packages/forge/src/skills/fix-and-learn/SKILL.md
Use AFTER a root cause has been identified (typically via systematic-debugging) to execute the fix and capture the learning in the vault. Triggers on "fix it", "apply the fix", "patch this and remember". Do NOT use as the first response to a bug — use systematic-debugging first to find root cause.
npx skillsauth add adrozdenko/soleri fix-and-learnInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Fix bugs through a structured recovery workflow, then capture the root cause as a reusable anti-pattern. The learning step makes fixes compound across sessions.
Never jump to writing code. Always follow this lookup order:
YOUR_AGENT_core op:route_intent
params: { prompt: "<bug description>" }
YOUR_AGENT_core op:search_intelligent
params: { query: "<error message or bug description>" }
YOUR_AGENT_core op:memory_search
params: { query: "<bug description>" }
If vault returns a high-confidence match — use it. Don't re-investigate solved problems.
If vault has no answer, search for known issues, Stack Overflow answers, GitHub issues, official docs.
YOUR_AGENT_core op:loop_start
params: { prompt: "Fix: <bug description>", mode: "custom" }
If Steps 2-3 didn't produce a solution, use systematic-debugging skill:
Run test suite. Use verification-before-completion skill. Complete loop: YOUR_AGENT_core op:loop_complete.
YOUR_AGENT_core op:capture_knowledge
params: {
title: "<bug title>",
description: "<root cause, solution, what made it hard to find>",
type: "anti-pattern",
category: "<domain>",
tags: ["<error-type>", "<component>"]
}
Run YOUR_AGENT_core op:curator_detect_duplicates to avoid redundant entries.
Bug resolved, tests pass, root cause captured in vault. A fix without a capture is incomplete.
Do NOT rationalize away failures. A fix is not done until it is proven done.
| Op | When to Use |
| ----------------------------------------------- | -------------------------- |
| route_intent | Classify as FIX intent |
| search_intelligent | Check vault for known bugs |
| memory_search | Search session memories |
| loop_start / loop_iterate / loop_complete | Iterative fix cycle |
| capture_knowledge / capture_quick | Persist anti-pattern |
| curator_detect_duplicates | Prevent redundant entries |
testing
Triggers: "terse mode", "be brief", "less tokens", "fewer tokens", "compress output", "caveman", or invokes /terse. Token-efficient responses with full technical accuracy.
tools
Triggers: "compress this file", "compress CLAUDE.md", "compress memory", "shrink this", "reduce tokens in file", or invokes /compress. Compresses natural language files to save input tokens.
testing
Triggers: "release", "bump version", "publish packages", "cut a release", "version bump", "npm publish". Bumps monorepo versions, commits, tags, pushes to trigger CI release. Use deliver-and-ship for quality gates.
development
Triggers: "implement X", "build Y", "fix Z", "add feature", or any work task needing planning + execution. Full orchestration loop: plan, execute, complete with vault context and brain recs.