Skills warpdotdev common-skills
readout
- Use it when:
- You say "write this up" mid-investigation, or want a readable explainer such as how a server processes webhook events.
- It does:
- Asks two to four scoping questions with concrete options, then hands a short brief to one local child agent that mines the conversation or researches the code.
- You get:
- ~/.readouts/<date>-<topic>.html built from a shared template, with linked and embedded code references, plus a regenerated index.html of every readout.
- Modes:
- Snapshot, from what the conversation already found; research, starting fresh from the codebase.
- Runs:
- As a side task: the main agent launches the child and carries on, then relays the file path.
TL;DR
A readout is meant to be read weeks later by someone with none of the original context. The main agent's part is small: sharpen the scope, always settling depth and audience but skipping questions when the request is already specific, then write a brief of 10 to 20 lines with pointers rather than pasted findings: the questions to answer, what to cover and exclude, repo paths, and each repo's URL and commit for code links. One child agent, launched locally through Warp's run_agents tool so the file lands on your machine, does the writing. In snapshot mode it searches the parent conversation by run ID and verifies file references; in research mode it traces the real code paths and grounds claims in file:line references, separating verified from inferred. It follows the skill's doc guide and HTML template, embeds snippets and refreshes the index with bundled Python scripts, and opens the file unless the machine is headless. Without subagents, the main agent writes the document itself.
Summarizes the skill at 8792394.
npx skills add https://github.com/warpdotdev/common-skills --skill readout skills.sh pageSource on GitHubAll skills from warpdotdev/common-skills
- Total Downloads
- 17,700 on skills.sh, Nov 9, 2026
- Repo stars
- 678 warpdotdev/common-skills
- First seen
- Jul 8, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 637 |
| Sep 28 | 577 |
| Oct 5 | 922 |
| Oct 12 | 486 |
| Oct 19 | 358 |
| Oct 26 | 356 |
| Nov 2 | 106 |
| Nov 9 | 78 |
| Category |
Articles, docs, internal comms, research write-ups and prose that doesn't read as generated. |
|---|---|
| Type |
A multi-step process the agent follows: interview, debug, run a TDD loop, review. |
| Effect |
Its own steps create or change files, git state or local tools. |
| Needs |
Relies on the agent being able to spawn subagents. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics |
SKILL.md
No copy of its SKILL.md yet.