SKILL RADAR · GITHUB

Useful agent skills, ranked by real adoption.

Browse verified skills from public repositories. Compare what each skill does, package contents, install activity, and source evidence before adding it to your agent.

CATALOG SCOPE
VERIFIED
skills
10,772
repositories
1711
last synced
Sep 23, 2026
10,772 skills
neolabhq
Community

critique

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

decay

Manage evidence freshness by identifying stale decisions and providing governance actions

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

design-testing-strategy

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

do-and-judge

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

do-competitively

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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.

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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.

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

fix-tests

Systematically fix all failing tests after business logic changes or refactoring

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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.

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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.

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

implement-task

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

judge-with-debate

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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.

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

memorize

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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.

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

plan-do-check-act

Iterative PDCA cycle for systematic experimentation and continuous improvement

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

query

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

reflect

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

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

reset

Reset the FPF reasoning cycle to start fresh

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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.

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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.

installs
1
GitHub stars
1.7K
Updated
Aug 26
neolabhq
Community

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.

installs
1
GitHub stars
1.7K
Updated
Aug 26