI Math · hashgraph-online bundleUse JavaScript number math safely for front-end UI behavior, including expressions, precedence, coercion, NaN, Infinity, floating-point precision, BigInt limits, modulo wrapping, rounding, random values, and repeatable UI randomness. Use when building sliders, carousels, counters, animation values, randomized UI, financial-ish display values, or debugging numeric edge cases in browser JavaScript.
- ▌ Make Product Viral · hashgraph-online bundleMake a product, landing page, pricing page, launch page, free tool, or social preview easier to understand, buy, remember, and share using Marc Lou-inspired viral product patterns.
- ▌ Mimicry Behavioral · hashgraph-online bundleApply behavioral mimicry — making an interface element behave like a familiar physical object so the user's physical-world intuitions transfer to the digital interaction. Use when designing gestures, animations, transitions, drag-and-drop, scroll behaviors, or any interaction where physical-world analogies could clarify the experience. Behavioral mimicry is more durable than visual skeuomorphism — physics-mimicking behaviors age well — but it requires deliberate calibration: too much physical fidelity slows the interaction down without communicating anything new.
- ▌ Skill Copilot Provider · hashgraph-online bundleGitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode
- ▌ Skill Decision Support · hashgraph-online bundlePresent options with trade-offs for informed decision-making — use when choosing between approaches
- ▌ Attribution Model · hashgraph-onlineDesign an attribution model and credit rules. Real path data → attribution-report. "set up multi-touch attribution"
- ▌ B2b Timing Engine · hashgraph-onlineDesign recurring B2B buyer-presence systems that keep a company remembered until pain becomes urgent, using time-based visibility cadence instead of unreliable intent signals or linear funnel assumptions. Use when buyers know the company but deals stall, follow-up is inconsistent, the team waits for triggers, expands markets too early, or wants a 4-6 week account visibility rhythm.
- ▌ Competitor Alerts · hashgraph-onlineConfigure competitor alerts: change thresholds per competitor, urgency routing, digests. "set up competitor alerts"
- ▌ Content Repurpose · hashgraph-onlineRepurpose one content piece into 10+ channel formats with drafts and a calendar. "repurpose this blog post"
- ▌ Credential Switch · hashgraph-onlineSwitch the active credential profile to another client, validating keys first, approval-gated. "activate Acme's API keys"
- ▌ Emerging Channels · hashgraph-online bundleEvaluate emerging channels such as voice or social commerce with pilot plans. "should we open a TikTok Shop"
- ▌ Import Guidelines · hashgraph-onlineImport brand guidelines into enforceable rules: voice, banned words, styles. "here's our brand voice guide"
- ▌ Page SEO Analysis · hashgraph-onlineAnalyze the SEO of one URL, scored /80 with paste-ready fixes. "analyze the SEO of this page"
- ▌ Panews Web Viewer · hashgraph-online bundleRead public PANews website pages as Markdown. Use for homepage, article-page, and column-page reads.
- ▌ Translate Content · hashgraph-onlineTranslate marketing content using the brand glossary and do-not-translate terms, with quality scoring. "translate this into Japanese"
- ▌ Agent Deck Setup · hashgraph-onlineUse when setting up Agent Deck, the MCP is disconnected, or the local daemon is down. Guides install/start with read-only checks; the user runs install commands.
- ▌ Caveman Internal · hashgraph-online bundleInternal token-compression protocol for Cavekit agent artifacts — handoff notes, artifact summaries, context bundles, review notes, status lines. NOT the user-facing /caveman skill; that one compresses assistant replies to the user. This skill compresses machine-to-machine prose so the next agent in the loop reads fewer tokens. Three intensities (lite / full / ultra) with automatic selection based on budget pressure. Used by task-builder, builder, inspector, verifier, convergence-monitor, and the stop-hook status block.
- ▌ Codex Auth Setup · hashgraph-onlineInstall or refresh codex-multi-auth for the official Codex CLI, run first login, and verify account health and routing.
