Skip to content
Back to search

speckit-agent-skills

Agent skills for Spec Kit

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/dceoy/speckit-agent-skills with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/dceoy/speckit-agent-skills'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/dceoy--speckit-agent-skills/badge.svg)](/listings/dceoy--speckit-agent-skills)

HTML

<a href="/listings/dceoy--speckit-agent-skills"><img src="/api/listings/dceoy--speckit-agent-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Clone this repository.

   git clone https://github.com/dceoy/speckit-agent-skills.git
   cd speckit-agent-skills

2. Install [Spec Kit](https://github.com/github/spec-kit).

3. Initialize a target project with the Spec Kit integration appropriate for your agent.

   specify init --here --integration <integration>

4. If the target runtime consumes Agent Skills directly, copy the required skills from `skills/` into that project's skills directory when needed.

   cp -a skills/* /path/to/project/skills/

5. Invoke the relevant `speckit-*` skill or runtime command from your agent.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 200 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # speckit-agent-skills
  2. Agent skills and generated runtime entry points for [Spec Kit](https://github.com/github/spec-kit).
  3. ## Overview
  4. This repository tracks the current Spec Kit output together with a small set of repository-specific skills.
  5. - **Shared Agent Skills** - `skills/` contains the shared `speckit-*` skills plus repository-specific skills. Claude Code uses them through `.claude/skills`, while Codex CLI uses them through `.agents/skills`.
  6. - **Cursor Agent** - Spec Kit-generated skills live in `.cursor/skills/`.
  7. - **GitHub Copilot CLI** - Spec Kit-generated agents and prompt wrappers live in `.github/agents/` and `.github/prompts/`.
  8. - **OpenCode** - Spec Kit-generated commands live in `.opencode/commands/`.
  9. - **Gemini CLI** - `.gemini/commands/` remains checked in, but Gemini is not part of the current CI regeneration set.
  10. - **Spec Kit infrastructure** - `.specify/` contains integration state, manifests, scripts, and templates used by the generated skills and commands.
  11. The tracked Spec Kit version is recorded in [VERSION.md](./VERSION.md). CI checks the latest Spec Kit release and regenerates outputs only when that version changes.
  12. ## Current integration model
  13. The repository CI currently runs `specify init --integration` for:
  14. - `codex`
  15. - `agy`
  16. - `cursor-agent`
  17. - `copilot`
  18. - `opencode`
  19. - `claude`
  20. The generated files are therefore not all stored in the same layout:
  21. | Runtime / integration | Repository path | Role |
  22. | --------------------- | ------------------------------------- | -------------------------------------------------------------------- |
  23. | Agent Skills (`agy`) | `skills/` | Shared Spec Kit skills |
  24. | Claude Code | `.claude/skills -> ../skills` | Shared skills exposed to Claude Code |
  25. | Codex CLI | `.agents/skills -> ../skills` | Shared skills exposed to Codex |
  26. | Cursor Agent | `.cursor/skills/` | Cursor-specific generated skill copies |
  27. | GitHub Copilot CLI | `.github/agents/`, `.github/prompts/` | Generated agents and prompt wrappers |
  28. | OpenCode | `.opencode/commands/` | Generated commands |
  29. | Gemini CLI | `.gemini/commands/` | Checked-in commands; not regenerated by the current CI configuration |
  30. Legacy layouts such as `.claude/commands/`, `.codex/prompts/`, and `.opencode/command/` are intentionally not maintained.
  31. ## Quickstart
  32. 1. Clone this repository.
  33. ```bash
  34. git clone https://github.com/dceoy/speckit-agent-skills.git
  35. cd speckit-agent-skills
  36. ```
  37. 2. Install [Spec Kit](https://github.com/github/spec-kit).
  38. 3. Initialize a target project with the Spec Kit integration appropriate for your agent.
  39. ```bash
  40. specify init --here --integration <integration>
  41. ```
  42. 4. If the target runtime consumes Agent Skills directly, copy the required skills from `skills/` into that project's skills directory when needed.
  43. ```bash
  44. cp -a skills/* /path/to/project/skills/
  45. ```
  46. 5. Invoke the relevant `speckit-*` skill or runtime command from your agent.
  47. ## Spec Kit workflow
  48. The main Spec-Driven Development flow in this repository is:
  49. 1. **Constitution** - Define project principles.
  50. 2. **Specify** - Capture requirements for new work.
  51. - Or **Baseline** - Derive a specification from an existing codebase.
  52. 3. **Clarify** _(optional)_ - Resolve material ambiguities.
  53. 4. **Plan** - Produce the implementation strategy.
  54. 5. **Tasks** - Generate ordered work items.
