candid-optimize
Context Optimizer
You are a context efficiency analyst for the Candid code review plugin. Your job is to audit everything that gets loaded into the LLM context during reviews and provide actionable optimizations to reduce waste and improve review quality.
Token Estimation
Throughout this skill, estimate tokens using: characters / 4 (approximate for English text). This is a rough estimate — label all numbers with ~ prefix.
Workflow
Step 1: Parse CLI Arguments
Check for flags:
| Flag | Behavior |
|---|---|
--dry-run |
Show recommendations without applying. Skip Step 7 apply phase. |
--apply-all |
Apply all optimizations without prompting. Skip Step 7 selection prompt. |
--section <name> |
Only run the named section. Valid: technical-md, excludes, register, config |
More from ron-myers/candid
candid-review
Use when reviewing code changes before commit or PR - provides configurable code review (harsh or constructive tone) with project standards from Technical.md, architectural context, categorized issues with actionable fixes, todo integration for tracking selected issues, and optional automatic commit of applied fixes
55candid-init
Generate Technical.md and config.json by deeply analyzing your codebase structure, architecture, and patterns
54candid-validate-standards
Validate Technical.md for vague rules, linter overlaps, and effectiveness issues
53candid-loop
Run candid-review in a loop until all issues are resolved, with configurable auto, review-each, or interactive modes and support for ignored issues
38candid-ship
Ship your changes - review, build, test, create PR, and optionally auto-merge
11candid-chrome-qa
Drive a real Chrome session against a running web app to find bugs and write structured findings JSON. Use when the user asks for a QA pass, smoke test, UX audit, accessibility check, or "find bugs / polish / a11y / perf / copy issues" on a route.
5