Parcourir le registre

Toutes les entrées, par ordre alphabétique — 81 384 au total. Page 104 sur 326.

• deck-safety-alert红琥珀警示色 + hazard 条纹 + L1/L2/L3 tier 卡片 + 删除线标题
• deck-simple通用 horizontal-swipe HTML deck, 不要 magazine 调
• deck-structureWhen and how to suggest reordering, splitting, or trimming a deck — agenda placement, CTA placement, problem-s
• deck-studioPPT 生产 Agent：理解场景 → 推荐风格 → 先出大纲 → 定义页面 → 双通路交付（PPT 内容稿 / 逐页视觉图 / 信息图组图）。当用户要做汇报、路演、培训课件、提案、咨询报告的演示文稿，或要把大纲/文章做
• deck-swiss-international16 列网格 + 单一饱和 accent + 22 个锁死版面 (Klein Blue / Lemon / Mint / Safety Orange)
• deck-tech-sharingGitHub-dark + JetBrains Mono + 终端代码块, 含 agenda + Q&A
• deck-writerPlan and write a complete presentation as slide-by-slide Markdown, including the deck brief, narrative outline
• deck-xhs-pastel奶油底 + 柔光 blob + 马卡龙圆角卡片 + Playfair 斜体序号
• deck-xhs-post9 页 3:4 竖版图文, 暖 pastel + 虚线 sticker 卡片
• deck-xhs-white纯白 + 顶部彩虹 bar + 渐变文字 + 马卡龙软卡片 + 黑底 pill
• declarative-read-only-command-allowlistsExpress shell-command safety as declarative flag maps so tooling knows exactly what passes.
• decocms-mcp-developmentBuild and maintain MCPs in the decocms/mcps monorepo. Covers deco HTTP server pattern (withRuntime, createPriv
• decode-minified-js-gatesClassify gate call variants in a minified JavaScript bundle. Covers context-window extraction around a flag oc
• decommission-validated-systemDecommission a validated computerized system at end-of-life. Covers data retention assessment by regulation, d
• decomp-fileDecompile a whole file (segment) in this Paperboy N64 project from top to bottom. Use when asked to decompile
• decompileDecompile a function to C-like pseudocode using angr
• decomposeDecompose work into stages with physical artifacts and acceptance checklists. Gap detector. Use when opening a
• decomposition-planning-roadmapCreates step-by-step decomposition plans and migration roadmaps for breaking apart monolithic applications. Us
• decoy-deployDECOY SUP deployment — running ./deploy --decoy [scope flags], 5-phase spinup, behavior.json plumbing, audit s
• dedao-jinxian按得到金线9条标准评估、审稿、打磨以"知识服务"为目标的内容,例如课程讲稿、专栏文章、讲书稿、知识付费内容、培训讲义、科普文章、演讲稿、分享稿。凡用户要求审稿、品控、把关、评估内容质量,或提到"金线""得到金线""得到标
• dedup-historyUse when a content-generating skill needs deduplication against history records. Referenced as a sub-skill by
• dedup-skillsLedger-first dedup of a skills/ or prompt-directory tree. Use when the user asks to dedup skills, find rules r
• dedupeUse when consolidating overlapping instruction files, auditing skills for duplicated guidance, or pruning para
• dedupe-rankUse when a broad paper candidate pool needs deterministic deduplication and a stable core set. **Trigger**: de
• dee-mcpFree AI music generation. Generate, share, and discover songs. First 10/month free.
• deel-ui-skillsDeel's UI design system. Use when building interfaces inspired by Deel's aesthetic - light mode, Inter font, 4
• deepWalks a deeply nested reference chain. Use when the user asks about the multi-step nested pipeline documentati
• deep-agentic-core-mcpUnified MCP server for AgenticLens and Agentic Chaos capabilities.