- ▌ Deepscan Monitor · hashgraph-onlineRun and monitor PapersFlow DeepScan jobs. Use when the user wants long-running research progress, intermediate findings, final reports, or plotting from a completed run.
- ▌ Ecosystem Health · hashgraph-onlineMonitor health across configured service endpoints, CI pipelines, and critical issues. Automatically invoked during session-start when ecosystem-health is enabled in Session Config.
- ▌ Explain Decision · hashgraph-onlineFetch the full reasoning behind an AxonFlow policy decision — matched policies, risk level, override availability, recent hit count
- ▌ Frappe Fullstack · hashgraph-onlineEnd-to-end Frappe and ERPNext implementation guidance spanning backend Python, backend JavaScript surfaces, Vue or React frontends, customizations, and bench-aware delivery. Use when the task crosses multiple Frappe layers.
- ▌ Lark Skill Maker · hashgraph-online创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill(包装原子 API 或编排多步流程)时使用。
- ▌ Maestro Frontier · hashgraph-onlineMaestro Frontier local multi-CLI fusion engine - compose or choose a read-only model panel, inspect the catalog, arm, disarm, or run it
- ▌ Maestro Settings · hashgraph-onlineView and change Maestro toggles (terse, frontier, context-bar, discipline, verify) via the settings CLI
- ▌ Project Map Find · hashgraph-online bundleUse when locating existing project features, flows, pages, modules, components, utilities, patterns, contracts, business concepts, or similar functionality before answering where something is or before building related functionality. Trigger for 项目里有没有做过, 在哪里, 类似功能, 已有功能, 复用, 不要重复造轮子, 项目里叫什么, 哪些文件, 找一下, existing feature, similar functionality, where is, reuse, avoid rebuilding, project concept, feature inventory, capability map, or implementation already exists. Do not use for pure styling, isolated bug fixes, code explanation, or tests unless the user asks for existing/related capability discovery.
- ▌ Xedit Automation · hashgraph-online bundleUse whenever the task involves inspecting, modifying, or building plugins for Bethesda games via the forked xEdit automation daemon. Loads first; routes to the right path (MCP intent tool, MCP atomic passthrough, or sub-agent delegation) and prevents the agent from bypassing the harness.
- ▌ Dataproduct Implement · hashgraph-onlineGiven an Entropy Data data product URL or id, fetch its data contracts (output port ODCS files written next to the SQL under models/output_ports/v<N>/, input port ODCS files cached next to their dbt source under models/input_ports/), translate the schema into dbt models, and ensure the project has the publishing layer (ODPS, OpenLineage, GitHub Actions). Trigger when the user asks to "implement the data product <url>", "build the dbt pipeline for this data product", or "scaffold dbt models from a data contract".
- ▌ Rust API Test Harness · hashgraph-online bundleUse when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test isolation, external HTTP mocks, or CI-ready cargo verification for Actix, Axum, Warp, Rocket, or similar Rust web frameworks.
- ▌ Rust Trait API Design · hashgraph-online bundleDesign and review Rust trait APIs, generic bounds, dispatch models, and conversion contracts for clear public interfaces. Use when designing, refactoring, or reviewing traits, generics, trait objects, associated types, impl Trait, From/TryFrom, AsRef, Borrow, or crate APIs.
- ▌ Hicks Law Pricing · hashgraph-online bundleUse this skill when designing pricing tables, plan pickers, tier selectors, or any conversion surface where the choice itself is the conversion event. Trigger when laying out 3-tier or 4-tier pricing, when arguing about whether to add a fourth plan, when designing the "Choose your plan" step of onboarding, or when fixing low conversion on a pricing page. Pricing pages are a special Hick's Law case: the decision is the entire purpose of the page, and decision fatigue equals lost revenue. Sub-aspect of `hicks-law`; read that first if you haven't already.
