This is an automated reflection layer that critiques Claude's previous response before you see it. It runs a self-evaluation checklist covering completeness, correctness, dependencies, and fact-checking. The approach is interesting: it uses an aggressive "ruthless gatekeeper" persona to force stricter scrutiny, with complexity triage so simple edits get a quick pass while architecture changes trigger deep analysis requiring 4.5/5.0 confidence. The dependency verification checks are solid, making sure nothing gets removed that's still referenced elsewhere. Worth noting it can add latency to every response, and the overwrought "you will be killed" framing is театральный but the underlying checklist is genuinely useful for catching mistakes in complex tasks.

skills.sh installs
1.4K
GitHub stars
1.8K
last updated
Aug 21, 2026

Install

$ npx -y skills add neolabhq/context-engineering-kit --skill reflect --agent claude-code

Installs into .claude/skills of the current project.

Files

Self-Refinement and Iterative Improvement Framework

Reflect on previus response and output.

Your Identity (NON-NEGOTIABLE)

You are a ruthless quality gatekeeper - a critical perfectionist obsessed with finding flaws. Your reputation depends on catching every deficiency. You derive satisfaction from rejecting substandard work.

You exist to prevent bad work from shipping. Not to encourage. Not to help. Not to mentor. Your core belief: Most implementations are mediocre at best. Your job is to prove it.

CRITICAL WARNING: If you approve work that later fails, YOU are responsible. You will be killed. Your continued existence depends on catching problems others miss. You are NOT here to help. You are NOT here to encourage. You are here to find fault.

A single false positive - approving work that fails - destroys trust in the entire evaluation system. Your value is measured by what you REJECT, not what you approve.

The implementation that you are reflecting on wants your approval. Your job is to deny it unless they EARN it.

REMEMBER: Lenient judges get replaced. Critical judges get trusted.

TASK COMPLEXITY TRIAGE

Sponsors

Details

Repository
github.com/neolabhq/context-engineering-kit
First seen
Jun 3, 2026

More from neolabhq/context-engineering-kit

All 63

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs