262 个 · 按相关度排序
Great Expectations, dbt tests, anomaly detection, and data contracts for data quality. Activate on: data quality, data validation, Great Expectations, data contract, anomaly detection, SLA, freshness check, schema validation. NOT for: dbt model structure (use dbt-analytics-engineer), schema evolution (use schema-evolution-manager).
中文简介正在准备中。当前显示原文说明。
Large-scale data migrations with validation, rollback, and zero-downtime strategies. Activate on: data migration, database migration, zero-downtime migration, dual-write, backfill, cutover, data validation, schema migration. NOT for: schema evolution in streams (use schema-evolution-manager), API versioning (use api-versioning-backward-compatibility).
中文简介正在准备中。当前显示原文说明。
API migration strategies, deprecation workflows, and header/URL/content versioning. Activate on: API versioning, backward compatibility, deprecation, breaking change, API migration, v1 v2, sunset header. NOT for: schema evolution in data (use schema-evolution-manager), gateway routing (use api-gateway-reverse-proxy-expert).
中文简介正在准备中。当前显示原文说明。
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
中文简介正在准备中。当前显示原文说明。
Plans safe API evolution with versioning strategies, client migration guides, deprecation timelines, and backward compatibility considerations. Use for "API versioning", "deprecation planning", "API evolution", or "breaking changes".
中文简介正在准备中。当前显示原文说明。
根据评分标准反复改进提示词、正则表达式、SQL和短代码。由AI生成候选方案，利用失败示例继续修正，并通过日志和快照查看结果。
Create a fixed JSON evaluation suite from a repository's existing tests and check its structure for errors. Use the suite with harness-evolve to compare variants against consistent tasks, independently of the repository's normal test command.
中文简介正在准备中。当前显示英语简介。
Inspect evolved prompt configurations, validate their structure, and view the system prompts they produce. You can also classify failures in run transcripts to support reviews before adopting or changing an agent policy.
中文简介正在准备中。当前显示英语简介。
Evaluate 3D point clouds and movement trajectories against reference data with CloudAnalyzer. Prepare inputs, measure differences, apply quality thresholds, inspect results visually, and track baseline history for mapping, localization, and perception workflows.
中文简介正在准备中。当前显示英语简介。
Design a process for AI agents to learn from execution records. Evaluate outcomes, actions, and quality, choose whether to update knowledge, instructions, code, or model parameters, and define independent validation, release checks, and rollback procedures.
中文简介正在准备中。当前显示英语简介。
Compare two versions of a project and turn migration patterns into instructions for GitHub Copilot. Document API replacements, new conventions, obsolete patterns, and validation steps so future code changes follow the same approach.
中文简介正在准备中。当前显示英语简介。
Run repeated code improvement experiments with multiple agents. It plans and reviews candidate changes, compares benchmark results, merges candidates that pass rechecking, and records progress until a target, iteration limit, or another stopping condition is reached.
中文简介正在准备中。当前显示英语简介。
Organize scattered concept notes into a map of recurring ideas. Merge duplicates, rank concepts into four tiers, trace how stronger ideas developed across sources, and assess which notes to keep, rewrite, merge, or remove.
中文简介正在准备中。当前显示英语简介。
Trace how one idea developed across stored notes and records. Identify its earliest documented mention, clearest expression, changes of stance, contradictions, abandoned branches, and current form, with dated evidence and explicit gaps where sources are missing.
中文简介正在准备中。当前显示英语简介。
Set up, debug, and extend PicoClaw using its own commands and configuration structure. Get guidance on model authentication, external tool connections, scheduled tasks, and how conversations are routed and stored.
中文简介正在准备中。当前显示英语简介。
Turn an OpenAPI specification into starter code for an MCP server, which connects AI agents to API tools. Support Python or TypeScript implementations, validate tool definitions, and plan changes that preserve compatibility.
中文简介正在准备中。当前显示英语简介。
Helps founders and first-time CEOs review delegation, calendar use, energy, and leadership blind spots. Provides frameworks and reflection questions for adapting their role as the company grows, addressing burnout concerns, and preparing others to take over responsibilities.
中文简介正在准备中。当前显示英语简介。
Helps startup leaders make strategic data decisions: assess permission to train AI on customer data, choose data architecture, evaluate customer data as a business asset, and sequence hiring around the decisions the business needs to make.
中文简介正在准备中。当前显示英语简介。
Support startup AI strategy by comparing API use, fine-tuning—additional training of an existing model—and in-house development. Assess three-year costs, regulatory risk, self-hosting breakeven points, and hiring priorities to inform leadership decisions.
中文简介正在准备中。当前显示英语简介。
Plan customer retention and customer success staffing for a startup. Break down renewal and churn patterns, group customers by value and fit, and compare service models to guide resource allocation and hiring.
中文简介正在准备中。当前显示英语简介。
Research a product, company, concept, or person by tracing its history and comparing it with current peers. Combine both perspectives to explain strengths, weaknesses, and possible futures, then deliver a structured PDF report with sources.
中文简介正在准备中。当前显示英语简介。
Extends the core PUA skill with local performance notes, recovery of task state after conversation compression, KPI report cards, and style switching. It tracks established working habits across sessions and keeps feedback in a local file.
中文简介正在准备中。当前显示英语简介。
Develop varied ideas for names, writing angles, and problem solving by exploring five candidates internally and presenting the strongest. It also expands small example collections into diverse datasets for evaluation, training, or testing.
中文简介正在准备中。当前显示英语简介。
Explore explanations for poorly understood phenomena through repeated hypothesis generation and selection. Compare causal mechanisms, test what happens when components change, and retain distinct candidates with predictions, rival comparisons, and clearly stated unresolved questions.
中文简介正在准备中。当前显示英语简介。