RADAR DE SKILLS · GITHUB
Agent Skills úteis, classificados pelo uso real.
Compare Skills verificados por finalidade, conteúdo do pacote, instalações e evidências da fonte antes de adicioná-los.
- ESCOPO DO CATÁLOGO
- VERIFICADO
- Skills
- 10.772
- repositórios
- 1711
- última sincronização
- 23 de set. de 2026
neolabhqcritique
Comprehensive multi-perspective review using specialized judges with debate and consensus building
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqdecay
Manage evidence freshness by identifying stale decisions and providing governance actions
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqdesign-testing-strategy
Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqdo-and-judge
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqdo-competitively
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqdo-in-parallel
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqdo-in-steps
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqfix-tests
Systematically fix all failing tests after business logic changes or refactoring
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqgit-notes
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqgit-worktrees
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqimplement-task
Implement a task step by step with automated LLM-as-Judge verification at the end of each phase
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqjudge-with-debate
Evaluate solutions through multi-round debate between independent judges until consensus
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqlaunch-sub-agent
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqload-pr-comments
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/.md for parallel agents to fix.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqmemorize
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqmulti-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqplan-do-check-act
Iterative PDCA cycle for systematic experimentation and continuous improvement
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqplan-task
Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verifiable phases
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqquery
Search the FPF knowledge base and display hypothesis details with assurance information
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqreflect
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqreset
Reset the FPF reasoning cycle to start fresh
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqresolve-fixed-pr-comments
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqreview-local-changes
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.
neolabhqreview-pr
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.
- instalações
- 1
- GitHub Stars
- 1,7 mil
- Atualizado
- 26 de ago.