  55. 6. **Analyze** _(optional)_ - Check consistency across the specification, plan, and tasks.
  56. 7. **Converge** _(optional)_ - Compare an existing implementation with the spec/plan/tasks and append remaining work to `tasks.md`.
  57. 8. **Implement** - Execute the tasks.
  58. Additional utilities include **Checklist** for requirements-quality checks and **Tasks to Issues** for converting generated tasks into GitHub issues.
  59. ### Visual workflow
  60. ```mermaid
  61. flowchart TD
  62. C0["speckit-constitution"] --> C1["speckit-specify"]
  63. C0 --> B["speckit-baseline"]
  64. C1 --> C2["speckit-plan"]
  65. B --> C2
  66. C2 --> C3["speckit-tasks"]
  67. C3 --> C4["speckit-implement"]
  68. C1 -.-> O1["speckit-clarify"]
  69. B -.-> O1
  70. O1 -.-> C2
  71. C3 -.-> O2["speckit-analyze"]
  72. O2 -.-> C4
  73. C3 -.-> O3["speckit-converge"]
  74. O3 -.-> C4
  75. C3 -.-> O4["speckit-taskstoissues"]
  76. C1 -.-> O5["speckit-checklist"]
  77. C2 -.-> O5
  78. C3 -.-> O5
  79. ```
  80. ## Skills
  81. ### Spec Kit skills
  82. The current shared `speckit-*` set includes:
  83. - `speckit-analyze`
  84. - `speckit-baseline`
  85. - `speckit-checklist`
  86. - `speckit-clarify`
  87. - `speckit-constitution`
  88. - `speckit-converge`
  89. - `speckit-implement`
  90. - `speckit-plan`
  91. - `speckit-specify`
  92. - `speckit-tasks`
  93. - `speckit-taskstoissues`
  94. Most Spec Kit-managed skills are tracked by the manifests in `.specify/integrations/`. `speckit-baseline` is a repository-specific skill for deriving specifications from existing code.
  95. ### Utility skills
  96. - `claude-command-converter` - Repository-specific utility for converting Claude command content into Agent Skill format.
  97. ## Structure
  98. ```text
  99. .
  100. ├── skills/ # Shared and repository-specific Agent Skills
  101. ├── .agents/
  102. │ └── skills -> ../skills # Codex CLI access to shared skills
  103. ├── .claude/
  104. │ └── skills -> ../skills # Claude Code access to shared skills
  105. ├── .cursor/
  106. │ └── skills/ # Cursor Agent generated skills
  107. ├── .gemini/
  108. │ └── commands/ # Checked-in Gemini commands
  109. ├── .github/
  110. │ ├── agents/ # GitHub Copilot generated agents
  111. │ ├── prompts/ # GitHub Copilot prompt wrappers
  112. │ └── workflows/ # CI and Spec Kit regeneration workflows
  113. ├── .opencode/
  114. │ └── commands/ # OpenCode generated commands
  115. ├── .specify/
  116. │ ├── integrations/ # Integration manifests
  117. │ ├── scripts/bash/ # Spec Kit helper scripts
  118. │ ├── templates/ # Spec Kit templates
  119. │ ├── init-options.json # Last initialization options
  120. │ └── integration.json # Current integration state
  121. ├── .vscode/
  122. │ └── settings.json # Workspace settings
  123. └── VERSION.md # Tracked Spec Kit version
  124. ```
  125. ## Regeneration
  126. `.github/workflows/ci.yml` calls `.github/workflows/speckit-init.yml`. The workflow:
  127. 1. resolves the latest Spec Kit release,
  128. 2. records `specify --version` in `VERSION.md`,
  129. 3. skips regeneration when `VERSION.md` is unchanged,
  130. 4. runs `specify init --force --here --ignore-agent-tools --script sh --integration` for the configured integrations,
  131. 5. formats generated Markdown and JSON, and
  132. 6. opens or updates a pull request when the tracked Spec Kit version changes.
  133. Treat manifest-managed runtime files as generated output. Prefer changing the integration configuration or repository-specific skills instead of manually maintaining generated copies.
  134. ## Prerequisites
  135. Install and authenticate only the runtime tools you intend to use, plus Spec Kit itself.
  136. - **Claude Code** - Uses `.claude/skills`.
  137. - **OpenAI Codex CLI** - Uses `.agents/skills`.
  138. - **Cursor Agent** - Uses `.cursor/skills/`.
  139. - **GitHub Copilot CLI** - Uses `.github/agents/` and `.github/prompts/`.
  140. - **OpenCode** - Uses `.opencode/commands/`.
  141. - **Gemini CLI** - Can use the checked-in `.gemini/commands/`, but those files are outside the current regeneration set.
  142. - **Spec Kit** - Install from [github.com/github/spec-kit](https://github.com/github/spec-kit).
  143. ## Usage notes
  144. - Skills do not always auto-run; use the runtime's skill invocation flow or request the skill explicitly.
  145. - If a skill fails, inspect its `SKILL.md` and verify the required Spec Kit project structure and prerequisites.
  146. - Run Spec Kit helper scripts from the repository root and prefer their structured output modes such as `--json` when available.
  147. - Do not restore legacy runtime layouts unless a currently supported Spec Kit integration starts generating them again.
  148. ## License
  149. See [LICENSE](./LICENSE) for details.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.