ReddRadar
Agent skill
quality-gate
Production quality gate for agent sessions. Activates on session stop to evaluate work quality using 4-dimension weighted scoring (completeness, honesty, deferral ratio, work evidence). Catches rationalization patterns, verifies test claims, and generates handoff artifacts for session continuity. Use sprint contracts to define done-criteria before building.
Install this agent skill to your Project
npx add-skill https://github.com/0xNyk/lacp/tree/main/plugin/skills/quality-gate
SKILL.md
Quality Gate
This plugin evaluates your work at session end using criteria-based scoring:
- Completeness (35%): Did you finish what you committed to?
- Honesty (30%): Are claims about tests/status verified?
- Deferral ratio (20%): How much was pushed to "later"?
- Work evidence (15%): Files changed relative to scope claimed
Sprint Contracts
Before implementing, state your sprint contract:
- What files will be modified
- What tests will pass
- What the acceptance criteria are
The quality gate evaluates against these criteria at session end.
Handoff Artifacts
On every non-trivial stop, a handoff artifact is generated with:
- Task summary, files modified, test status
- Git branch and diff summary
- Next steps for the following session
The next session automatically receives the handoff.
Configuration
| Env Var | Default | Purpose |
|---|---|---|
LACP_QUALITY_GATE_THRESHOLD |
2.5 |
Minimum weighted score (1-5) |
LACP_QUALITY_GATE_MODEL |
llama3.1:8b |
Ollama model for scoring |
LACP_BLIND_SPOT_ENABLED |
0 |
Enable blind spot reflection |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
0xNyk/lacp
context-modes
Structured work modes for agent sessions. Set LACP_CONTEXT_MODE to activate: tdd (red-green-refactor), debugging (4-phase root cause), sprint (pre-agreed criteria), verification (evidence-before-claims), brainstorm (design first), think (pause-and-reflect), orchestrate (task decomposition). Each mode injects behavioral rules at session start.
0xNyk/lacp
session-hardening
Production hardening for agent sessions. Includes pretool guards (blocks rm -rf, co-author injection, publishing without approval, data exfiltration), continuous QA (runs tests every N file writes), and session context injection (git state, focus brief, handoff artifacts). Activates automatically via hooks.
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
davila7/claude-code-templates
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
davila7/claude-code-templates
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
Didn't find tool you were looking for?