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-create-prdgit 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-create-prd)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-create-prd"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-create-prd/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-create-prd"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-create-prd.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 | $0.00073 | $0.01168 |
| Opus 5 | $0.00036 | $0.00584 |
| Sonnet 5 | $0.00015 | $0.00234 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
speclite-create-prd 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 7d 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.
This is a copy
86% identical to speclite-domain-research — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
[技能说明] Create PRD 是 Speclite 规划与产品设计工作流 Skill,用于在目标项目中按配置语言、输出语言和工作流步骤完成对应制品或交付动作。
源入口说明:Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a new PRD"
[核心能力]
- Speclite 激活解析:解析三层 customize(base→team→user)、workflow.persistent_facts 和 workflow.on_complete,并通过 speclite resolve config --project-root {project-root} 加载 merged runtime config。
- 源制品发现与上下文加载:按 workflow 规约读取项目制品、配置字段、历史上下文和必要数据文件,保持源流程的输入发现语义。
- 步骤化工作流执行:按 references/workflow-details.md 与拆分后的 reference/step 文件逐步执行,遵守顺序、HALT 条件、菜单等待和状态推进规则。
- 模板化输出生成:使用 assets 中的模板或示例骨架生成文档、报告、规格或交付产物,输出语言服从 document_output_language。
- 质量校验与交接:执行清单、报告、状态同步或 completion handoff,并在退出前解析和执行 workflow.on_complete。
- 迁移一致性约束:当前运行规约只依赖 Speclite runtime,不读取旧运行目录、旧配置文件或旧命令命名空间。
[约定]
裸路径相对于 {skill-root} 解析;{project-root} 是目标项目工作目录;{speclite-runtime-root} 是 {project-root}/_speclite;{skill-name} 是目录 basename。
[激活流程]
触发后先解析 workflow,执行 activation_steps_prepend,加载 persistent_facts,运行 speclite resolve config --project-root {project-root},按 communication_language 与用户沟通,并执行 activation_steps_append。配置文件缺失或关键字段为空时必须 HALT;config.toml.example 只说明字段结构,不作为 runtime fallback。
customization 必须通过 `speclite resolve customization --skill {skill-root} --project-root {project-root}` 读取 merged JSON;`workflow.on_complete` 使用 `speclite resolve customization --skill {skill-root} --project-root {project-root} --key workflow.on_complete` 解析。默认 activation 不手写 TOML merge,不使用 `--human` 作为 machine input。
[执行流程]
1. 先完整阅读 references/workflow-details.md;该文件是从源入口转换后的权威工作流规约。随后按需读取 references/workflow-details.md、references/data/prd-purpose.md、references/steps/step-01-init.md、references/steps/step-01b-continue.md、references/steps/step-02-discovery.md、references/steps/step-02b-vision.md 等 reference 文件。
2. 执行工作流前,确认 {skill-root}、{project-root}、{speclite-runtime-root}、{skill-name} 四个路径变量均已明确。
3. 若 workflow 指向 step 文件,必须一次只读取当前 step,完整执行后再进入下一步;遇到菜单或用户确认点时 HALT 等待。
4. 生成或更新产物时,按源 workflow 的模板、清单、状态字段和输出位置要求执行,不得因为迁移而改变核心需求。
5. 收尾前运行 checklist 或质量检查,解析 workflow.on_complete,并在输出文档末尾追加本 Skill 的生成标注。
[注意事项]
- 名称、目录与 YAML name 字段保持 kebab-case 一致:speclite-create-prd。
- references/workflow-details.md 和配套 reference 文件均为有效执行规约,不是背景资料。
- 模板或示例骨架位于 assets/prd-template.md。
- 数据和结构化参考位于 data/domain-complexity.csv、data/project-types.csv。
- config.toml.example 仅作字段结构参考,不作为 runtime fallback。
- 当前运行规约不得依赖旧运行目录、旧 YAML 配置或旧命令命名空间。
- 输出文档末尾必须追加 *本文档由 speclite-create-prd Skill 自动生成* 标注。
[生成信息] 本 Skill 由 speclite-skill-creator 自动生成。
What ships with it
24 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/prd-template.md 164 B
- CHANGELOG.md 351 B
- config.toml.example 562 B
- customize.toml 1.6 KB
- data/domain-complexity.csv 7.2 KB
- data/project-types.csv 3.1 KB
- references/data/prd-purpose.md 7.1 KB
- references/steps/step-01-init.md 7.6 KB
- references/steps/step-01b-continue.md 5.6 KB
- references/steps/step-02-discovery.md 7.9 KB
- references/steps/step-02b-vision.md 6.6 KB
- references/steps/step-02c-executive-summary.md 7.1 KB
- references/steps/step-03-success.md 9.0 KB
- references/steps/step-04-journeys.md 8.8 KB
- references/steps/step-05-domain.md 6.8 KB
- references/steps/step-06-innovation.md 8.5 KB
- references/steps/step-07-project-type.md 8.6 KB
- references/steps/step-08-scoping.md 11 KB
- references/steps/step-09-functional.md 9.0 KB
- references/steps/step-10-nonfunctional.md 8.8 KB
- references/steps/step-11-polish.md 9.2 KB
- references/steps/step-12-complete.md 5.0 KB
- references/workflow-details.md 5.2 KB
- SKILL.en.md 3.7 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.
- 7d ago First seen · 50 lines · 73 tokens per session scan A aafb6da86ba7
speclite-create-prd is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 1,168 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to speclite-domain-research, differing in 18 lines, and is treated as a copy.
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…