- ▌ Dataproduct Bootstrap · hashgraph-online bundleBootstrap a brand-new dbt data product from scratch — create dbt_project.yml, the Entropy Data model layout (input_ports, staging, intermediate, output_ports/v1), README with uv install instructions, .gitignore, and a profiles.yml.example for the chosen warehouse. After scaffolding, hands off to the entropy-data-sync skill to add the publishing layer (ODPS, ODCS, OpenLineage, GitHub Actions). Trigger when the user asks to start a new data product, scaffold a new dbt project, or "create a data product from scratch."
- ▌ Offloading Extraction · hashgraph-onlineUse when the user wants to extract a document via the cloud rather than the local kreuzberg CLI. Covers POST /v1/extract — JSON vs multipart bodies, URL crawls, options block, webhook attachment, and the async response shape.
- ▌ Dev Grill Docs · hashgraph-online bundleClarify feature requirements, pressure-test scope and domain terms, and produce a feature spec before implementation. Use for fuzzy requirements, PRD/spec requests, 需求对齐, 拷问需求, or 设计文档. Read existing evidence before asking focused questions. For concrete implementation planning use dev-plan; a generic "do not edit code" instruction alone does not trigger intake. Supports --quick, --deep, and --spec-only.
- ▌ Skill Doc Sync · hashgraph-online bundlePost-ship doc sync across project markdown. Use when: sync docs, update docs, document changes, release notes.
- ▌ B2b Reach Engineering · hashgraph-onlineBuild B2B reach systems that make a defined market aware of the company through named accounts, real buyers, controlled delivery channels, and first-touch saturation. Use when the right market may not know the company exists, outbound gets little signal, brand awareness is vague, the target market is too broad, or the team needs a concrete account list and reach plan.
- ▌ B2b Trust Engineering · hashgraph-onlineEngineer B2B buyer trust by reducing perceived risk, stacking relevant proof, simplifying next steps, and designing sales calls to confirm confidence rather than persuade from scratch. Use when qualified buyers take calls, request proposals, start trials, or show interest but then stall, ghost, choose safer incumbents, or hesitate because proof, certainty, process, or risk reversal is weak.
- ▌ Django DB Performance · hashgraph-online bundleDiagnose and improve slow Django database-backed endpoints with evidence-first profiling, query-plan review, index selection, ORM loading fixes, batching, database-side computation, materialized views, and pagination choices. Use when a Django view, API, job, report, queryset, or database query is slow and the right optimization path is not obvious.
- ▌ Autopilot Status · hashgraph-onlineShow autopilot status: health, auto-corrections, guardrails, escalations. "what did the autopilot change"
- ▌ Funnel Architect · hashgraph-online bundleDesign a funnel for the business model: stages, KPIs, journey. Existing data → funnel-audit. "design a funnel for our SaaS"
- ▌ Influencer Brief · hashgraph-onlineWrite an influencer campaign brief: creator criteria, pay, approvals, disclosure. "write a brief for our influencer campaign"
- ▌ Paid Advertising · hashgraph-online bundlePlan or audit paid ads with current platform rules and benchmarks: Google PMax/AI Max, Meta, retail. "should we use Performance Max"
- ▌ Redirect Manager · hashgraph-onlineCreate, audit and fix URL redirects on a connected CMS, approval-gated. "set up a 301 redirect"
- ▌ Search Knowledge · hashgraph-onlineSearch the brand's stored knowledge and memory, ranked with provenance. "what are our brand voice guidelines"
- ▌ Segment Audience · hashgraph-onlineBuild audience segments in CRM, email or ad platforms with consent checks, approval-gated. "create a segment of lapsed customers"
- ▌ Trust And Liking · hashgraph-online bundleUse when improving cold outreach, sales conversations, customer discovery, community moderation, referral asks, partnership messages, interviews, or relationship-based persuasion where similarity, compliments, familiarity, cooperation, association, or rapport may affect trust.
