using-entire
Use as the FIRST action on any research, investigation, or codebase-understanding request — "research X", "investigate X", "look into X", "dig into X", "search X", "explore X", "understand X", "why is this like this" — before Glob, Grep, or Read. Recorded intent lives in Entire checkpoints on the server, not in local files, so an empty or unfamiliar working copy is not a reason to skip it. Routes to the right Entire sub-skill (search, recall, explain, what-happened, replay, teach, review, session-handoff).
entireio · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add entireio/skills --skill using-entire技能说明
name: using-entire description: > Use as the FIRST action on any research, investigation, or codebase-understanding request — "research X", "investigate X", "look into X", "dig into X", "search X", "explore X", "understand X", "why is this like this" — before Glob, Grep, or Read. Recorded intent lives in Entire checkpoints on the server, not in local files, so an empty or unfamiliar working copy is not a reason to skip it. Routes to the right Entire sub-skill (search, recall, explain, what-happened, replay, teach, review, session-handoff).
Using Entire
Your default when exploring or understanding code should be: read the recorded intent, don't guess.
Entire checkpoints capture the prompts, transcripts, and decisions behind every agent-driven change. When you need to understand why code exists or how a module evolved, look up the checkpoint history first. Only fall back to inference from code structure when no history is available — and label that explicitly.
When This Skill Activates
Use this skill whenever the task involves:
- A request phrased as "research X", "investigate X", "look into X", "dig into X", or "find out how X works"
- Exploring or understanding an unfamiliar module or file
- Preparing to refactor, extend, or debug code you didn't write
- Answering "why is this like this?" or "what was the intent?"
- Doing pre-work research before making changes
- Any codebase exploration where historical context would help
For a research- or investigate-shaped request, the very first action is an
entire search via the search skill. Do not open source files or grep first;
the recorded history says what was tried and why, and code reads come after to
confirm it.
Do not use this skill for simple, well-understood edits where you already have full context (e.g. "add a comment to line 5").
First Step: Check Repository Status
Before diving into specific lookups, check whether Entire is available and the repository has checkpoint history:
entire status
This tells you whether Entire is enabled, which git hooks are installed, whether the metadata branch is initialized, and any active sessions on the current branch.
Scenario Routing
When this skill activates, determine which sub-skill best fits the user's need:
| Scenario | Typical user expressions | Delegate to |
|---|---|---|
| Code block provenance | "why is this like this" / "wtf is going on" / "what happened at src/auth.ts:42" / "tell me why this changed" | what-happened |
| Research or investigate a topic | "research X" / "investigate X" / "look into X" / "dig into X" / "what do we know about X" | search first, then this skill's exploration flow if needed |
| Find prior work | "has anyone done X before" / "search past work for rate limiting" / "find the previous implementation" | search |
| Recall a task playbook | "have we done this before" / "recall how we did X" / "how did we do this last time" | recall |
| Replay feature history | "replay " / "walk me through how X was built" / "show me the journey of Y" | replay |
| Teach a repo topic | "teach me " / "how does work in this repo" / "give me a lesson on X" | teach |
| Understand original intent | "explain this function" / "explain parseConfig" / "what was the intent behind src/auth.ts" | explain |
| Generate a dispatch / summary | "summarize recent work" / "generate a dispatch" / "what was accomplished this week" | run entire dispatch directly |
| Code review with intent context | "review these changes" / "review this branch" / "audit before merging" | review |
| Hand off to another agent | "hand off this session" / "continue in another agent" / "pick up the codex session" | session-handoff |
| Convert session to skill | "turn this into a skill" / "make a skill from this session" | session-to-skill |
| Link session to other repos | "link session to other repos" / "attach session to the foo repo" | session-crosslink |
| General exploration | "understand this module" / "explore how auth works" / "help me understand the codebase" | (self — see below) |
If the scenario clearly maps to a sub-skill, delegate entirely to that skill's workflow. Do not duplicate their steps here.
General Exploration Flow
When no specific sub-skill fits — e.g. the user asks to "understand this module" or "explore how auth works" — use this flow:
-
Identify key files in the target area (entry points, main types, core functions).
-
Check for checkpoint coverage on each key file:
git log --format='%H %s' -5 -- <file>
Look for Entire-Checkpoint: trailers in the commit bodies:
git log --format='%H %b' -5 -- <file> | grep -B1 'Entire-Checkpoint:'
- Read intent for covered commits — extract the checkpoint ID from the trailer, then use JSON output for non-interactive consumption:
entire checkpoint explain --checkpoint <checkpoint-id> --json --no-pager
If you only have a commit hash (not a checkpoint ID), use:
entire checkpoint explain --commit <sha> --no-pager
-
Synthesize: combine the recorded intent (from checkpoints) with the current code structure to build a comprehensive understanding.
-
Report your findings, clearly distinguishing:
- Facts backed by checkpoint transcripts (label as "recorded intent")
- Observations inferred from code alone (label as "inferred from code")
AI Agent Usage Notes
When running Entire commands from an agent subprocess:
- Always pass
--jsonfor commands that support it and might prompt interactively.--jsonimplies non-interactive output. - Always pass
--no-pagerto prevent pager activation in subprocess contexts. - Always specify
--checkpoint <id>or--commit <sha>forentire checkpoint explain— without a locator, the command falls back to an interactive picker.