drn/dots - Página 2

learn

Alias for /improve — improve skills, capture context & knowledge. Use for skill iteration, capturing learnings, or upgrading agent context.

Idioma del texto original: inglés

combine-prs

Compare two competing PRs implementing the same feature, identify strengths of each, and combine the best parts into a single branch. Use when comparing PRs, combining implementations, cherry-picking between PRs, or resolving competing approaches.

Idioma del texto original: inglés

polish

Analyze codebase for code smells and refactor to drastically improve code quality. Expert in clean code, SOLID principles, Ruby patterns, service objects, and refactoring. Use for code quality audits, refactoring sessions, and cleaning up technical debt.

Idioma del texto original: inglés

email

Search and read Gmail messages. Use when looking up emails, reading email threads, or checking inbox labels.

Idioma del texto original: inglés

loop

Run a prompt on a recurring interval using a blocking sleep loop. Use for polling CI, babysitting deploys, monitoring logs, periodic checks, or scheduled task execution.

Idioma del texto original: inglés

slack

Query Slack channels, search messages, and fetch user information. Use when reading Slack data, checking channel history, searching messages, or looking up users.

Idioma del texto original: inglés

deploy

Deploy latest master to production with a version tag. Use when releasing to production or tagging a deploy.

Idioma del texto original: inglés

prompt-summary

Summarize the prompts used in the current conversation as a numbered list. Use when the user wants to see the prompt chain, review their prompts, or share the sequence of prompts that produced a result.

Idioma del texto original: inglés

contest

Competing implementations with judge evaluation. Use when comparing multiple approaches, picking the best solution, or running a bake-off.

Idioma del texto original: inglés

perf

Before/after performance benchmarking comparing current branch against base, with statistical analysis. Use for benchmarking, profiling, or measuring performance impact.

Idioma del texto original: inglés

rebase

Rebase current branch onto latest upstream default branch and force-push to update PR. Use when updating a branch, rebasing onto main, or resolving conflicts.

Idioma del texto original: inglés

release

Create a versioned release with changelog generation, git tag, and GitHub release. Use for creating releases, tagging versions, or publishing changelogs.

Idioma del texto original: inglés

equip

Analyze a spec, PRD, or codebase to identify missing skills and agents, propose them, then write them. Use for skill gap analysis, agent gap analysis, bootstrapping agent capabilities from a spec, or equipping a project with skills.

Idioma del texto original: inglés

bisect

Find which commit introduced a bug using git bisect with automatic test verification. Use when tracking down which commit introduced a bug.

Idioma del texto original: inglés

changelog

Generate an intelligent changelog from recent commits. Use for release notes, version history, or documenting what changed.

Idioma del texto original: inglés

debug

Multi-agent competing hypotheses debugging. Use when stuck on a bug, need root cause analysis, or want competing debug theories.

Idioma del texto original: inglés

deps

Audit outdated dependencies, check for vulnerabilities, and upgrade with test verification. Use for dependency audits, security checks, or upgrading packages.

Idioma del texto original: inglés

devils-advocate

Execute the /devils-advocate workflow shared across Codex, Claude Code, and Copilot in this repository. Use when you want to stress-test ideas, challenge assumptions, or play devil's advocate.

Idioma del texto original: inglés

explore

Multi-agent parallel research with peer-challenged synthesis. Use for deep research, codebase exploration, or investigating how something works.

Idioma del texto original: inglés

guard

Pre-commit safety check for secrets, security antipatterns, and test breakage. Use for pre-commit checks, secret scanning, or verifying test safety.

Idioma del texto original: inglés

knowledge

Initialize or update a project knowledge base for durable cross-session knowledge capture. Use for setting up or updating project knowledge bases.

Idioma del texto original: inglés

migrate

Multi-agent codebase migration with module ownership. Use for large refactors, API upgrades, framework migrations, or bulk code changes.

Idioma del texto original: inglés

prune

Clean up merged and stale git branches, prune old local and remote branches safely. Use for cleaning up old branches or pruning stale remotes.

Idioma del texto original: inglés

retro

Run a structured retrospective or post-incident review with optional knowledge base capture. Use for running retrospectives, postmortems, or incident reviews.

Idioma del texto original: inglés

scaffold

Bootstrap new components, files, or modules matching existing repo conventions and patterns. Use for creating new files, components, or modules that follow repo patterns.

Idioma del texto original: inglés

spike

Time-boxed technical investigation with structured findings document, tech spike, research spike, proof of concept. Use for time-boxed research, technical spikes, or proof of concept work.

Idioma del texto original: inglés

standup

Generate a daily standup summary from recent git activity, commits, open PRs, and current work in progress. Use for daily standup prep or summarizing recent work.

Idioma del texto original: inglés

swarm

Conductor-native multi-agent orchestration with real-time progress. Use for parallel agent swarm, multi-agent tasks, agent team, team coordination, parallel workers.

Idioma del texto original: inglés

prioritize

RICE-scored backlog prioritization. Use for sprint planning, feature prioritization, or backlog grooming.

Idioma del texto original: inglés

ci-investigate

Investigate flaky CI failures across multiple workflow runs to identify patterns, categorize root causes, and propose fixes. Use when asked to investigate CI failures, find flaky tests, diagnose test flakiness, or understand why CI is failing repeatedly.

Idioma del texto original: inglés