全部 Agent Skills
41,263 个结果
- Cutting SkillsbostonaholicAudits or trims an existing agent skill to its behavioral core and narrows over-broad trigger metadata. Use when the user asks to cut, simplify, shorten, de-slop, or reduce the context cost or trigger aggressiveness of a SKILL.md or skill folder. Never infer from a skill being long or edited for another purpose.
- DailykubilaygulacdiWrite the lead's daily stand-up message for the current project, "yesterday / today", short and paste-ready, at a level between technical and non-technical. Use when the lead asks for a daily, a stand-up, a daily report, "what did we do yesterday / today", or a summary of the day's work to post to their team.
- Data Analysisrhawk117Answers a question from data with a result that can be defended: fixes the question, the observation grain, the denominator and the baseline before choosing a method, validates along the deployment boundary without leakage, and reports effect size with uncertainty and what the evidence does not show. Hands back a rerunnable analysis script and a filled report.
- Data ChangeDimkoxUse for SQL schema changes, migrations, indexes, backfills, Elasticsearch/OpenSearch mappings, ClickHouse pipelines, and data-quality work.
- Data Cleanhongtongzhou-design数据清洗规范。当用户要求清洗/整理数据集、制定清洗规则、去重与缺失值处理、或产出清洗报告时使用。先画像再定规，规则先写进 rules.md 再动手，脚本只读原始数据绝不原地修改，处理后数据写入产物目录（不进 git），产出含行号/计数证据的清洗报告。
- Data Edahongtongzhou-design探索性数据分析与绘图规范。当用户要求对数据集做 EDA、分布/相关/异常分析、或绘制可复现图表时使用。分析前先做数据档案（样本量/缺失模式/变量类型）并列数据警告；分布、相关、异常按适用性覆盖并披露选择；图表英文标注、由可复现脚本生成并写入 figures/；每条发现区分描述性事实、探索模式和有明确验证依据的确证结论并可回溯出处；统计结论先过 stats-check 口径。
- Data Engineeringrhawk117Makes data code correct first and cheap second: pins down the output, estimates sizes before running, checks schema and join contracts, chooses the engine, reads the query plan before tuning, and has results returned or published as artifacts instead of printed. Covers synthetic data and tests for data code. Hands back the changed code with the measurement behind every speed or memory claim.
- Data SciencePetriLahdelmaExpert data science guidance for analytics, data processing, visualization, statistical analysis, machine learning, and AI integration. Use when analyzing data, building ML models, creating visualizations, processing datasets, conducting A/B tests, optimizing metrics, or integrating AI features. Includes Python (pandas, scikit-learn), data pipelines, and model deployment.
- Data Science ToolsmikkelkrogsholmDocumentation of available data science libraries (scipy, numpy, pandas, sklearn) and best practices for statistical analysis, regression modeling, and organizing analysis scripts. **CRITICAL:** All analysis scripts MUST be placed in reports/{topic}/scripts/, NOT in root scripts/ directory.
- Davinci ResolvealivirgoAutomate DaVinci Resolve media and timelines with its scripting API, build Fusion workflows, and configure render jobs.
- Db OpsSagargupta16Database work on the user's apps with a read-only-first posture. Inspect schema and live data (Neon or another hosted Postgres via its MCP server or CLI, local SQLite or Postgres via the repo's own CLI), answer what tables and columns exist and whether prod and local point at the same database, then on ask author and run migrations (Alembic for Python backends, Drizzle for TypeScript ones)…
- DbtalivirgoBuild dbt models with refs, data tests, and generated documentation for version-controlled warehouse transformations.
- dbt DevelopmentrittmananalyticsProactive skill for validating dbt models against coding conventions. Auto-activates when creating, reviewing, or refactoring dbt models in staging, integration, or warehouse layers. Validates naming, SQL structure, field conventions, testing coverage, and documentation. Supports project-specific convention overrides and sqlfluff integration.
- Ddu Proverkazhuga79Локализация РФ. Проверка договора участия в долевом строительстве (ДДУ) перед подписанием — 214-ФЗ «Об участии в долевом строительстве», ключевая защита покупателя жилья на этапе строительства. Эскроу-счёт (обязателен с 2019 года), гарантийный срок 5 лет на объект и 3 года на оборудование, неустойка за просрочку передачи (1/150 ключевой ставки ЦБ в день для граждан), актуальный статус моратория…
- DeaprolegendluvUse DEA MCP tools for stateful debugger sessions, compact stop deltas, and bounded inspection of GDB, LLDB, and PDB targets.
- Dead Code EliminationalivirgoUse static analysis to identify unused functions, variables, and imports before proposing code removal.
- Deal Champion MappingmbfinottiBuilds an evidence-graded stakeholder map for one active deal from titles, call notes, email and meeting activity, and CRM contact roles, naming the likely champion, economic buyer, and blockers, each with a confidence level tied to observed behaviour rather than title. Covers B2B buying committees and high-consideration B2C households.
- Deal Red FlagsmbfinottiReviews one deal's free-text notes - call notes, opportunity fields, CRM activity log, email threads - for qualification red flags such as single-threaded deal, no champion, no compelling event, unverified budget, no agreed next step, or fading engagement, each graded on severity and confidence with the quoted note fragment behind it. Covers B2B and B2C.
- Deal Value CalcmbfinottiBuilds the ROI and business case for one deal - value drivers, full investment, ROI, payback, three cases conservative-first, and a one-page case the champion can forward. The buyer supplies every assumption, each number labeled buyer-supplied, benchmark, or rep-assumed, and none invented. Covers B2B and high-ticket B2C.
- DedupesrinitudeUse when deduplicating bounded collections.
- Deduplicated File CachingalivirgoCache file reads using modification times or content hashes and invalidate them when the underlying files change.
- deed-pagef-o-x11Publish files to a permanent deed.page URL. No account.
- Deep Learningzjflsæ ¹æ®å¦ä¹ 主é¢åèå´ï¼æéæå¨ç书åãå客ãç½ç«ãæ¡æ¶ã论æçå¦ä¹ èµæï¼æ¯æ论æèªå¨ä¸è½½
- Deep Reading FrameworkdevkadeThree-pass critical reading framework for systematic document analysis. Supports tech blogs, retrospectives, technical documentation, personal writing, and academic papers. Primary focus on Third Pass critical analysis, context validation, and actionable reconstruction. Use when analyzing complex documents, performing critical reading, extracting actionable insights, or conducting deep analysis.