• deep-analysisRuns a long, structured multi-step reasoning chain over the sequential-thinking MCP server, with branching, re
• deep-analyzeDeep-dive analysis of an initial proposal — research code implementation, produce an actionable roadmap and al
• deep-auditComprehensive codebase or system audit. Use when asked to "audit the codebase", "review everything", "find all
• deep-brainstormingUse when brainstorming a product or feature where multiple valid technology choices exist and the wrong one is
• deep-cleanFull-spectrum consolidation of AI agent configuration files. Goes beyond memory-only dream skills: audits and
• deep-code-reviewUse when the user wants a pull request, diff, commit, patch, branch, or set of changed files reviewed through
• deep-code-reviewerPerform rigorous, architecture-aware code review focused on subtle correctness bugs, race conditions, performa
• deep-company-seriesAI Berkshire skill: 深度公司系列：8 篇长文拆一家公司. Source: skills/deep-company-series.md.
• deep-contextProduct management skills for Claude Code. 8 plugins, 35 skills, one-line install. Customer discovery that ver
• deep-debugThe single entry point for ALL debugging — bugs, test failures, CI failures, Metaflow run failures, Jenkins bu
• deep-debug-ensemble-v1Use when the user asks to debug with ensemble judges, or explicitly requests the ensemble variant of deep-debu
• deep-designThe single entry point for ALL design and specification work. Use when designing, specifying, architecting, wr
• deep-discuss结构化深度讨论 Skill，用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难，或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我
• deep-dive2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point i
• deep-execution-frameworkMetacognitive execution framework for deep project engagement, production-ready output, and critical self-dire
• deep-exploreMulti-wave parallel code exploration orchestrator. Use when: large-scale codebase research, understanding comp
• deep-financial-researchComprehensive financial research using MCP servers (Exa + Financial Datasets). Includes integrated DCF valuati
• deep-ideaUse when generating novel ideas, breakthroughs, concepts, product ideas, research directions, startup ideas, o
• deep-interviewSocratic deep interview with mathematical ambiguity gating before autonomous execution
• deep-learning苏格拉底式深度学习导师 —— 当你想"真正搞懂"一样东西（一个概念、一套系统、一个业务领域、一段代码、一篇文章的底层逻辑），而不只是要个答案时使用。它不一次性把答案倒出来，而是循序渐进地教、逼你用自己的话复述、追着问"为
• deep-linkingGenerate deep linking infrastructure with URL schemes, Universal Links, and App Intents for Siri/Shortcuts. Us
• deep-planUse before touching code for any multi-step task — features, refactors, migrations, architectural decisions, b
• deep-qaUse when reviewing, auditing, QAing, critiquing, verifying, or assessing any artifact — a spec, code change, d
• deep-qa-ensemble-v1Use when the user asks to review with ensemble judges, or explicitly requests the ensemble variant of deep-qa.
• deep-readComprehensive codebase reading engine. Systematically reads actual source code line by line through a 6-phase
• deep-readingComposable, community-driven workflows for smartgate — declarative pipelines (research, deep-reading, memory)
• deep-reading-analystDeep analysis of articles/long-form via thinking frameworks (SCQA, mental models, inversion) — 'analyze articl
• deep-referenceUse when validating deep references
• deep-referencesA skill with a deeply nested reference path.
• deep-researchUse this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is
• deep-research-add-fieldsAdd field definitions to existing research outline.
• deep-research-agentComprehensive research agent for in-depth investigation. Use when users ask for deep research, comprehensive a
• deep-research-glimConducts deep, multi-angle research using glim MCP tools and parallel subagents. Use for deep research, compet
• deep-research-mcp-serverMCP server that gives Claude, Cursor, or any AI agent web search, clean page reading, and one-call research do
• deep-research-notebooklmDeep research skill powered by NotebookLM MCP. Conducts structured multi-source research (market analysis, com
• deep-research-proMulti-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports.
