Depuració
Detecció i correcció de problemes i anàlisi d’errors
model-router
nguyenthienthanh
"Automatically select optimal Claude model (Haiku/Sonnet/Opus) based on task complexity to reduce costs while maintaining quality."
linear-create
Finesssee
Create Linear issues. Use when creating bugs, tasks, or feature requests.
test
popmechanic
Self-contained test automation — invoke directly, do not decompose. End-to-end integration test that assembles a fixture, deploys Connect + Cloudflare, and presents a live URL for browser verification.
go-errors
peixotorms
Use when handling errors in Go code. Covers error interface, fmt.Errorf, %w verb, unwrap, error chain, error wrapping, errors.Is, errors.As, sentinel errors, custom error type, panic and recover, error handling strategy, error handling patterns, stack trace, pkg/errors, error group, errgroup, multi-error, validation errors, in-band errors, error type switch, and common error handling mistakes.
git-commit-helper
Crumbgrabber
Generate descriptive commit messages by analyzing git diffs. Use when
monitoring-observability
1Mangesh1
Observability patterns and monitoring best practices. Use when user asks to "set up monitoring", "structured logging", "distributed tracing", "metrics collection", "observability", "APM setup", "log aggregation", "metrics dashboards", "error tracking", "performance monitoring", or mentions observability stack and monitoring strategy.
git-conventions
vendeesign
"Guide automatique pour les opérations git. Activer quand Claude exécute des commandes git (commit, branch, push, merge, rebase, PR) en dehors de /codebloom:push. Couvre : conventional commits, nommage de branches, messages de PR, et garde-fous contre les opérations destructives. Ne pas charger si /codebloom:push est active (elle intègre déjà ces conventions)."
review-plan
benredmond
Advisory plan review - validates plan correctness and identifies gaps before implementation. Works on any task with research and plan sections.
rust-iot
peixotorms
Use when building IoT applications, sensor networks, or edge devices in Rust. Covers telemetry, protocol buffers, protobuf, CoAP, BLE, Bluetooth, serial communication, GPIO, edge computing, OTA update, firmware, data pipeline, MQTT with rumqttc, offline-first store-and-forward, exponential backoff retry, power management, TLS security, and telemetry publishing.
condition-based-waiting
Crumbgrabber
Use when tests have race conditions, timing dependencies, or inconsistent
subagent-driven-development
Crumbgrabber
Use when executing implementation plans with independent tasks in the
session-summary
ProjAnvil
会话总结技能，用于总结当前会话的上下文，包括已完成的任务、技术决策和下一步计划。使用此技能生成交接文档，以便在不丢失关键上下文的情况下开始新会话。
code-review
1Mangesh1
Code review checklists, PR review patterns, and feedback templates. Use when user asks to "review this code", "code review checklist", "PR review template", "review best practices", "write review feedback", or any code review tasks.
fix
TakaGoto
"Diagnose and fix your RAG pipeline — skip the teaching, get to the answer"
break-it
TakaGoto
"Find the bug — learn RAG by debugging intentionally broken pipelines"
code-review
TakaGoto
"Get expert feedback on your RAG code"
optimizing-performance
rileyhilliard
Measure-first performance optimization that balances gains against complexity. Use when addressing slow code, profiling issues, or evaluating optimization trade-offs.
verification-before-completion
rileyhilliard
Run verification commands before claiming work is complete or fixed. Use before asserting any task is done, bug is fixed, tests pass, or feature works.
reading-logs
rileyhilliard
Analyzes logs efficiently through targeted search and iterative refinement. Use when investigating errors, debugging incidents, or analyzing patterns in application logs.
post-mortem
rileyhilliard
Review a completed session to extract actionable improvements. Identifies DX friction, documentation gaps, architectural confusion, anti-patterns, process failures, and skill/config improvements. Uses progressive disclosure for targeted investigation types.
dev-debug
edwinhu
"This skill should be used when the user asks to 'debug', 'fix bug', 'investigate error', 'why is it broken', 'trace root cause', 'find the bug', or needs systematic debugging and course-correction with verification-driven methodology using ralph loops."
ds-fix
edwinhu
"This skill should be used when the user asks to 'fix analysis', 'wrong results', 'notebook error', 'reviewer feedback', 'data changed', 'debug notebook', or needs mid-analysis course-correction for wrong results, notebook errors, or data changes."
refactoring-code
rileyhilliard
Improves code structure while preserving behavior through test verification. Use when cleaning up code, reducing duplication, simplifying complexity, or reorganizing modules.
marimo
edwinhu
This skill should be used when the user asks to "use marimo", "create a marimo notebook", "debug a marimo notebook", "inspect cells", "understand reactive execution", "fix marimo errors", "convert from jupyter to marimo", or works with marimo reactive Python notebooks.