- ▌ Validate Profile · hashgraph-onlineValidate the brand profile is production-ready: fields, compliance, connectors. "is the brand setup correct"
- ▌ Peer Review Loop · hashgraph-onlinePeer Review Ralph Loop — combines Cavekit kits with a Ralph Loop and true cross-model peer review using Codex (OpenAI). Claude builds from specs; Codex reviews adversarially. Primary path: Codex CLI delegation via codex-review.sh (fast, no MCP overhead). Legacy fallback: Codex as MCP server when CLI delegation is unavailable. Covers setup, iteration patterns, convergence detection, and completion criteria. Triggers: "peer review loop", "ralph loop with codex", "cavekit ralph", "peer review build loop", "cross-model loop", "codex peer reviewer", "cavekit to ralph loop"
- ▌ Superloopy Clone · hashgraph-online bundleUse when the user asks for Superloopy clone or asks to clone, rebuild, reverse-engineer, replicate, or copy a website or page into a Superloopy-governed implementation. Triggers on "loopy clone", target URLs plus requests such as "clone this site", "rebuild this page", "make a copy of this website", "pixel-perfect clone", or "AI website clone". Requires browser automation and records component specs, assets, implementation, build output, and visual QA as Superloopy evidence.
- ▌ Docs Agile Integration · hashgraph-online bundleIntegrate documentation work with Agile product development by making docs visible in sprint planning, release trains, definitions of done, review timing, and retrospective improvement. Use when docs are missing from scrum boards, stories, acceptance criteria, release planning, or cross-team work, or when writers need a lightweight process for documentation inside Agile teams.
- ▌ Sop Library · hashgraph-onlineManage the agency SOP library: templates, assignments, compliance. "create an SOP for blog publishing"
- ▌ Zotero Research · hashgraph-onlineUse when the user wants to search, browse, read, summarize, cite, annotate, or manage their Zotero library through Zotero MCP. Triggers include Zotero, 文献库, 查文献, 读论文, PDF 注释, citation key, BibTeX, 标签, 集合, and adding or updating Zotero items.
- ▌ Htmx Security · hashgraph-online bundleReview and harden security for htmx and server-driven web apps. Use when handling user-supplied HTML, escaping or sanitizing fragments, adding CSP, evaluating XSS risk, configuring CSRF or cookies, loading htmx from a CDN, using SRI hashes, accepting hx-* attributes from content, or reviewing htmx request headers and history caching.
- ▌ Martech Audit · hashgraph-onlineAudit the martech stack for gaps, overlaps and wasted spend, with a consolidation plan. "audit our martech stack"
- ▌ Vda 6 3 Audit · hashgraph-online bundleVDA 6.3 Process Audit — conduct or prepare for a process audit using the VDA 6.3 methodology, evaluate process elements P1–P7, calculate degree of fulfillment, classify findings, and generate an audit report. Use when a customer requests a VDA 6.3 audit, when auditing a supplier's manufacturing process, or when preparing for a VDA process audit visit. Covers VDA 6.3 4th edition (2023).
- ▌ Simulink Baseline Test · hashgraph-onlineCreate a MATLAB baseline regression test class for a Simulink model. Use when asked to create a baseline test, golden-reference test, or regression test for a Simulink model.
- ▌ 8d Report Writing · hashgraph-online bundleSubmit an 8D to a customer, format a Ford 8D report, BMW G8D, VW QMSS, or OEM complaint response for formal submission. Covers OEM-specific format requirements, evidence standards, and discipline-by-discipline writing rules for D0–D8. Use when preparing an 8D report for Ford, BMW, VW/Audi, Stellantis, or any customer requiring formal 8D closure.
- ▌ Blueprint Writing · hashgraph-onlineHow to write Blueprint-quality blueprints that AI agents can consume effectively. Covers implementation-agnostic blueprint design, testable acceptance criteria, hierarchical structure, cross-referencing, blueprint templates, greenfield and rewrite patterns, blueprint compaction, and gap analysis. Trigger phrases: "write blueprints", "create blueprints", "blueprint this out", "define requirements for agents", "how to write blueprints for AI"
- ▌ Counter Narrative · hashgraph-onlineBuild a counter-narrative playbook for a competitor's rebrand, category claim or attack. "respond to their attack campaign"
- ▌ Narrative Tracker · hashgraph-onlineTrack the brand narrative in AI engines against desired positioning, flag misstatements. "is AI misrepresenting our brand"
- ▌ Rg Budget Search · hashgraph-onlineIn large or many-file projects, prefer cxs over raw rg/grep to reduce context waste.