• deep-research-reportConvert deep research output (Claude Research, ChatGPT Deep Research, Gemini, Codex — any long-form MD/Word/te
• deep-research-teamThis skill should be used when the user asks for "deep research", "research team", "comprehensive analysis", "
• deep-research-workflowUse when a research task benefits from an explicit phased workflow with structured source handoff across searc
• deep-researcherPerforms comprehensive, multi-layered research on any topic with structured analysis and synthesis of informat
• deep-review設計整合性、セキュリティ、RDD準拠を深掘りチェックする。basic-review後の二次レビュー、sprint→mainマージ前の品質確認で使う。
• deep-scanFeed this agent a data file (appointment export, referral data, financial data) and it runs ALL relevant analy
• deep-skill-finder最好的找Skill的方式，能够基于你的任务，去寻找最匹配的高质量Skill。以下两种情况下都应使用本技能：① 用户主动要找 Skill，或者需要借助他人经验时——当用户说"找个 xxx 技能""股票分析别人怎么做的""找
• deep-specConducts an interview-driven design session using a multi-level zoom approach (L5:Domain to L1:Line), producin
• deep-workWhen the user says they can't focus, can't get the real work done, are losing the day to shallow tasks, or hav
• deep-work-plannerDesigns a daily schedule that protects deep work - classifies tasks as deep or shallow, places 2-4 focus block
• deepadbDeepADB — full-featured Android Debug Bridge MCP server. 209 tools across 49 modules for device inspection fro
• deepagents-architectureGuides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternat
• deepagents-code-reviewReviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_d
• deepagents-implementationImplements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, de
• deeparchi-patent-mcpPatent search over 1.4B global records via Google Patents on BigQuery, with CN coverage.
• deepbomLocal multi-format deployment-artifact analysis for on-device AI models
• deepbook-orderbookIntegrate DeepBook v3 orderbook on Sui (limit orders, CLOB, DEX). Use when the user wants to build on DeepBook
• deepbook-researchResearch DeepBook trading data and market gaps on Sui. Use when the user wants DeepBook research, market oppor
• deepchat-cliUse DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OC
• deepchat-data-importHelp developers build third-party tools that import, inspect, migrate, or analyze DeepChat data. Use when Code
• deepchat-releasePrepare and publish DeepChat releases in this repository. Use when Codex needs to bump the app version, update
• deepchat-sddUse before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or
• deepchat-sdd-cleanupUse only when a developer explicitly asks to clean, prune, tidy, or organize DeepChat SDD documentation after
• deepchat-settingsDeepChat app settings modification (DeepChat 设置/偏好) skill. Activate ONLY when the user explicitly asks to chan
• deepchemMolecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) wi
• deepchem-circular-featurizationUse this skill to compute compact DeepChem circular fingerprints from a small set of SMILES strings with the r
• deepchem-molgraph-featurizationUse this skill to featurize SMILES strings into DeepChem molecular graph objects. Prefer it for local graph-ba
• deepenOptional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the c
• deepfake-detector-mcpDeepfake Detector MCP Server by MEOK AI Labs
• deepgram-webhooksReceive and verify Deepgram webhooks (callbacks). Use when setting up Deepgram webhook handlers, processing tr
• deepline-ads-audiencesUse this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Matc
• deepline-analyticsUse this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or
• deepline-feedbackSend feedback or bug reports to the Deepline team, including session transcript and environment info. Use when
• deepline-gtmGTM prospecting, enrichment, outreach, scoring, CSVs, and plays. Discovery: deepline-pre-research. Providers:
• deepline-monitorsACCESS-GATED beta. Deepline Monitors are provider event feeds (job posts, email replies, funding, intent) that
• deepline-playsUse this skill for Deepline GTM jobs that search, enrich, score, collect signals, or automate a workflow: “fin
• deepline-plays-reviewUse this skill when a human needs to review a Deepline Play result and hand feedback, labels, or approval back
• deepline-pre-researchUse when the user wants a last30days-style pre-research pass in Deepline: discover the critical public, privat
• deepline-quickstartRun a quick Deepline demo recipe to show the user how Deepline works.
• deepmap-earth-grounding-mcpVerifiable Earth ground truth for AI agents: water, hazard, ground stability, resource, with proof.
