ReddRadar
Topic: workflow
528 skills in this topic.
-
next-upgrade
Upgrade Next.js to the latest version following official migration guides and codemods
inkeep/agents 1,070
-
next-cache-components
Next.js 16 Cache Components - PPR, use cache directive, cacheLife, cacheTag, updateTag
inkeep/agents 1,070
-
next-best-practices
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
inkeep/agents 1,070
-
manage-database-usage
How to correctly access the Doltgres manage database with branch-scoped connections. Use when reading or writing manage data (agents, tools, projects, credentials, triggers, evaluators, etc.). Triggers on: manage database, withRef, c.get('db'), manageDbPool, branch checkout, doltgres, ref-scope, branchScopedDb, AgentsManageDatabaseClient.
inkeep/agents 1,070
-
internal-surface-areas
Dependency graph of internal subsystems, infrastructure, and tooling (everything NOT customer-facing).
Use during planning, PR review, or refactoring to understand the internal ripple effects of a change.
Complements product-surface-areas (which covers customer-facing surfaces).
inkeep/agents 1,070
-
github-repo-sanity
Sanity-check GitHub repositories before citing, recommending, or comparing them.
Use when an agent refers to GitHub repos, OSS libraries, starter kits, templates, SDKs, MCP servers, or example projects.
Verify repo health using recent commit activity and adoption signals such as stars before recommending it.
Prefer active repos; explicitly flag stale, archived, or low-signal repos instead of presenting them as good defaults.
inkeep/agents 1,070
-
find-similar
Find similar or analogous code patterns elsewhere in a codebase.
Use when answering "Do we do something similar elsewhere?" or "What existing patterns match this?"
Returns factual findings about similar code - locations, similarity type, and confidence.
inkeep/agents 1,070
-
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
inkeep/agents 1,070
-
data-model-changes
Guide for making changes to the database schema, validation, types, and data access layer. Use when adding tables, columns, relations, or modifying the data model. Triggers on: add table, add column, modify schema, database change, data model, new entity, schema migration.
inkeep/agents 1,070
-
audience-impact
Who does this change affect and how does it reach them? Maps audiences (roles × deployment modes) to impact propagation — immediate, next-publish, next-deploy, or silent.
Use when planning, implementing, or reviewing a change to understand blast radius by audience.
Complements product-surface-areas and internal-surface-areas (which catalog what exists; this skill tells you who cares).
Triggers: who is affected, blast radius, breaking change, audience, persona, impact analysis, changeset needed, docs needed.
inkeep/agents 1,070
-
api-logging-guidelines
Best practices and guidelines for using logger in API routes. Defines appropriate logging levels, what to log, and when to avoid logging. Use when implementing or reviewing API route logging, debugging strategies, or optimizing log output.
inkeep/agents 1,070
-
add-model
Add a new language model to the Giselle codebase. Use when the user wants to add, register, or integrate a new LLM model (OpenAI, Anthropic, Google) into the system.
giselles-ai/giselle 510
-
ao-workflow-runner
多角色 YAML 工作流执行引擎——解析 workflow YAML，加载 agency-agents-zh 角色，按 DAG 顺序执行
jnMetaCode/agency-orchestrator 211
-
maestro:visual
Create interactive HTML visualizations of maestro state and debug data
ReinaMacCredy/maestro 26
-
maestro:verification
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
ReinaMacCredy/maestro 26
-
maestro:debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
ReinaMacCredy/maestro 26
-
maestro:prompt-leverage
Strengthen a raw user prompt into an execution-ready instruction set for Claude Code, Amp, Codex, or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.
ReinaMacCredy/maestro 26
-
maestro:tdd
Use when implementing any feature or bugfix, before writing implementation code
ReinaMacCredy/maestro 26
-
maestro:parallel-exploration
Use when you need parallel, read-only exploration with task() (Scout fan-out)
ReinaMacCredy/maestro 26
-
maestro:note
Capture decisions, constraints, and context to persistent memory. Global memory is injected into every session and implementation run. Per-feature memory tracks working context.
ReinaMacCredy/maestro 26
-
maestro:next-move
Strategic analysis of a project to identify the single highest-leverage, most innovative addition. Use when the user asks what to build next, what the most impactful improvement would be, what's missing, or any question about strategic direction and priorities. Also use when stuck choosing between competing features.
ReinaMacCredy/maestro 26
-
maestro:design
Deep discovery and specification for ambitious features. Full BMAD-inspired interview with classification, vision, journeys, domain analysis, and FR synthesis. Same output contract (spec.md + plan.md) as a standard feature but far richer. Use for multi-component systems, regulated domains, or unclear requirements.
ReinaMacCredy/maestro 26
-
maestro:debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
ReinaMacCredy/maestro 26
-
maestro:brainstorming
Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
ReinaMacCredy/maestro 26