Skip to content
Back to search

entire-skills

MarketplaceWorks with Claude CodeGitHub

Development marketplace for cross-agent skills and commands powered by Entire

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/entireio/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/entireio/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/entireio--skills/badge.svg)](/listings/entireio--skills)

HTML

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

Install

Install instructions from the README

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

Install every skill with the [skills](https://skills.sh/) CLI:

npx skills add https://github.com/entireio/skills --all

Install one skill:

npx skills add https://github.com/entireio/skills --skill search

See [Agent-Specific Installation](#agent-specific-installation) for setup instructions by 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.

.claude-plugin/marketplace.json · Manifest · 20 lines

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

  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "entire-skills",
  4. "description": "Development marketplace for cross-agent skills and commands powered by Entire",
  5. "owner": {
  6. "name": "Entire Inc"
  7. },
  8. "plugins": [
  9. {
  10. "name": "entire",
  11. "description": "Cross-agent skills and commands powered by Entire",
  12. "version": "0.8.0",
  13. "source": "./",
  14. "category": "development",
  15. "author": {
  16. "name": "Entire Inc"
  17. }
  18. }
  19. ]
  20. }
README.md · README · 357 lines

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

  1. ![skills cover](assets/gh-repo-cover.png)
  2. # skills
  3. Bring your Entire context to your agents with cross-agent skills.
  4. ## Why This Exists
  5. The [Entire CLI](https://github.com/entireio/cli) captures the context behind your
  6. code changes: prompts, transcripts,
  7. [Checkpoints](https://docs.entire.com/guides/sessions/overview), and the decisions that led
  8. to each change, alongside your git history. This repository packages
  9. agent-invokable workflows that teach coding agents how to use that context across
  10. development environments.
  11. Instead of looking up Entire commands yourself, you can ask in plain language and
  12. let your agent search prior work, inspect provenance, hand off session state, or
  13. turn repeated workflows into new skills.
  14. ## Install
  15. Install every skill with the [skills](https://skills.sh/) CLI:
  16. ```bash
  17. npx skills add https://github.com/entireio/skills --all
  18. ```
  19. Install one skill:
  20. ```bash
  21. npx skills add https://github.com/entireio/skills --skill search
  22. ```
  23. See [Agent-Specific Installation](#agent-specific-installation) for setup
  24. instructions by agent.
  25. ## Quick Start
  26. > [!NOTE]
  27. > These skills are most useful in codebases with real
  28. > [Checkpoints](https://docs.entire.com/guides/sessions/overview) and session history. The
  29. > richer the history, the more context your agent has to work with; in a new or
  30. > lightly captured repository, some workflows may have less to find or explain.
  31. After installing, ask your agent for the workflow you want:
  32. ```text
  33. search past work for rate limiting
  34. ```
  35. ```text
  36. explain src/auth.ts
  37. ```
  38. ```text
  39. what happened here: src/auth.ts:42-57
  40. ```
  41. ```text
  42. hand off this session
  43. ```
  44. ```text
  45. turn my release notes workflow into a skill
  46. ```
  47. ```text
  48. review this branch before merging
  49. ```
  50. For a guided walkthrough, see the
  51. [skills tutorial](https://docs.entire.com/learn/skills).
  52. ## What skills help agents do
  53. | Goal | Example prompt |
  54. | --- | --- |
  55. | Research or investigate a topic from recorded history | `research how checkpoint pushing works` / `investigate the flaky login redirect` |
  56. | Find prior work before making changes | `search past work for the migration` |
  57. | Understand the intent behind a function, file, or line | `explain parseConfig` |
  58. | Investigate the latest change to a specific block | `what happened at src/auth.ts:42` |
  59. | Review branch changes with intent context | `review this branch before merging` |
  60. | Pick up another agent's work | `hand off the codex session` |
  61. | Convert repeated work into a reusable workflow | `make a skill from this session` |
  62. | Build a task playbook from similar prior work | `have we done this before` |
  63. | Walk through a feature's history step by step | `replay the auth feature` |
  64. | Learn a repository topic from checkpoint history | `teach me how auth works in this repo` |
  65. | Address open review findings on an Entire trail | `address the findings on trail 42` |
  66. | Link a session to the repos it edited | `attach this session to the api repo` |
