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 skills add flanliulf/SpecLite --skill speclite-write-opensource-docsgit clone --depth 1 https://github.com/flanliulf/SpecLiteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/flanliulf/speclite/speclite-write-opensource-docs)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-write-opensource-docs"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-write-opensource-docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-write-opensource-docs"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-write-opensource-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00121 | $0.01114 |
| Opus 5 | $0.00060 | $0.00557 |
| Sonnet 5 | $0.00024 | $0.00223 |
| Haiku 4.5 | $0.00012 | $0.00111 |
Grade A, and why
speclite-write-opensource-docs 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 6d ago.
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.
What it actually says
[Overview(技能说明)]
本 Skill 用于编写和维护开源项目的 docs/ 目录文档。它把 docs/ 视为面向 GitHub、npm 和未来官网站点的公开文档源,按 Diataxis 区分 Tutorials、How-To、Explanation、Reference 和 Glossary,并保持 README、package surface、索引和渲染约束一致。
[Core Capabilities(核心能力)]
- Repo 证据审计:先读取真实 docs/、README、package metadata、CLI/API surface 和现有规范;项目规范缺失时使用内置 style guide baseline。
- Diataxis 分类:将请求归入 tutorial、how-to、explanation、reference 或 glossary,并按对应结构写作。
- 目录脚手架:创建或补齐 docs/tutorials、docs/how-to、docs/explanation、docs/reference、docs/reference/glossary 等结构。
- GitHub/npm 友好写作:使用 CommonMark / GitHub Flavored Markdown,不生成 Starlight-only admonition 语法。
- 索引同步:新增、迁移或重命名文档时同步 docs/index.md;影响 package-facing 入口时同步 README 或保留兼容入口。
- 规范沉淀:创建和维护 docs/_STYLE_GUIDE.md,明确目录职责、模板、校验目标和后续 docs tooling 缺口。
- 质量验证:检查文档类型边界、链接、旧入口、渲染约束、目标 tooling 声明和泛化内容外迁边界。
[Workflow(执行流程)]
详细执行流程见 references/write-opensource-docs-workflow.md。入口流程如下:
1. 判断任务模式:`assess`、`scaffold`、`write`、`migrate` 或 `validate`。
2. 读取项目事实:`docs/` 文件树、`docs/index.md`、项目 `docs/_STYLE_GUIDE.md` 或 `references/docs-style-guide-baseline.md`、README、package metadata 和相关源码入口。
3. 依据 `references/diataxis-doc-types.md` 选择文档类型;高影响分类不明确时,先向用户询问。
4. 根据模式生成或修改文档,使用 `assets/` 中对应模板。
5. 同步索引和兼容入口,避免新文档成为孤岛。
6. 运行可用验证命令;`npm run docs:*` 仅在 `package.json` 已存在对应脚本时运行。
7. 总结 touched files、文档类型、未实现 tooling 和剩余风险。
[Notes(注意事项)]
- docs/ 是公开项目文档源,不替代 _bmad-output/、_speclite-output/ 或 assets/source/speclite/。
- Reference 回答“是什么、字段是什么、怎么调用”;Explanation 回答“为什么、如何工作、设计取舍是什么”。
- Tutorials 面向新手完整学习路径;How-To 面向已有基础用户解决具体任务。
- 当前主要渲染目标是 GitHub 和 npm,提示块使用 blockquote 形式,例如 > Note:、> Tip:、> Caution:。
- 文档规范优先级为项目 docs/_STYLE_GUIDE.md > 本 Skill 内置 references/docs-style-guide-baseline.md > 用户本轮明确指令。
- 目标 docs tooling 可以写入规范,但在脚本未接入 package.json 前,不得声称它们是当前可运行门禁。
- 泛化 AI Coding 思想或与当前项目事实无关的长篇理念文档,应迁出项目 docs/ 或标为外部参考,不混入官网文档源。
[Generation Metadata(生成信息)]
本 Skill 由 speclite-skill-creator 自动生成。如需修改,必须同步更新 SKILL.md 与 SKILL.en.md,并同步 assets/source/speclite/sdlc-skills/1-analysis/speclite-write-opensource-docs/ 与实际安装副本。
What ships with it
14 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.
- assets/explanation-template.md 383 B
- assets/glossary-template.md 160 B
- assets/how-to-template.md 456 B
- assets/reference-template.md 479 B
- assets/style-guide-template.md 1.1 KB
- assets/tutorial-template.md 728 B
- CHANGELOG.md 956 B
- references/conversation-derived-rules.md 1.7 KB
- references/diataxis-doc-types.md 2.4 KB
- references/docs-style-guide-baseline.md 6.8 KB
- references/examples.md 1.5 KB
- references/validation-checklist.md 1.2 KB
- references/write-opensource-docs-workflow.md 3.5 KB
- SKILL.en.md 4.2 KB
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.
- 6d ago First seen · 45 lines · 121 tokens per session scan A c3c6544445a0
speclite-write-opensource-docs is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 121 tokens to every session and 1,114 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
lain
Structural code intelligence for AI coding agents. Use this skill when the user wants to understand how a codebase is organized (modules, call graphs, file dependencies), find where to start reading, trace the impact of a change, find code by meaning, or understand what a symbol does in its full context. Do NOT use…
botpipe-workflow-authoring
Author, review, and improve Botpipe workflows. Use when Codex is asked to create packaged or workspace-local Botpipe workflows, convert codebases into workflows, design provider-heavy producer/verifier steps, write Botpipe prompts/contracts, inspect Botpipe traces, or apply Codex CLI/gpt-5.5 workflow patterns.
pre-merge
The CI gate. Takes a feature branch from "eng says done" to "PR open against staging with green checks". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → open PR. Emits…
intake
The planning front-door. Captures feature ideas and bugs as graded rows in the root INTAKE.md ledger. Use it when the user says "log an idea", "capture a bug", "add to the backlog", "note this down", "track this feature", or invokes /intake. Owns the requirements interview — fleshes out thin ideas, proactively…
merge
The ship gate — the only skill that merges. --staging merges the feature→staging PR on green CI, deploys, verifies, emits a human test script and stamps the staging sign-off on approval. --production ships the double-confirmed release to main and deploys production. Never self-certifies staging; nothing reaches main…
msg
Root menu for msg skills, plus harness modes. --init is the one-time project bootstrap — use it when the user says "initialise project", "bootstrap repo", "set up the framework", "start a new project", or asks to set up project structure in an empty repo. Other modes: --init-staging (add a staging branch), --update…