Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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-skill-creator)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-skill-creator"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-skill-creator/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-skill-creator"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-skill-creator.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 | $0.00076 | $0.01463 |
| Opus 5 | $0.00038 | $0.00732 |
| Sonnet 5 | $0.00015 | $0.00293 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
speclite-skill-creator 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 9d 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）] 通过结构化交互对话创建符合 Anthropic Skills 开放标准的完整 Agent Skills 包。它把用户需求转化为标准化的 SKILL.md、SKILL.en.md、CHANGELOG.md、references/、scripts/ 和 assets/，并用脚本化 Workflow density gate 保证入口文件符合渐进式披露思想。
[Core Capabilities（核心能力）]
- 需求挖掘：一次最多提问 3 个，收集名称、目标、触发词、输入输出、catalog 和执行步骤。
- 工作流匹配：根据业务特征推荐顺序、多 MCP、迭代、上下文感知或领域专有模式，详见 references/workflow-patterns.md。
- 规范转译：生成三段式 description、以 speclite- 开头的 kebab-case name、allowed-tools，并按 metadata 字段契约写入 metadata.version、metadata.author 和可选 metadata.catalog。
- 双语入口生成：生成中文 canonical SKILL.md 与英文 mirror SKILL.en.md，保持 YAML、版本、目录和执行语义一致。
- Workflow density gate：使用 deterministic 脚本统计正文长度、Workflow 长度和占比，命中阈值时抽取 workflow reference。
- Flow Gate guidance：为会推进 Story/Epic 状态或依赖实现锚点的 workflow skill 生成 Contract -> Functional -> Evidence 门控表达，避免固定路径误判。
- 渐进式文件组织：按 SKILL.md、SKILL.en.md、CHANGELOG.md、references/、scripts/、assets/ 分配核心指令、详细资料、脚本和模板。
- 质量与测试指导：控制正文长度、语言规则、命名规范、生成标注和触发测试建议。
[Workflow（执行流程）]
本 Skill 采用需求收集→结构规划→文件生成→density gate→总结交付的顺序工作流。完整步骤见 references/skill-creation-workflow.md。
Step 1：收集并确认需求
读取 `references/skill-creation-workflow.md` 的 Requirement Collection 部分，按最多 3 个问题一组收集信息，并在生成前展示确认清单。
Step 2：规划文件结构并生成入口
先写入 `assets/source/speclite/<group>/<skill-name>/`，其中 `<group>` 为 `core-skills`、`sdlc-skills/<phase>` 或 `support-skills`。生成 SKILL.md、SKILL.en.md、CHANGELOG.md，并按需生成 references/、scripts/、assets/；需要外部 forge mirror 时，再同步到 `/Users/fancyliu/Repos/skills-creator/forge/speclite/` 对应分区。
Step 3：加入 Flow Gate guidance
若 Skill 会推进 Story/Epic 状态、消费 Story 文件、检查实现 anchor 或写入 implementation artifacts，必须在入口或 reference 中加入 flow-gate guidance：固定路径只有 owning SPEC 明确要求时才是 hard gate，否则应描述 equivalent implementation policy。
Step 4：运行 Workflow density gate
生成草稿后，优先调用已安装 `speclite-skill-lint` 的 `scripts/check_skill_density.py`；在本仓库源码中使用 `python3 assets/source/speclite/support-skills/speclite-skill-lint/scripts/check_skill_density.py <skill-dir>`。脚本结果是唯一判断来源。
Step 5：按 gate 结果拆分 Workflow
若任一入口文件满足 `workflow_chars > 1500` 且 `workflow_ratio > 0.5`，必须创建 `references/<skill-name>-workflow.md` 或等价 workflow reference。入口 Workflow 只保留阶段摘要、何时读取 reference 和关键停止条件。
Step 6：完成总结
展示文件树、渐进式披露分层、触发测试建议、版本信息和后续通过 `speclite-skill-lint` 收敛的入口。
[Notes（注意事项）]
- SKILL.md 是中文 canonical 文档，正文使用中文；章节标题使用 English（中文）形式；命令、路径、字段名、fixture 名称、schema/issue id 等技术标识使用英文。
- SKILL.en.md 是英文 mirror，不得新增中文入口没有的能力、步骤、限制或触发条件。
- 每个 Skill 必须包含 SKILL.md、SKILL.en.md 和 CHANGELOG.md，版本号保持同步。
- 中文与英文入口正文分别控制在 5000 字以内；Workflow density gate 是 Warning 级质量规则，但创建时命中必须拆分。
- YAML frontmatter 只允许 name、description、license、allowed-tools、metadata，且不得包含 XML 尖括号或代码执行逻辑。
- metadata 仅支持 version、author、catalog：version 和 author 必填，catalog 在 Skill 归入 catalog 时填写并与路径及 mirror 对齐。
- 目录和 name 字段必须使用 kebab-case，并以 speclite- 开头；禁止保留前缀 claude-、codex-、anthropic-*。
- 涉及实现阶段状态推进或 anchor 检查的 workflow skill，必须说明 owning SPEC、equivalent implementation policy 和 Flow Gate report 消费方式。
- 运行产物写入 .specskills/output/，过程分析文档写入 .specskills/docs/analysis/，不得散落在项目根目录。
- 如需安装测试，只同步到实际存在的安装根；不得凭空创建 .codex/skills。
[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/support-skills/speclite-skill-creator/ 与实际安装副本。
What ships with it
7 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.
- 9d ago First seen · 59 lines · 76 tokens per session scan A 4a47a1fc5858
speclite-skill-creator is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,463 once invoked, about $0.0004 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 2026-08-31.
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.
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…
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…
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…