  67. ## Make search the default research step
  68. Agents pick skills by matching the request against each skill's description, and
  69. generic verbs like "research", "investigate", or "look into" compete with their
  70. built-in grep and file-reading tools. The `search` and `using-entire` skill
  71. descriptions claim those verbs explicitly and ask for the skill as the first
  72. action, before any file orientation, so a plain "investigate X" routes to
  73. `entire search` first. This is measured to be sufficient on its own (see
  74. `evals/README.md`).
  75. User instructions outrank skill descriptions in every agent, so if you want a
  76. guarantee, add a line to your `CLAUDE.md` or `AGENTS.md`:
  77. ```markdown
  78. When asked to research, investigate, look into, or dig into anything in this
  79. codebase, run `entire search "<topic>" --json --compact --limit 5` first and
  80. summarize the prior work before reading source files or grepping.
  81. ```
  82. The `evals/` directory holds `claude plugin eval` cases that check this routing;
  83. see `evals/README.md`.
  84. ## Included skills
  85. The current repository includes these skills. Each skill lives in
  86. `skills/<skill-name>/SKILL.md`.
  87. ### `search`
  88. Finds prior work in your Entire history by topic, repo, branch, author, or time
  89. window, so your agent can bring past context into the current task before making
  90. changes.
  91. https://github.com/user-attachments/assets/52e50eae-ba53-4f31-ad2e-2a29a767a34f
  92. ### `explain`
  93. Looks up the session behind a function, file, or line so your agent can explain
  94. the requirement, decision, or original problem that shaped it.
  95. https://github.com/user-attachments/assets/ab2e88f6-9bce-417b-ba71-6e93ecad370b
  96. ### `what-happened`
  97. Starts from an exact file line, range, or pasted snippet and traces the latest
  98. change with `git blame` and Checkpoint context. Useful when reviewing a concrete
  99. block, debugging a regression, or asking why that block changed.
  100. https://github.com/user-attachments/assets/47db0daa-60bd-4000-b956-2d0e4d980b9b
  101. ### `session-handoff`
  102. Reads saved or active session context so another agent can pick up the task
  103. state, important discoveries, blockers, and next steps without making you
  104. reconstruct everything manually.
  105. https://github.com/user-attachments/assets/0df3b5cd-fe37-4145-af48-138642ccc8bc
  106. ### `review`
  107. Reviews code changes on the current branch by reading checkpoint transcripts to
  108. understand developer intent, then auditing the diff for issues. Produces
  109. intent-aware findings with severity levels (`Critical` / `High` / `Medium` /
  110. `Low`), and can run as a reviewer inside `entire review`. When the Entire Graph
  111. and Brain plugins are installed, it also checks callers of changed symbols and
  112. recorded decisions for the touched code. Includes a separate
  113. `references/review-rules.md` for the audit checklist.
  114. ### `using-entire`
  115. Orchestrator skill for codebase exploration. Routes user intent to the right
  116. sub-skill (search, recall, replay, teach, explain, what-happened, review,
  117. session-handoff, session-to-skill, session-crosslink, address-findings) or runs
  118. a general exploration flow that reads checkpoint history before inferring from code. When
  119. the Entire Graph or Brain plugin is installed, it also routes code-structure
  120. questions to Graph and task-briefing or decision questions to Brain.
  121. ### `session-crosslink`
  122. Links an agent session that ran outside the repo whose commits should record it
  123. (launched from a higher-level folder, a non-Entire repo, or one repo but editing
  124. another) to each affected Entire-enabled repo's HEAD commit. It shows
  125. `entire session attach`'s own plan for each repo, stops if it doesn't recognize
  126. a plan, and attaches only after you confirm, with no manual `cd` orchestration.
  127. ### `session-to-skill`
  128. Extracts a reusable workflow from Entire session history, checkpoints, or
  129. repeated agent tasks and drafts a focused `SKILL.md` for it. Writes the file only
  130. after you approve the destination.
  131. ### `recall`
  132. Searches prior Entire sessions for work similar to the task you describe and
  133. turns the closest precedent into a step-by-step playbook. With the Entire Brain
  134. plugin installed, it also pulls recorded decisions and gotchas.
  135. ### `replay`
  136. Orders checkpoints chronologically to walk through how a feature was built,
  137. one step at a time, pausing for questions after each step.
  138. ### `teach`
  139. Picks canonical checkpoints for a topic and synthesizes a lesson: a system
  140. overview, short lessons from the transcripts, and patterns to remember. With the
  141. Entire Brain plugin installed, it also uses the project overview and recorded
