RADAR DES SKILLS · GITHUB

Des Agent Skills utiles, classés selon leur usage réel.

Comparez les Skills vérifiés par fonction, contenu, installations et fiabilité de la source avant de les ajouter.

PÉRIMÈTRE
VÉRIFIÉ
Skills
10 772
dépôts
1711
dernière synchronisation
23 sept. 2026
10 772 Skills
neolabhq
Communauté

critique

Comprehensive multi-perspective review using specialized judges with debate and consensus building

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

decay

Manage evidence freshness by identifying stale decisions and providing governance actions

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

design-testing-strategy

Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

do-and-judge

Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

do-competitively

Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

do-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.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

do-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.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

fix-tests

Systematically fix all failing tests after business logic changes or refactoring

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

git-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.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

git-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.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

implement-task

Implement a task step by step with automated LLM-as-Judge verification at the end of each phase

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

judge-with-debate

Evaluate solutions through multi-round debate between independent judges until consensus

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

launch-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

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

load-pr-comments

Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/.md for parallel agents to fix.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

memorize

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

multi-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.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

plan-do-check-act

Iterative PDCA cycle for systematic experimentation and continuous improvement

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

plan-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

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

query

Search the FPF knowledge base and display hypothesis details with assurance information

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

reflect

Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

reset

Reset the FPF reasoning cycle to start fresh

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

resolve-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.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

review-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.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août
neolabhq
Communauté

review-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.

installations
1
GitHub Stars
1,7 k
Mis à jour
26 août