From signal
Review code in SIGNAL's one-line format with required severity per issue. Output is typed, structured, and chainable — not prose paragraphs. Use when user types /signal-review, "review this", "review my code", "check this PR", "review this file", or asks for a code review on any file, diff, or PR. Works standalone or as part of a SIGNAL session.
How this skill is triggered — by the user, by Claude, or both
Slash command
/signal:signal-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
One line per issue. Severity required. Summary at the end. No prose.
One line per issue. Severity required. Summary at the end. No prose.
Activate when user says any of:
/signal-review"review this", "review my code", "review this file""check this PR", "code review", "look at this diff""what's wrong with this", "any issues with this code"Target can be: a file, a diff, a PR URL, a code block, or the current working directory.
If the user's message is only /signal-review, treat that as review now.
One line per issue:
{file}:{line}|{issue}|{severity:1-5}|{fix}
Full example:
auth.js:47|nullref on empty arr|4|add guard clause before map
api.js:103|missing await on async call|5|add await
utils.js:12|unused import lodash|1|remove import
∑ 3 issues [1×sev5, 1×sev4, 1×sev1] critical→api.js:103
Rules:
∑ {N} issues [{breakdown}] critical→{highest-sev-location}
Examples:
∑ 5 issues [2×sev5, 1×sev3, 2×sev1] critical→auth.js:47
∑ 1 issue [1×sev2]
∑ 0 issues ✓
If zero issues: output only ∑ 0 issues ✓. No explanation, no praise.
Full definitions in references/severity.md. Quick reference:
| Level | Meaning |
|---|---|
5 | Breaks in production, security vulnerability, data loss |
4 | Likely runtime error, will crash under normal use |
3 | Wrong behavior under specific conditions, logic error |
2 | Code smell, maintainability issue, confusing pattern |
1 | Style, minor cleanup, nitpick |
Severity assignment rule: Assign based on impact when triggered, not probability of triggering. A SQL injection that only fires on a specific input is still sev5.
In order of priority:
If the user doesn't specify what to review:
git diff HEAD)gh pr diff {url} and review| Flag | Behavior |
|---|---|
--quick | Sev3+ only. Skip style and nitpicks. |
--security | Security-focused pass only. |
--sev {N} | Only report issues at severity N or above. |
--fix | After listing issues, output the corrected code block. |
--fix output:
List all issues first, then output the corrected file or function in a single code block. Do not mix issue lines with code.
When reviewing multiple files, group by file:
auth.js:
auth.js:47|nullref on empty arr|4|add guard clause before map
auth.js:89|hardcoded secret|5|move to env var
api.js:
api.js:103|missing await|5|add await
∑ 3 issues [2×sev5, 1×sev4] critical→api.js:103
The summary line covers all files combined.
If BOOT:review is active (see signal/references/boot-presets.md):
TMPL:revseverity_required∑ lineSIGNAL_DRIFT: <one-line reason> instead of falling back to proseIf SIGNAL is not active, still use this format. The template is the default for this skill regardless of SIGNAL mode.
This skill's own output must comply with SIGNAL compression rules if SIGNAL is active:
∑ 0 issues ✓∑ summaryGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub mattbaconz/signal --plugin signal