一键导入
refine-skill-design
Audit and refactor existing SKILLs to meet spec compliance, repository asset boundaries, tool adaptation requirements, and LLM best practices.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Audit and refactor existing SKILLs to meet spec compliance, repository asset boundaries, tool adaptation requirements, and LLM best practices.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Store, look up, or delete a personal credential (server SSH password, database password, website login, API key/token, certificate passphrase) in the macOS Keychain using a consistent <project>-<env>-<kind> naming scheme, and optionally record a pointer (never the secret itself) in the current project's Claude Code memory. Always use this skill whenever the user asks to save, store, remember, look up, rotate, or delete a password, API key, token, SSH credential, or database credential on this machine — even if they don't say "Keychain" or "security" explicitly, e.g. "save this database password so I don't lose it", "把这个数据库密码存一下", "记一条密钥", "这台服务器的密码帮我记下来", "what's the postgres password for staging again", "delete the old GitHub token from keychain". Do not use this for team-shared secret vaults, CI/CD secret injection, or anything that needs to sync across machines — those need a real secrets manager, not this skill.
Drain pending NATS messages from a producer contract via NATS MCP tools. Discovers the available NATS tool capabilities, selects exact-subject or wildcard mode from .cortex/nats.yaml, applies Tolerant Reader semantics, executes ack/nak/term decisions, and returns aggregated stats.
From inside a linked worktree, deliver the current feature branch into main — merge with --no-ff, push, and optionally clean up the worktree, all without leaving CWD.
After code changes, auto-detect the project's build system and local deployment method for a given directory, then build the project and restart its locally-deployed environment (Docker Compose / systemd / process manager). Never assumes — asks only when detection is ambiguous. Caches detected commands per project in .cortex/redeploy-local.yaml; re-invocations on the same project skip re-scanning until signal files change, the cache expires (30 days), or the skill version bumps.
From the main repo on the main branch, scan all linked worktrees and local branches, let the user multi-select, then merge --no-ff + push them sequentially and clean up succeeded worktrees together.
Generate an LLM agent test suite (golden cases, mock-LLM unit tests, evaluator harness) from an agent implementation and its agent-test contract. Use when an agent has no tests, or a contract exists but the test code is missing.
| name | refine-skill-design |
| description | Audit and refactor existing SKILLs to meet spec compliance, repository asset boundaries, tool adaptation requirements, and LLM best practices. |
| description_zh | 审计并重构既有 SKILL,使其符合规范、仓库资产边界、工具适配要求与 LLM 最佳实践。 |
| tags | ["writing","meta-skill","optimization"] |
| version | 1.5.0 |
| license | MIT |
| recommended_scope | user |
| metadata | {"author":"ai-cortex"} |
| triggers | ["refine skill","skill design","audit skill","skill refactor","skill compliance"] |
| input_schema | {"type":"document-artifact","description":"Existing SKILL.md file to audit and refactor"} |
| output_schema | {"type":"document-artifact","description":"Optimized SKILL written to source SKILL.md (default) or to temp/new path when user opts out; includes diff summary and version suggestion"} |
作为一项“元技能”,该技能审查并重构草稿形式的人工智能能力定义。它应用高级即时工程视角来提高逻辑稳健性、场景覆盖率和指令依从性,以便每项功能都满足LLM最佳实践。
首要目标:生成经过审查并重构的技能文档,以满足规范合规性、仓库资产边界和 LLM 最佳实践。
成功标准(必须满足所有要求):
AGENTS.md、术语定义、外部链接、语言和资产优先级规则验收测试:人工智能代理能否在不同的环境中一致地应用这种精炼的技能,而不会产生歧义?
本技能负责:
AGENTS.md 和本地术语定义本技能不负责:
转交点:当 SKILL 被细化并提供差异摘要时,移交给用户进行审查和版本控制提交。
description、tags、triggers 足以支持语义发现。范围:此技能用于审查并重构现有技能,而不是从头开始创建。要学习如何创建新技能、规划脚本/引用/资产或运行 init/package 脚本,请使用 Skills.sh 的“技能创建器”(例如 anthropics/skills)。
AGENTS.md 与 docs/architecture/terminology.md;不得默认抓取外部 HTTP/HTTPS 链接,除非上下文显式声明 allow_external_fetch=true。SKILL.md,并在输出中同时附上diff摘要与版本号建议,方便审阅和审核。规则:默认直接改进并覆盖原始SKILL.md,同时提供可审计的diff摘要与版本号建议;只有在用户明确要求“只生成精修草稿、不改源文件”时,才写入临时或新建精修文件。每次运行须在以下策略中二选一:
| 战略 | 路径模式 | 行为 |
|---|---|---|
| 直接覆盖(默认) | 技能/<技能名称>/SKILL.md | 直接覆盖源文件,保证前置事项版本已更新,且在产出中包含变更摘要,属于审计 |
| 固定温度(选择退出) | skills/<技能名称>/SKILL.refined.md | 在用户要求“不要改原文件,只给细化”时使用;每次运行覆盖相同的临时文件 |
| 每次运行新(选择退出) | skills/<技能名称>/SKILL.refined.YYYYMMDD.md | 在用户要求“为这次细化保留单独的文件”时使用;每次运行创建新的细化文件 |
用户覆盖:如果用户指定路径或策略,请遵守它。否则使用直接覆盖。
SKILL.md,但必须同步更新 frontmatter 的 version,并在输出中提供完整的变更摘要,确保可审计。SKILL.md,只能写入临时或新建精炼文件。不要做这些(其他技能可以处理它们):
generate-standard-readme;生成 AGENTS.md → 使用 generate-agent-entrydecontextualize-text何时停止并交接:
AGENTS.md、术语定义、外部链接和语言规则人工智能代理能否在不同的环境中一致地应用这种精炼的技能而不会产生歧义?
如果否:技能需要进一步完善。查看“行为”部分以确保清晰并添加更具体的说明。
如果是:细化已完成。向用户提供差异摘要和版本推荐。
名称:拼写检查 该技能检查拼写。 输入:多语言文本。 输出:更正后的文本。
名称:波兰语-文本-拼写 描述:多语言文档的上下文感知拼写和术语纠正。 标签:[写作、质量控制] 版本:1.1.0
技能:拼写和术语
目的:识别并修复低级拼写错误和术语不一致,而不改变作者的意图或语气
行为
- 检测语言。
- 如果文本较长,则构建术语列表。
- 区分“打字错误”和“故意风格”。
限制:不要更改专有名词或特定缩写,除非明显错误