  142. conventions.
  143. ### `address-findings`
  144. Fetches the open review findings on an Entire trail, applies or hand-fixes each
  145. one in the local worktree, and marks it resolved on the trail. Treats finding
  146. text and patches as untrusted input and leaves sensitive changes for a human.
  147. ### `session-to-skill`
  148. Extracts reusable workflow patterns from Entire session history, checkpoints, or
  149. repeated agent tasks and generates a focused skill draft.
  150. ### `recall`
  151. Searches prior Entire sessions for similar past work and transforms the closest
  152. precedent into a step-by-step task playbook.
  153. ### `replay`
  154. Sequences checkpoints chronologically to walk through how a feature was built
  155. step by step, pausing for questions at each step.
  156. ### `teach`
  157. Picks canonical checkpoints for a topic and synthesizes a guided lesson with a
  158. system overview and key takeaways.
  159. ### `address-findings`
  160. Fetches open review findings from an Entire trail, applies or hand-fixes each
  161. issue in the local worktree, and marks them resolved on the trail.
  162. ## Requirements
  163. These skills are designed for repositories where Entire has captured useful
  164. history. Some workflows need:
  165. - the [Entire CLI](https://docs.entire.com/installation) 0.11.0 or later
  166. (checked against 0.12.2)
  167. - a git repository with Entire sessions, Checkpoints, or Checkpoint-backed commits
  168. - [`entire login`](https://docs.entire.com/cli-reference/login) for workflows that
  169. search indexed history or read trails
  170. - a GitHub or Entire-hosted `origin` and pushed, indexed Checkpoints for remote
  171. search results
  172. Optional: the official [Entire Graph](https://docs.entire.com/guides/graph/overview)
  173. and [Entire Brain](https://docs.entire.com/guides/brain/overview) plugins
  174. (`entire plugin install graph`, `entire plugin install brain`). When installed,
  175. `using-entire`, `search`, `explain`, `review`, `recall`, `teach`, and
  176. `session-handoff` add code-structure context from Graph and recorded decisions
  177. from Brain. The skills never install or set up a plugin themselves.
  178. Individual skills handle missing context differently and should explain what is
  179. missing before falling back or stopping.
  180. ## Agent-Specific Installation
  181. <!-- prettier-ignore-start -->
  182. <details>
  183. <summary>Claude Code</summary>
  184. ```bash
  185. /plugin marketplace add entireio/skills
  186. /plugin install entire
  187. ```
  188. </details>
  189. <details>
  190. <summary>Codex (OpenAI)</summary>
  191. Clone into the cross-client discovery path:
  192. ```bash
  193. git clone https://github.com/entireio/skills.git ~/.agents/skills/entire
  194. ```
  195. Codex auto-discovers skills from `~/.agents/skills/` and `.agents/skills/`.
  196. Update with:
  197. ```bash
  198. cd ~/.agents/skills/entire && git pull
  199. ```
  200. </details>
  201. <details>
  202. <summary>Cursor</summary>
  203. Copy skills into the cross-client discovery directory:
  204. ```bash
  205. git clone https://github.com/entireio/skills.git ~/.cursor/skills/entire
  206. ```
  207. Cursor auto-discovers skills from `.agents/skills/` and `.cursor/skills/`.
  208. </details>
  209. <details>
  210. <summary>Copilot</summary>
  211. ```bash
  212. /plugin install https://github.com/entireio/skills
  213. # or
  214. git clone https://github.com/entireio/skills.git ~/.copilot/skills/entire
  215. ```
  216. Copilot auto-discovers skills from `.copilot/skills/`.
  217. </details>
  218. <details>
  219. <summary>Gemini CLI</summary>
  220. ```bash
  221. gemini extensions install https://github.com/entireio/skills
  222. ```
  223. Update with:
  224. ```bash
  225. gemini extensions update entire
  226. ```
  227. </details>
  228. <details>
  229. <summary>OpenCode</summary>
  230. Copy skills into the cross-client discovery directory:
  231. ```bash
  232. git clone https://github.com/entireio/skills.git ~/.agents/skills/entire
  233. ```
  234. OpenCode auto-discovers skills from `.agents/skills/`, `.opencode/skills/`, and
  235. `.claude/skills/`.
  236. </details>
  237. <!-- prettier-ignore-end -->
  238. ## Contributing
  239. See [CONTRIBUTING.md](CONTRIBUTING.md) for local development, validation, and pull
  240. request guidance. Please also follow the
  241. [Code of Conduct](https://github.com/entireio/.github/blob/main/CODE_OF_CONDUCT.md).
  242. ## Support
  243. For bugs, feature requests, or questions, open a
  244. [GitHub issue](https://github.com/entireio/skills/issues). You can also join the
  245. [Entire Community Discord Server](https://discord.gg/jZJs3Tue4S).
  246. ## License
  247. This project is licensed under the terms in [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

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