- ▌ Managing Cloud Usage · hashgraph-onlineUse when the user asks about quota, billing visibility, or processed-page counts. Covers GET /v1/usage — query params, response shape, when to report usage proactively to the user.
- ▌ Speculative Pipeline · hashgraph-onlineA pipeline execution strategy where downstream stages start before upstream stages finish, using staggered timing with configurable delays. The leader begins first, and followers start after a delay, building from whatever partial output exists. Combined with convergence loops, early follower output self-corrects as upstream artifacts solidify. Cuts total pipeline time dramatically -- a 3-stage pipeline that takes 12 hours sequentially can finish in roughly 7 hours with speculative-pipeline staggering. Triggers: "speculative-pipeline", "staggered pipeline", "parallel prompts with delay", "overlap pipeline stages", "faster pipeline".
- ▌ Versioning Documents · hashgraph-onlineUse when the user wants to retrieve a stored document and its extraction result, list a document's versions, or diff two versions. Covers GET /v1/documents/{id}, GET /v1/documents/{id}/versions, and the sync-with-async-fallback diff at GET /v1/documents/{id}/diff plus its poll endpoint.
- ▌ Codebase Exploration · hashgraph-online bundleExplore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts. Use when exploring code, understanding architecture, finding functions/types, analysing dependencies, searching database schemas or API specs, or when socraticode/codebase_search tools are available. Activates when the user asks about code structure, wants to find where a feature lives, or needs to understand how code is organised.
- ▌ Consistency Internal · hashgraph-online bundleApply internal consistency — making your product coherent with itself across all surfaces, components, and flows. Use when designing or auditing component libraries, defining design tokens, settling cross-team naming conventions, planning a design-system rollout, integrating acquired or legacy code, or evaluating whether two features should share or diverge in their interaction model. Internal consistency is enforced through design systems, shared vocabularies, and process discipline; it erodes through hand-off losses, sprint-driven shortcuts, and team boundaries that don't coordinate.
- ▌ Context Architecture · hashgraph-onlineProgressive disclosure architecture for organizing project context as a DAG (directed acyclic graph). Agents enter at the root and traverse only the subgraph relevant to their task. Covers the 4-tier information flow (refs → kits → plans → impl), CLAUDE.md hierarchy across context/ and source tree, index files as DAG hub nodes, nesting rules, and backward compatibility. Trigger phrases: "context architecture", "progressive disclosure", "organize context for agents", "context directory structure", "how to structure docs for AI", "context hierarchy"
- ▌ Octopus Architecture · hashgraph-online bundleReview system architecture, simplify boundaries, or compare interface designs from repository evidence
- ▌ Rust Bevy State Flow · hashgraph-online bundleDesign and review Bevy game state flow with plugins, AppState enums, OnEnter and OnExit setup, state-scoped cleanup, menus, pause screens, transitions, and run conditions. Use when adding reusable Bevy game state management, debugging duplicated entities after transitions, or separating menu, loading, playing, paused, and game-over logic.
- ▌ Aesthetics Router · hashgraph-online bundleUse this skill whenever a design task involves the felt quality of an interface — beauty, polish, brand voice, persuasion, emotional response, marketing surfaces, hero sections, onboarding tone, empty/celebration states, illustrations, mascots, avatars. Trigger when the user mentions tone, polish, brand, "feels cold/cheap/premium," personality, voice, mascot, hero, "make it more delightful," or asks how a screen should make the user feel. Framework-agnostic. Routes the model to the right aesthetics principle in this plugin.
- ▌ Enforce Design CI · hashgraph-online bundleUse when a repository needs deterministic pull-request checks for new accessibility, design-token, component-structure, responsive, and UI-state regressions with file-level evidence.
- ▌ Extracting Tables · hashgraph-onlineUse when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.