• deepmd-finetune-dpa3Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained
• deepmd-python-inferenceRun Python inference with DeePMD-kit models using the DeepPot API. Use when the user wants to load a trained/f
• deepmd-trainTrain DeePMD-kit models with progressive disclosure. Use when the user wants to train a DeePMD-kit potential,
• deepnatalNatal charts cross-verified three ways. Refuses to answer rather than guess.
• deeppapernoteGenerate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use wh
• deepread-apiFull DeepRead API reference. All endpoints, auth, request/response formats, blueprints, webhooks, error handli
• deepread-bank-statementsExtract structured data from bank statements — account holder, period, opening/closing balances, and every tra
• deepread-byokBring Your Own Key to DeepRead. Connect your OpenAI, Google, or OpenRouter API key — all document processing r
• deepread-form-fillAI-powered PDF form filling via DeepRead. Upload any PDF form + your data as JSON — AI detects fields, maps da
• deepread-id-documentsExtract structured data from passports, driver's licenses, and national ID cards for KYC/onboarding — name, do
• deepread-insuranceExtract structured data from insurance claims, policies, EOBs, and loss reports. Pre-built schemas for claiman
• deepread-invoiceExtract structured data from invoices, receipts, and bills using DeepRead. Pre-built schemas for vendor, line
• deepread-legalExtract structured data from contracts, legal agreements, court filings, and compliance documents. Pre-built s
• deepread-medicalExtract structured data from medical records, lab reports, prescriptions, and clinical documents. Pre-built sc
• deepread-pay-stubsExtract structured data from pay stubs and earnings statements — employer, employee, pay period, gross/net pay
• deepread-piiRedact PII from documents before sharing or sending to LLMs. 14 PII types (names, SSN, credit cards, medical r
• deepread-purchase-ordersExtract structured data from purchase orders — PO number, buyer/supplier, line items, quantities, prices, deli
• deepread-resume-parserParse resumes and CVs into structured JSON — contact info, work history, education, skills, and total years of
• deepread-setupGet started with DeepRead. Automatically obtains an API key via OAuth device authorization flow, then walks th
• deepread-shipping-docsExtract structured data from bills of lading, packing lists, and shipping manifests — shipper, consignee, carr
• deepread-tax-formsExtract structured data from W-2s, 1099s, 1040s, and other tax forms — employer/payer, recipient, wages, withh
• deeprefineAgent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of
• deepresearch-searchStage 2b of the lit review pipeline: run a Google Gemini Deep Research deep search (Interactions API) from the
• deepseekDeepSeek AI models for coding. Use for code AI.
• deepseek-harnessDelegate code review, development, and research tasks to DeepSeek Harness.
• deepseek-provider-contractValidate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode to
• deepspeedExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16
• deepspot-mGenerate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you n
• deepstream-devNVIDIA DeepStream SDK development guidance for Python pyservicemaker pipelines, video analytics, TensorRT inte
• deepstream-generate-pipelineBuild DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inf
• deepstream-import-vision-modelNVIDIA DeepStream model-import guidance for bringing vision models from Hugging Face or NVIDIA NGC into DeepSt
• deepstream-profile-pipelineProfile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the us
• deepstream-run-mv3dtRun and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user as
• deepstream-sopUse this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP In
• deepthonkProvider-neutral OpenDeepThink reasoning server: generate, judge, rank, mutate.
• deeptoolsNGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, p
• deeptools-ngs-analysisNGS CLI for ChIP/RNA/ATAC-seq. BAM→bigWig with RPGC/CPM/RPKM, sample correlation/PCA, heatmaps/profiles around
• deepviews-mcpFree financial data MCP server — company analysis, DCF valuation, comparable companies, industry benchmarks, s
• deezer-mcpSearch tracks and albums on Deezer. No key required.
