Revisió de codi
Revisió i anàlisi automatitzades del codi
greploop
greptileai
Iteratively improves a PR until Greptile gives it a 5/5 confidence score with zero unresolved comments. Triggers Greptile review, fixes all actionable comments, pushes, re-triggers review, and repeats. Use when the user wants to fully optimize a PR against Greptile's code review standards.
dyad:lint
dyad-sh
Run pre-commit checks including formatting, linting, and type-checking, and fix any errors.
sdr-outbound-rules
sachacoldiq
SDR outbound writing rules, 8 allowed messaging frameworks, and tone guidelines by offer type. Use when training SDRs, creating messaging guidelines, or standardizing outbound quality.
check-pr
greptileai
Checks a GitHub pull request for unresolved review comments, failing status checks, and incomplete PR descriptions. Waits for pending checks to complete, categorizes issues as actionable or informational, and optionally fixes and resolves them. Use when the user wants to check a PR, address review feedback, or prepare a PR for merge.
audit-agents
melodic-software
Audit Claude Code subagents for quality, compliance, and maintainability. Use after creating or modifying agents, before releases, or for periodic quality checks.
audit-hooks
melodic-software
Audit Claude Code hooks for quality, compliance, and maintainability. Use after creating hooks, before releases, or for periodic quality checks.
learn
langwatch
"Learn from mistakes by updating AGENTS.md. Use when a mistake was made that should be prevented in future sessions."
audit-rules
melodic-software
Audit Claude Code rule files for quality and compliance. Use when creating or validating .claude/rules/*.md files, or troubleshooting rule loading issues.
audit-memory
melodic-software
Audit Claude Code CLAUDE.md memory files for quality, compliance, and organization. Use to validate import syntax, detect circular imports, and check hierarchy compliance.
challenge
langwatch
"Stress-test an architecture proposal, plan, or technical idea. Invokes the devils-advocate agent to find weaknesses before you commit."
orchestrate
langwatch
"Orchestration mode for implementation tasks. Manages the plan → code → review loop. Use /orchestrate <requirements> or let /implement invoke it."
test-review
langwatch
"Review specs and tests for pyramid placement and quality."
watch-ci
langwatch
"Watch CI for the current branch's PR. Blocks until CI completes, then fixes failures or addresses review comments. Loops until green."
security-review
LangConfig
"Comprehensive security code review covering OWASP Top 10, authentication, authorization, and secure coding practices. Use when reviewing code for vulnerabilities or implementing security features."
ui-review
srbhr
Review UI changes against Swiss International Style design system. Checks colors, typography, borders, shadows, spacing, and anti-patterns. Use before committing any frontend UI changes.
Accessibility Generator
rshankras
Human Interface Guidelines: Accessibility
analyze-local-telemetry
garden-co
Use when the user wants to analyze OTel traces/logs/metrics captured locally — inspect spans, find slow operations, correlate logs with traces, sanity-check metrics. Talks SQL to dev/local-telemetry over HTTP via curl. Trigger phrases include "look at the traces", "what spans did X emit", "why was this slow", "any errors in the logs", "check the metrics".
openwork-debug
different-ai
Debug OpenWork sidecars, config, and audit trail
browser-setup-devtools
different-ai
Guide users through browser automation setup using Chrome DevTools MCP as the primary path and the OpenCode browser extension as a fallback. Use when the user asks to set up browser automation, Chrome DevTools MCP, browser MCP, browser extension, or runs the browser-setup command.
gemini-peer-review
jezweb
"Get a second opinion from Gemini on code, architecture, debugging, or security. Uses gemini-coach CLI with AI-to-AI prompting for clear, actionable analysis. Trigger with 'ask gemini', 'gemini review', 'second opinion', 'peer review', or 'consult gemini'."
context-manager
jezweb
"Audit and manage the full project context landscape: CLAUDE.md memory hierarchy, project documentation, markdown footprint, and content overlap. Detects project type, scores quality, flags stale docs, and reports total context cost. Trigger with 'audit context', 'audit memory', 'update CLAUDE.md', 'restructure memory', 'session capture', 'check project docs', 'markdown footprint', or 'what docs does this project need'."
github-release
jezweb
"Prepare and publish GitHub releases. Sanitizes code for public release (secrets scan, personal artifacts, LICENSE/README validation), creates version tags, and publishes via gh CLI. Trigger with 'release', 'publish', 'open source', 'prepare for release', 'create release', or 'github release'."
github-release
jezweb
"Prepare and publish GitHub releases. Sanitizes code for public release (secrets scan, personal artifacts, LICENSE/README validation), creates version tags, and publishes via gh CLI. Trigger with 'release', 'publish', 'open source', 'prepare for release', 'create release', or 'github release'."
critical-thinking
tronghieu
Audit the reasoning of a document or argument (memo, proposal, investment analysis, board paper, article, the user's own draft): claims, evidence, unstated assumptions, logical gaps, fallacies, and what would falsify it, each anchored to quoted text. Use whenever the user wants reasoning examined, in any language ("audit this argument", "is this analysis sound", "poke holes in this proposal", "review the logic of my draft"; Vietnamese "phản biện giúp tôi", "soi lập luận này", "tài liệu này có lỗ hổng gì", "góp ý bản nháp của tôi"), even when they never say "critical thinking". Also use when the user drops a document and asks whether to trust or act on it, or asks to see their reasoning profile. Not for company-level strategic bets (strategy-board) or learning a topic through dialogue (socratic-questor).