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-codeInstalls 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- Write Concisely1.4K
- Kaizen1.4K
- Multi Agent Patterns1.4K
- Memorize1.3K
- Update Docs1.3K
- Critique1.3K
- Brainstorm1.3K
- Judge With Debate1.3K
- Root Cause Tracing1.3K
- Agent Evaluation1.3K
- Subagent Driven Development1.3K
- Review Local Changes1.3K
- Test Driven Development1.3K
- Plan Task1.3K
- Judge1.3K
- Why1.3K
- Do And Judge1.3K
- Setup Serena Mcp1.3K
- Implement Task1.3K
- Write Tests1.3K
- Test Prompt1.3K
- Analyse Problem1.3K
- Do In Steps1.3K
- Create Rule1.3K