• defaultBasic policy and philosophy when acting as an AI agent
• defect-detectionAnalyze manufacturing defect detection and quality control systems — computer vision inspection pipelines, SPC
• defending-applicationsApplication security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA
• defending-llms-with-guardrailsDeploy Llama Guard, NeMo Guardrails, and LLM Guard input/output scanners as runtime defenses.
• defense-budgetAnalyze defense program budgets and acquisition costs — earned value management (EVM/CPI/SPI), should-cost mod
• defense-in-depthUse when invalid data causes failures deep in execution, requiring validation at multiple system layers - vali
• defense-in-depth-validationValidate at every layer data passes through to make bugs impossible. Use when building data pipelines or syste
• defense-maintenanceAnalyze defense maintenance and readiness systems — MRO optimization, mission capable rate tracking, reliabili
• defense-prep-thคำถาม + คำตอบที่กรรมการชอบถาม | สำหรับ นักศึกษา. Triggers when user says (Thai/EN): 'thesis defense', 'สอบป้อง
• defense-supply-chainAnalyze defense supply chain systems — DFARS compliance assessment, CMMC cybersecurity readiness, sole-source
• deferred-findingUse when a review finding cannot be fixed in current PR - creates properly documented tracking issue with full
• deferred-refresh-flag-contractDecide when to auto-refresh plugins after marketplaces change and when to defer to a manual `/reload-plugins`
• deferring-state-readsUse this skill to push frequently-changing Jetpack Compose state reads (scroll position, animation values, dra
• defi-mcpAI agent access to on-chain DeFi data on Polygon & Arbitrum: balances, positions, prices.
• defi-protocol-interactionDeFi protocol interaction skill for Uniswap, Aave, Compound, and other major DeFi protocols
• defi-protocol-templatesImplement DeFi protocols with production-ready templates for staking, AMMs, governance, and flash loans. Use w
• defi-quote-exec-demoA curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts ac
• defi-safety-shieldComprehensive DeFi safety monitoring - scan tokens for risks, detect phishing, audit wallet approvals, and sco
• defi-security[AUTO-INVOKE] MUST be invoked BEFORE deploying DeFi contracts (DEX, lending, staking, LP, token). Covers anti-
• defi-yield-scoutFind, compare, and risk-score DeFi yield opportunities across 20+ protocols and 10+ chains. Includes impermane
• defiguard-mcpDeFiGuard MCP Server - DeFi protocol risk analysis tools for AI coding agents. Analyze token contracts, detect
• defillama-suiResearch Sui DeFi TVL, protocols, and yield via DefiLlama. Use when the user wants Sui DeFi data, TVL, or prot
• defineDefine a work unit at any tier — product, epic, feature, or task. Invoke with /agn:define <level>. Produces vi
• define-hypothesisDefines a testable hypothesis with clear success metrics and a validation approach. Use when forming assumptio
• define-jtbd-canvasCreates a Jobs to be Done canvas capturing the functional, emotional, and social dimensions of a customer job.
• define-opportunity-treeCreates an opportunity solution tree connecting a desired outcome to customer opportunities and candidate solu
• define-perspectivesThis skill should be used when the user asks to "define our perspectives," "set up our scorecard structure," "
• define-prioritization-frameworkRun applicable prioritization frameworks (RICE, ICE, MoSCoW, Weighted Scoring, Kano) against a list of feature
• define-problem-statementCreates a clear problem framing document with user impact, business context, and success criteria. Use when st
• define-rubricBuilds measurable validation criteria when no existing standards apply. Invoked by team agents during review.
• define-strategyProduct strategy workflow — chain positioning, business model, OKRs, and roadmap Use when: Defining product st
• define-ux-success-metricsDefines how a design's success will be measured: HEART goals→signals→metrics, SUS/SEQ/NPS instrument selection
• define-variablesLiterature-grounded variable operationalization for observational research. Turns a data dictionary + research
• define-x68 plug-and-play, best-practice product management skills for AI agents: 30 Triple Diamond phase + 11 foundati
• defining-icpHelp users identify their most high-value customers by defining a hyper-specific ICP that maximizes product-ma
• defining-product-strategyHelp users move beyond ambitious goal-setting to create a rigorous diagnosis of challenges and a clear, action
• defining-product-visionDefine or refresh a product vision: vision statement, narrative, pillars, strategic choices, rollout.
