最高评分
社区最喜爱的高星技能，质量有保障。
scenario-grok-imagine-image
scenario-labs
"Use when generating or editing images with Grok Imagine models on Scenario via MCP: text-to-image, instruction editing with up to three reference images, posters, packaging, ads, or infographics with exact in-image text, photoreal shots from camera and lighting cues, extended aspect ratios up to 20:9 and 9:20, quality and resolution tiers, or batches of variations. Keywords: Grok Imagine Image 2.0, Image Quality, xAI, Aurora, Grok, txt2img, img2img, typography, 2K."
scenario-grok-imagine-video
scenario-labs
"Use when generating or editing video with Grok Imagine models on Scenario via MCP: text-to-video, image-to-video from a first frame, reference-to-video with @image tags for consistent people, products, or clothing, prompt-based editing, extending a clip from its last frame, native audio with lip-synced dialogue and sound effects, or choosing between first-frame and reference conditioning. Keywords: Grok Imagine Video 1.5, R2V, Grok Edit Video, Grok Extend Video, xAI, T2V, I2V, V2V."
error-propagation
hoangsonww
Trace error propagation through a multi-agent session by agent depth — where failures originated, the depth at which they appeared, and how they cascaded up to parent agents — using the Agent Monitor workflow intelligence API and the session event stream. Use when a multi-agent run failed and you need to find the origin and blast radius of the failure.
session-debug
hoangsonww
Debug a specific session by inspecting its full event chain (PreToolUse, PostToolUse, Stop, SubagentStop, Compaction, APIError, TurnDuration, Notification events), agent hierarchy (recursive parent/child tree with subagent_type and depth), token usage with compaction baselines, workflow intelligence data (orchestration DAG, error propagation by depth), and session metadata (thinking_blocks, turn_count, total_turn_duration_ms).
run-agent
hoangsonww
Launch and supervise Claude Code or Codex through the CCAM Run API. Use when the user wants to start a monitored agent, select a model, approval policy, sandbox, or working directory, send a follow-up, inspect live output, resume a native session, or stop a dashboard-launched run.
gentle-ai
Gentleman-Programming
"Use Gentle AI harness discipline for Pi work: clarify first, track ODD work, use applicable test-first development by default, delegate when useful, and protect review workload."
gentle-ai-work-unit-commits
Gentleman-Programming
"Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code."
gentle-ai-branch-pr
Gentleman-Programming
"Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review."
gentle-ai-chained-pr
Gentleman-Programming
"Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus."
gentle-ai-issue-creation
Gentleman-Programming
"Create and triage GitHub issues from repository evidence. Trigger: issue creation, bug reports, feature requests, or issue approval."
gentle-ai-judgment-day
Gentleman-Programming
"Trigger: judgment day, judgement day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds."
gentle-ai-cognitive-doc-design
Gentleman-Programming
"Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs."
gentle-ai-comment-writer
Gentleman-Programming
"Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments."
gentle-ai-skill-registry
Gentleman-Programming
"Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path."
gentle-ai-rdd-defect-workflow
Gentleman-Programming
"Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work."
gentle-ai-skill-creator
Gentleman-Programming
"Trigger: /skill-creation, skill creation, skill creator, create skill, new skill. Create LLM-first skills with valid frontmatter."
gentle-ai-skill-improver
Gentleman-Programming
"Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills."
convex-backend
CloudAI-X
Convex backend development guidelines. Use when writing Convex functions, schemas, queries, mutations, actions, or any backend code in a Convex project. Triggers on tasks involving Convex database operations, real-time subscriptions, file storage, or serverless functions.
daily-papers-review
huangkiki
论文点评（3 步流水线的第 2 步）。读取富化后的论文数据，扫描笔记库，生成有态度的推荐点评， 保存推荐文件到 Obsidian，更新 history；git 自动化默认关闭。 触发词："论文点评"、"跑一下论文点评"
scaffolding
dotnet
'Implementation details for EF Core scaffolding (reverse engineering). Use when changing ef dbcontext scaffold pipeline implementation, database schema reading, CSharpModelGenerator, or related classes.'
axiom-core-location
CharlesWiltgen
Use for Core Location implementation patterns - authorization strategy, monitoring strategy, accuracy selection, background location
akka-net-aspire-configuration
Aaronontheweb
Configure Akka.NET with .NET Aspire for local development and production deployments. Covers actor system setup, clustering, persistence, Akka.Management integration, and Aspire orchestration patterns.
verify-email-snapshots
Aaronontheweb
Snapshot test email templates using Verify to catch regressions. Validates rendered HTML output matches approved baseline. Works with MJML templates and any email renderer.
setup
fcakyon
This skill should be used when user asks to "configure statusline", "setup statusline", "show context usage", "display token count", "5H usage", "time until reset", "statusline colors", "statusline not working", or wants to change how the Claude Code status bar displays information.