Stats
Actions
Tags
From squad
File a new item. Runs squad new with type and title, then injects the standard item template body for you to fill in.
How this skill is triggered — by the user, by Claude, or both
Slash command
/squad:squad-fileThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are filing a new item. Run:
You are filing a new item. Run:
squad new $ARGS
This creates a new item file under .squad/items/ with frontmatter populated. Open the file and fill in the body using this template:
## Problem
<What is wrong / what does not exist. 1–3 sentences.>
## Context
<Why this matters. Where in the codebase it lives. What has been tried. Link to upstream specs if relevant.>
## Acceptance criteria
- [ ] Specific, testable thing 1
- [ ] Specific, testable thing 2
- [ ] (For bugs) A failing test exists; it now passes.
## Notes
<Optional design notes. Trade-offs considered. Pointers to related items.>
Risk classification reminder: bump risk: from low if the change touches sensitive paths defined in .squad/config.yaml. For risk: high items where rollback is non-trivial (schema migrations, multi-tier cutovers, anything git revert alone does not fully reverse), add a ## Rollback plan section before coding.
If this item is P0 or P1, add it to the "Ready" section of STATUS.md.
Commit:
git add .squad/items/<new-file>.md
git commit -m "docs: add <ID> <title>"
(No PM-trace IDs in the commit message body — the filename carries the ID.)
npx claudepluginhub zsiec/squad --plugin squadProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.