• definition-of-doneThe ordered finish-line runner for any change in this repo — generators, then the asset-integrity refresh last
• definitionsSets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know th
• definitive-article-writerWrite the ONE canonical page that owns a topic or a person's name — comprehensive, source-linked, structured s
• defluffDeterministic prose linter for LLM text — flags AI slop, filler, buzzwords, hedges, clichés.
• defuddleExtract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save toke
• deglazeStrip the sycophancy. Apply accountability pressure to push past an LLM's default declare-done glaze. Use when
• dehallucinationUse when verifying that AI-generated claims, references, or assertions are grounded in reality. Triggers: 'doe
• dehumanize-ai-textПрименять при переписывании текстов, сгенерированных LLM-агентами (отчеты, README, доки, письма, посты), в жив
• dei-strategyTRIGGER THIS when building DEI strategy, creating diversity goals, designing inclusive programs, building equi
• deid-reid-harnessBuild and run an adversarial de-identification ⟷ re-identification evaluation harness for clinical text: gener
• deidentifyDe-identify clinical research data before LLM-assisted analysis. Standalone Python CLI detects PHI via regex +
• dejared-mcpJava decompiler MCP server for AI coding agents. Explore, search, and decompile JAR, WAR, EAR, and AAR bytecod
• dekkoStatic code map generator: MAP.md + map.json for any repo, plus a Claude Code /map plugin
• delay-model-gate-evaluatorExecute delay-model validation gates against HPWL baselines. Use when evaluating model consistency, running Ga
• delega-efficienteUse when planning how to execute a task that involves delegation or orchestration - before launching subagents
• delegate-manager-to-subagentsManage execution of an approved plan through subagents. Use when the user asks the main agent to coordinate im
• delegate-setupConfigure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and ef
• delegate-to-ideDelegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context
• delegating-to-ottoDrives Astronomer's Otto agent (`astro otto`) as a delegated sub-agent for Airflow, dbt, and data-engineering
• delegating-workCreate a Delegation Pack (brief, decision rights, context handoff, check-in cadence, debrief).
• delegationParallelize work via background/foreground agents, built-in types, custom agents, or agent teams/swarms. USE W
• delegation-auditAudit model delegation and subagent effectiveness for a session — which models handled which subagent types, p
• delegation-briefInteractive skill for Cowork that generates a structured delegation brief
• delegation-coachTeaches you how to delegate tasks to Cowork so clearly that you get
• delegation-coreDelegates tasks to Gemini or Qwen with quota tracking and error handling. Use when tasks exceed context window
• delegation-frameworkBuilds task delegation systems with responsibility matrices, handoff templates, accountability tracking, and e
• delegation-principleCore principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagen
• delegation-scorerScore whether a delegation decision is healthy (amplifying what you love) or harmful (abdicating what you don'
• delegation-strategyDecision guide for choosing between inline work, one subagent, parallel subagents, and workflow orchestration.
• delentia-mcpStop rogue AI-agent tool calls before they run: deterministic policy gate + audit digest.
• deletePreview and permanently delete a NeatContext context while preserving any externally linked knowledge folder.
• deliberateMulti-model deliberation and research. USE WHEN deliberate, multi-model, cross-model, real models debate, genu
• delightAdd moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. E
• delimit-cliKeep the state. Change the model. Shared context and a multi-model panel across Claude Code, Codex, Cursor, An
• delinea-mcpDelinea Secret Server API: secrets search and retrieval.
