Improve
Use after completing a task, before claiming done, before handoff, or when asked "what are some improvements?" Surfaces concrete suggestions grounded in session observations.
Install
npx skills add NeverSight/learn-skills.dev --skill improvegit clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git /tmp/learn-skills.dev
mkdir -p ~/.claude/skills
cp -r /tmp/learn-skills.dev/data/skills-md/0xbigboss/claude-code/improve ~/.claude/skills/improvePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Improve Structured improvement pass grounded in what was observed during this session. ## Principles (Always Active) - Every suggestion must cite a specific observation — file path, error seen, pattern noticed, or behavior verified. "I saw X" beats "common practice suggests Y." - Distinguish grounded suggestions (observed evidence) from speculative ones (general knowledge). Mark speculative suggestions explicitly. - Prioritize by impact to the user, not by ease of description. - Do not suggest improvements that would change public API contracts, auth boundaries, or data schemas without flagging as high-risk. - Simplicity is a feature. Do not suggest adding complexity unless it prevents a concrete problem observed in this session. ## When to Use - User asks "knowing what you know now, what are some improvements?" or similar - Before claiming done in a ralph loop (self-check) - Before generating a handoff - After completing a significant chunk of work - When reviewing code that was just written or modified ## When Not to Use - At the start of a session before meaningful work has been done - When the user explicitly asks to skip review and ship - For architectural redesigns (use spec/plan flow instead) ## Dimensions Analyze across these dimensions. Skip any dimension with nothing grounded to say. ### Correctness Error handling gaps, unhandled edge cases, type safety issues, race conditions, missing validation at system boundaries. ### Simplicity
Details
- Skill name
improve- Repository
- NeverSight/learn-skills.dev
- Path
data/skills-md/0xbigboss/claude-code/improve/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Improve skill do?
Use after completing a task, before claiming done, before handoff, or when asked "what are some improvements?" Surfaces concrete suggestions grounded in session observations.
How do I install the Improve skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add NeverSight/learn-skills.dev --skill improve. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Improve popular?
It lives in NeverSight/learn-skills.dev, which has 223 GitHub stars and 42 forks.
Related skills
Council
223NeverSight/learn-skills.dev
Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.
Megaeth Developer
223NeverSight/learn-skills.dev
End-to-end MegaETH development playbook (Feb 2026). Covers wallet operations, token swaps (Kyber Network), eth_sendRawTransactionSync (EIP-7966) for instant receipts, JSON-RPC batching, real-time mini-block subscriptions, storage-aware contract patterns (Solady RedBlackTreeLib), MegaEVM gas model, WebSocket keepalive, bridging from Ethereum, and debugging with mega-evme. Use when building on MegaETH, managing wallets, sending transactions, or deploying contracts.
Openclaw Stock Skill
223NeverSight/learn-skills.dev
使用 data.diemeng.chat 提供的接口查询股票日线、分钟线、财务指标等数据,支持 A 股等市场。
Ingfah
223NeverSight/learn-skills.dev
Answer questions about Ingfah (อิงฟ้า) from its bundled user guide (คู่มือ), write FAQ files for its knowledge base (คลังความรู้), and work with the Ingfah client platform through client API-key authenticated APIs. Use when the user asks anything about Ingfah — services, how to do something in the dashboard, telephony, onboarding, settings, billing, release notes — wants an FAQ or knowledge document for an AI Agent, asks to inspect or manage products, AI agents, chat sessions, tools, customer templates, outbound batches, or analytics, or reports something wrong in what they see (a bad call sum
Harness Engineering Zh
223NeverSight/learn-skills.dev
为 AI Agent 友好的代码库搭建和改进 Harness 工程(包括 AGENTS.md、docs/、Lint 规则、Eval 系统、项目级 Prompt 工程)。触发场景:为 AI Agent 设置新项目/空项目,创建 AGENTS.md 或 CLAUDE.md,关于 Harness 工程的问题,让 Agent 在代码库上更高效地工作。当用户感到沮丧或抱怨 Agent 质量时也会触发(例如:'Agent 总是无视规范'、'它从不听从指令'、'为什么它总是做错 X'、'Agent 坏了')— 因为 Agent 输出质量差几乎总是意味着 Harness 缺失,而不是模型问题。涵盖:Context 工程、架构约束、多 Agent 协作、评估、长运行任务 Harness 以及 Agent 质量问题诊断。
Introspect
223NeverSight/learn-skills.dev
Analyze Claude Code session logs - extract thinking blocks, tool usage stats, error patterns, debug trajectories. Triggers on: introspect, session logs, trajectory, analyze sessions, what went wrong, tool usage, thinking blocks, session history, my reasoning, past sessions, what did I do.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.