rube-de
UserA curated collection of Claude Code plugins: multi-agent dev team, AI council code reviews, and project management
Categories
Indexed Skills (26)
cdt
Multi-agent development workflow using Agent Teams. Supports five modes: plan (architect teammate + PM teammate debate → plan.md), dev (developer teammate + code-tester teammate + qa-tester teammate + reviewer teammate iterate → code), full (plan → approval gate → dev), auto (plan → dev, no gate), and bugfix (tester + developer + reviewer TDD triad → fix + PR). Use when tasks benefit from collaborative agent teammates with peer messaging.
ci-review
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting. Runs specialized review agents, scores findings, and submits a GitHub PR review via `post-review.sh`. Always executes `post-review.sh` to submit a review on every run (including zero-findings runs). Triggers: /ci-review, review PR, CI code review, automated PR review. Use: /ci-review <PR#> [focus text] [--full|--lean|--single] [--agent] [--model sonnet|opus] [--min-severity <level>]
council
Consult external AI council (Gemini 3.7 Flash, Codex, GLM-5.3, Kimi) for thorough reviews and consensus-driven decisions. Use ONLY when explicitly invoked with "/council" or when user says "consult the council", "invoke council", or "council review". Do NOT auto-trigger on generic phrases like "thorough review".
dlc
Dev Life Cycle quality gates: run security scans, code quality checks, performance analysis, test coverage, and PR review compliance. Routes to domain-specific sub-skills or runs all checks in sequence.
doppler
Manage secrets with Doppler: CLI operations, project/config/environment management, secrets injection, CI/CD integrations, and security best practices.
feature-discovery
Discover what to build next across a whole product: fan out parallel agents to map the current repo into a feature inventory, research competitors, ideate across seven value lenses, dedup and shortlist, spec and adversarially validate the winners, then synthesize a ranked roadmap. Distinct from brainstorm, which goes deep on one feature - this goes wide and returns a ranked roadmap of many candidates. Heavyweight: runs a deterministic multi-agent Workflow of roughly 35-40 sub-agents at exhaustive depth. Use when the user asks what to build next, wants feature ideas, a roadmap or gap analysis, a competitor analysis, "what are we missing", or "where can we add value". For a casual "give me three ideas", answer directly instead of invoking this.
jules-review
Review Jules (Google AI agent) pull requests using AI council. Supports -quick flag for lightweight reviews via parallel triage.
oasis-dev
Help developers build on Oasis Network: Sapphire confidential EVM, ROFL off-chain apps, CLI operations, SDK patterns (Rust, Go, TypeScript, Python), and ParaTime development.
brainstorm
You MUST use this skill before /pm when work is ambiguous, scope is unclear, or multiple approaches exist. Explores problem space, proposes 2-3 approaches with trade-offs, and produces an approved spec document that feeds into both issue creation (/pm) and implementation planning (/cdt). Triggers: brainstorm, explore idea, think through, design approach, what should we build, explore options, weigh approaches, compare solutions, needs help deciding between alternatives.
next
Triage open GitHub issues and recommend what to work on next. Builds a dependency graph from issue bodies, detects circular dependencies, ranks unblocked issues by weighted scoring (blocks-others, priority, type, age, milestone), and presents top candidates for interactive selection. Triggers: what should I work on next, triage backlog, next issue, pick next task, recommend issue, prioritize issues.
pm
Project manager for GitHub issues: brainstorm design approaches, create structured issues optimized for LLM agent teams, triage and recommend what to work on next, audit and clean up stale issues, or deep-validate a single issue against the codebase. Triggers: create issue, plan work, new task, project manager, write ticket, draft issue, plan feature, plan project, start project, create ticket, review issue, brainstorm, explore idea, think through, pm.
review
Deep-validate a single GitHub issue against the codebase: cross-reference file paths, detect already-implemented features, check for related PRs, verify dependencies, and deliver a structured verdict with recommended action. Triggers: review issue, validate issue, check issue status, is this issue still needed, issue review.
update
Audit open GitHub issues for staleness, orphaned blockers, missing labels, codebase drift, and already-implemented features. Categorizes issues into close-candidates, update-needed, needs-triage, stale, and healthy. Supports bulk and individual remediation via interactive approval. Triggers: audit issues, clean up issues, update stale issues, issue hygiene, backlog cleanup, prune issues.
temporal
Help developers use Temporal for durable execution workflows. Covers CLI commands, SDK patterns (Go, TypeScript, Python, Java), workflow orchestration, and architectural decisions.
council-reference
Council review reference data — expertise weights, structured response format, scoring thresholds, and false positive taxonomy. Background knowledge for council subagents.
review-plan
Use after writing implementation plans (superpowers:writing-plans output) or when the user says "review plan", "check my plan", "sanity check the plan", "validate plan", "review before executing". Also use before superpowers:executing-plans if a plan has not been reviewed yet.
babysit
PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.
git-ops
Git hygiene: clean up merged branches, prune stale remotes, and verify repository state.
perf
Performance analysis: bundle size checks, profiling, benchmarks, and algorithmic complexity review. Identifies performance-sensitive areas and creates a structured GitHub issue.
pr-check
PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.
pr-validity
PR validity analysis: fetch PR diff, extract new code additions, search existing codebase for duplicate or overlapping implementations, classify changes, and create a structured GitHub issue.
quality
Code quality check: linting, complexity analysis, duplication detection, and dead code identification. Detects project linting config, runs appropriate tools, and creates a structured GitHub issue.
security
Security scan: dependency audits, SAST analysis, and secret detection. Detects project type, runs available security tools, classifies findings by severity, and creates a structured GitHub issue.
update-review-checklist
Audit review checklist for a repo: cluster recurring review-comment themes across merged PRs in a window, diff against docs/code-review-checklist.md, and open a PR proposing new entries with PR traceability. Designed for /schedule monthly cadence. Pass --dry-run to print clusters without opening a PR. Trigger phrases: audit review checklist, update review checklist, cluster PR findings.
develop
Use when implementing GitHub issues for skill or plugin development through TDD-governed phases with iterative planning, implementation, and review loops. Use this whenever the issue involves SKILL.md files, agent prompts, hook scripts, or plugin workflows.
plugin-dev
Validate plugin SKILL.md frontmatter and audit hook scripts for silent failures. Run validation to check all plugins pass schema, source path, and frontmatter checks. Run hook audit to detect unhandled errors in shell and Python scripts.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.