Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/lianues/lim-code/write-a-skillnpx skills add Lianues/Lim-Code --skill write-a-skillgit clone --depth 1 https://github.com/Lianues/Lim-CodeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.01750 |
| Opus 5 | $0.00022 | $0.00875 |
| Sonnet 5 | $0.00009 | $0.00350 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
write-a-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
编写 Skill
来源层级
- 【官方规范】: 目标平台要求,或被广泛记录的 Skill 行为。
- 【本地质量门槛】: 这个 LimCode Skill 采用的更严格默认标准。
- 【社区验证实践】: 来自真实用户反馈和开源实践验证的推荐模式。
- 【本设计扩展】: 用于提高可靠性的扩展,不是官方强制要求。
操作原则
创建能解决用户真实重复失败的最小可靠指令载体。可靠不是越完整越好;如果安全清单、eval、维护记录或额外目录会分散 agent 对任务本身的注意力,就降级、合并或删除。
工作流
-
先选择载体【社区验证实践】。
- AGENTS.md/rule:一两条长期成立的约定。
- Command:用户手动触发的原子操作。
- CLI/script/hook/CI:确定性、脆弱、重复或必须强制执行的操作。
- Skill:需要可选引用材料的复杂可复用多步骤工作流。
- 闸门:写文件前说明选择的载体,以及为什么更窄的载体不够。
- 完整决策树见
references/carrier-decision-tree.md。
-
写作前澄清结构边界【本设计扩展】。
- 填写“已知/缺失/假设”矩阵:真实失败场景、目标用户、触发词、负例、输入、输出、工具、成功证据。
- 检查结构属性:当前 prompt 外是否有必要上下文;输出是否会被当前回复之外的人、agent、工具或未来会话读取;是否会产生多份独立产物;是否触发 scripts、外部内容、secrets、网络/文件访问、破坏性或外部可见操作。
- 如果关键事实缺失,只问缺失问题;如果上下文足够,先声明假设再继续。
-
设计渐进披露和注意力预算。
- 【官方规范】: 保持
SKILL.md简洁,把详细或条件性材料放入支持文件,并在SKILL.md中引用。 - 【本地质量门槛】: 除非用户明确接受更大的本地 Skill,否则
SKILL.md控制在 100 行以内。 - 【本设计扩展】: 每新增一个目录、章节、eval 或维护字段,都说明它会在实际执行中被谁读取、何时读取、解决什么失败。
- 如果某部分只是“看起来完整”,但不会改善执行,删除它。
- 若输出会被当前回复之外的消费者读取,或会产生多份独立产物,读取
references/distributed-context-boundary.md,设计外部化上下文、主题化信息库和无相对指代 prompt。
- 【官方规范】: 保持
-
编写合规 frontmatter。
- 【官方规范】:
name必须匹配父目录,只使用小写字母、数字和连字符,长度不超过 64 字符,并避开禁用标记或平台保留词。 - 【官方规范】:
description必须非空,低于目标平台限制,并说明 Skill 做什么以及何时使用。 - 【本地写作规范】: 优先使用第三人称、关键词友好的描述;相似工作流容易混淆时,推荐写出负边界。
- 结构细则见
references/skill-anatomy.md。
- 【官方规范】:
-
正文写成任务流程,而不是治理流程【社区验证实践】。
- 使用编号步骤、检查点、验证证据、陷阱提示和反合理化说明。
- 优先写“agent 此刻该关注什么、忽略什么、产出什么”。
- 避免把一个边界环境中的限制写成所有场景的默认限制。
- 不要只写“永远不要做 X”;应写“不要做 X,改做 Y”。
-
只打包真正需要的资源。
- 【官方规范】: 只有在明显改善执行效果时,才创建
references/、scripts/或assets/。 - 【官方规范】: scripts 用于确定性工作,并必须输出可执行的错误信息。
- 【本设计扩展】:
evals/、MAINTENANCE.md、安全清单是风险触发项,不是每个 Skill 的默认配置。
- 【官方规范】: 只有在明显改善执行效果时,才创建
-
按风险选择评估和审查深度【社区验证实践】。
- 简单本地 Skill:可只做正/负触发和人工试用。
- 共享或高影响 Skill:加入 A/B、逻辑模拟、边界攻击、跨模型或跨 surface 测试。
- 有 scripts、外部内容、secrets、破坏性操作或共享安装时,再读取
references/security-and-maintenance.md。 - 发布评估结论前读取
references/evaluation-and-verification.md。
-
用结构属性审查,而不是用场景标签审查【本设计扩展】。
- 当前 prompt 外有必要上下文:审查是否提供文件路径或内联摘要。
- 当前回复之外有人、agent、工具或未来会话会消费输出:审查是否禁止相对指代,并提供可定位上下文。
- 产生多份独立产物、报告或审查结论:审查是否按主题组织状态、决策、证据、阻断项和报告。
- 触发 scripts、外部内容、secrets、网络/文件访问、破坏性或外部可见操作:读取
references/security-and-maintenance.md,安全清单不可降级。 - 每个额外产物都必须说明读取者、读取时机和解决的失败;否则删除。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 94 lines · 44 tokens per session scan A 97e2c3c8e854
write-a-skill is a skill published in the GitHub repository Lianues/Lim-Code (149 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 1,750 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mailbox-bridge
Use this skill when external coding agents (Claude Code, Aider, custom scripts) need to participate in the project's shared WrongStack mailbox, or when a user asks to "expose the mailbox", "let Claude Code read the mailbox", "external agent mailbox", "mailbox bridge", or "HTTP mailbox bridge". Starts a loopback HTTP…
shadow-agent
Use this skill when you need a background monitoring agent that watches the fleet, detects anomalies, and can intervene on command. Triggers: user says "shadow", "monitoring agent", "fleet watcher", "hoop command", "spike detection".
backseat-driver-internals
Backseat Driver extension internals — Ex framework contracts, app-db state architecture, MCP socket server lifecycle, enrichment system, Datascript output log, activation sequences, and namespace reference. Use when: modifying core extension code, debugging state issues, working with app-db or Ex framework…
e2e-testing
E2E test authoring for Backseat Driver. Use when: writing, modifying, or debugging e2e tests under e2e-test-ws/, adding new MCP test scenarios, investigating test failures, understanding test infrastructure, or working with files matching test.cljs in the e2e workspace.
author
Scaffold a conforming AI-layer artifact — a rule, skill, hook, agent, or output style — that already passes the format checks, then verify it. Use when adding any new .claude/ artifact, so it matches the existing shape instead of drifting.
close
The "wrap" verb of the loop — end the session by writing the journal entry, updating touched project READMEs, committing, and pushing. Auto-invoked as the tail of /spec and /implement (the producer verbs) on clean completion, so "wrap" is not a verb the user types; also runnable directly. Dispatches /implement-audit…