• delist-after-reconcile-enforcementRun delist or blocklist enforcement after synchronization so removals update both metrics and downstream refre
• deliverRender a selection of retrieved fragments into Claude's working context per the deliver format contract. Libra
• deliver-acceptance-criteriaGenerates structured Given/When/Then acceptance criteria for a user story or feature slice, covering the happy
• deliver-edge-casesDocuments edge cases, error states, boundary conditions, race conditions, and recovery paths for a feature - t
• deliver-launch-checklistCreates a cross-functional pre-launch checklist covering engineering, design, marketing, support, legal, and o
• deliver-prdCreates a comprehensive Product Requirements Document that aligns stakeholders on what to build, why, and how
• deliver-release-notesCreates user-facing release notes that communicate new features, improvements, and fixes in clear, benefit-foc
• deliver-user-storiesGenerates user stories in the standard persona, action, benefit story format from product requirements or feat
• deliver-y68 plug-and-play, best-practice product management skills for AI agents: 30 Triple Diamond phase + 11 foundati
• deliverability-checkAudit a sending domain's deliverability — SPF, DKIM, DMARC, MX, BIMI, blocklists — with a prioritized fix orde
• deliverability-checkerCheck email deliverability and DNS configuration. Use when: diagnosing email delivery issues; setting up new e
• deliverability-monitoringMonitor outbound deliverability health across domains, inboxes, DNS, bounces, spam placement, reply rates, and
• deliverability-qaUse when the user asks to "run a deliverability pre-flight before I send", "check my SPF/DKIM/DMARC/BIMI", "wh
• deliverable-selfloopScore an existing reader-facing deliverable and emit a deterministic PASS/FAIL scorecard plus bounded repair p
• delivering-mvp-fleetUse when the user wants to build, deliver, or orchestrate an MVP, prototype, demo, or v1 of ANY project (softw
• deliverkit-mcpPlan and verify multi-ecosystem packaging (Linux, Windows, macOS, HarmonyOS) for AI agents.
• deliveryAdaptive, resumable Git delivery across repositories and agent runtimes — probe policy, checkpoint coherent wo
• delivery-charterTurn a scoped engagement into a project charter, milestone plan, RAID log, and a one-page weekly status. Use a
• delphiUse when writing, reviewing or fixing Delphi / Object Pascal code — any .pas or .dpr unit, the RTL or the VCL
• delphi-clean-codePragmatic clean code standards for Delphi — concise, direct, no over-engineering
• delphi-code-refactoringRefactoring techniques for Object Pascal: Extract Method, Extract Class, Guard Clauses, Replace Magic Numbers,
• delphi-code-reviewDelphi code review checklist — quality, security, performance, SOLID, memory
• delphi-code-smellsUse when reviewing existing Delphi / Object Pascal code for defects, hunting a memory leak or an access violat
• delphi-intraweb-to-lazarus-migrationMigracao Delphi IntraWeb -> Lazarus IntraWeb com equivalencia funcional, sem refatorar regra de negocio. Inclu
• delphi-memory-and-exceptionsGood memory management practices, memory leak prevention and exception handling in Delphi
• delphi-memory-exceptionsGood memory management practices, memory leak prevention and exception handling in Delphi
• delphi-solid-patternsSOLID implementation patterns for Delphi projects — Repository, Service, Factory, Strategy with constructor in
• delphi-test-driven-development-tdd-and-dunitxGuidelines on how the AI ​​should act and code when the user requests TDD, unit tests, DUnitX or fakes/mocks u
• delphi-to-angularUse when converting Delphi VCL views (.dfm/.pas) from the P2 codebase to Angular components. Handles forms, fr
• delphi-to-lazarus-migration-quickVersao curta para migracao Delphi/IntraWeb -> Lazarus com equivalencia funcional. Foco em checklist objetivo,
• delphi-uses-graphAnalyzes a Delphi / Object Pascal codebase to extract unit-level `uses` dependencies. Use when the user upload
• delphimvcframeworkPatterns for development with DelphiMVCFramework (DMVC) — controllers, Active Record, JWT, Swagger
• deltaSynthetic audit fixture for delta.
• delta-skilltest fixture — curated folder layout
• delta-witness-mcpMCP tools for paid DELTA Witness Capture and Guard preflight observations