Help us improve
Share bugs, ideas, or general feedback.
From claude-auto-context
Detect structural issues and create proposal files in .claude-auto-context/suggestions/. USE WHEN file splits, directory reorganization, or pattern unification is needed.
npx claudepluginhub getklaim/claude-auto-context --plugin claude-auto-contextHow this skill is triggered — by the user, by Claude, or both
Slash command
/claude-auto-context:create-suggestionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze session data to detect structural issues and create proposal files requiring user approval before applying.
Refactors existing code for guideline compliance and testability using 4 parallel analysis agents. Use after /optimus:init or before /optimus:unit-test to align code and remove testability barriers.
Review and apply structural suggestions from Auto Context. USE WHEN user types /cac-apply or mentions applying suggestions.
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.
Share bugs, ideas, or general feedback.
Analyze session data to detect structural issues and create proposal files requiring user approval before applying.
Structural problems evidenced by session data:
Every suggestion MUST include:
Create files in .claude-auto-context/suggestions/ as suggestion-YYYYMMDD-HHMMSS-{slug}.md:
# Suggestion: {title}
## Description
{one-line summary — used for deduplication and context display}
## Status
pending
## Created
{ISO 8601 UTC timestamp, e.g. 2026-03-27T14:30:52Z}
## Category
{ai-unfriendly-large-file | ai-unfriendly-naming | ai-unfriendly-missing-docs | ai-unfriendly-structure | ai-unfriendly-fragile}
## Problem
{Description with quantitative evidence and specific file names}
## Related Files
- {file1.ext} — {why this file is involved}
- {file2.ext} — {why this file is involved}
## Proposal
### Read first
- {file1.ext} — {why executor must read this before changes, e.g. "contains function to extract"}
- {file2.ext} — {dependency or convention reference}
### Files to modify
- {file1.ext} — {what changes in this file}
- {file2.ext (new file)} — {what this new file will contain}
### Changes
1. In {file1.ext}, function `{functionName}` (lines ~{N}-{M}):
- {specific operation: extract, rename, move, delete, modify}
- {import/export updates needed after the change}
2. In {file2.ext (new file)}:
- Create with exports: {exportName1}, {exportName2}
- Import dependencies: {dep1} from {source}
### Impact
- {other-file.ext} — imports from {file1.ext}, import path may need update
- {test-file.ext} — test assertions may reference moved functions
### Acceptance criteria
- [ ] `grep -q '{exportName}' {new-file.ext}` — export exists in new location
- [ ] `grep -q 'from.*{new-file}' {file1.ext}` — import path updated
- [ ] No TypeScript/syntax errors in modified files
- [ ] Existing tests pass without modification (or test updates documented)
## Evidence Sessions
- session_{id} ({date}): {what was observed}
## Metrics
- Signal ratio: {X}%
- Sessions affected: {N}/{total}
- Estimated impact: {description}
IMPORTANT: The ## Proposal section MUST contain all five subsections (### Read first, ### Files to modify, ### Changes, ### Impact, ### Acceptance criteria). Proposals without these subsections are incomplete and will be rejected.
Changes section rules:
Acceptance criteria rules:
grep -q 'pattern' file.claude-auto-context/suggestions/ to avoid duplicatessuggestion-YYYYMMDD-HHMMSS format using current UTC time (e.g., suggestion-20260323-143052-my-slug.md)suggestion-YYYYMMDD-HHMMSS-{slug}.md