Agent skill

Windsurf Advanced Troubleshooting

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Advanced Devin Desktop (formerly Windsurf) debugging for hard-to-diagnose IDE, Cascade, and indexing issues.

MITAuto-check passedDevelopment

Install Windsurf Advanced Troubleshooting

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-advanced-troubleshooting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace windsurf-advanced-troubleshooting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/windsurf-advanced-troubleshooting .claude/skills/windsurf-advanced-troubleshooting && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
windsurf-advanced-troubleshooting
GitHub stars
2.8k
Token cost
~2.3k tokens
SKILL.md length
273 words
Files
2 (incl. references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Advanced Devin Desktop (formerly Windsurf) debugging for hard-to-diagnose IDE, Cascade, and indexing issues.

  • Works in 6 steps: Isolate Windsurf Layer vs VS Code Layer → Debug Cascade Context Issues → Debug Indexing Problems → …
  • Standard troubleshooting fails
  • SKILL.md covers Overview, Prerequisites, Tool Use and Instructions, plus 5 more sections
  • Calls python3

What it does

Windsurf Advanced Troubleshooting is an agent skill from jeremylongshore/tons-of-skills-marketplace. Advanced Devin Desktop (formerly Windsurf) debugging for hard-to-diagnose IDE, Cascade, and indexing issues. Use when standard troubleshooting fails, Cascade produces consistently wrong output, or investigating deep configuration problems. Trigger with phrases like "windsurf deep debug", "windsurf mystery error", "windsurf impossible to fix", "cascade keeps failing", "windsurf advanced debug".

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/official-docs.md`). Compatibility notes: Designed for Claude Code

It sits in Development, covering Debugging. It works with Model Context Protocol. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Standard troubleshooting fails
  • Cascade produces consistently wrong output
  • Investigating deep configuration problems
  • With phrases like windsurf deep debug

Example prompts

  • “windsurf deep debug”
  • “windsurf mystery error”
  • “windsurf impossible to fix”
  • “/windsurf-advanced-troubleshooting”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Grep, Bash(ls:*), Bash(curl:*), Bash(find:*)

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Isolate Windsurf Layer vs VS Code Layer
  2. Debug Cascade Context Issues
  3. Debug Indexing Problems
  4. Debug Extension Conflicts
  5. Debug MCP Server Issues
  6. Nuclear Reset Options

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Bash(ls:*)
    • Bash(curl:*)
    • Bash(find:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • windsurf.com
    • status.windsurf.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Claude Code

    From compatibility in the SKILL.md frontmatter.

Context cost

Windsurf Advanced Troubleshooting loads about 2.3k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 273 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 273 words, ~2,302 tokens.

Download SKILL.mdSave it as .claude/skills/windsurf-advanced-troubleshooting/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
windsurf-advanced-troubleshooting
description
Advanced Devin Desktop (formerly Windsurf) debugging for hard-to-diagnose IDE, Cascade, and indexing issues. Use when standard troubleshooting fails, Cascade produces consistently wrong output, or investigating deep configuration problems. Trigger with phrases like "windsurf deep debug", "windsurf mystery error", "windsurf impossible to fix", "cascade keeps failing", "windsurf advanced debug".
allowed-tools
Read, Grep, Bash(ls:*), Bash(curl:*), Bash(find:*)
compatibility
Designed for Claude Code
argument-hint
[scope or requirements]
version
1.12.0
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, windsurf, debugging, advanced, troubleshooting

Windsurf Advanced Troubleshooting

Overview

Deep debugging techniques for Windsurf issues that resist standard troubleshooting. Covers Cascade context corruption, indexing engine problems, extension conflicts, MCP failures, and workspace configuration debugging.

Prerequisites

  • Standard troubleshooting attempted (see windsurf-common-errors)
  • Terminal access
  • Understanding of Devin Desktop's editor, Cascade, indexing, extension, and MCP layers

Tool Use

  • Use Read to inspect only the repository files and configuration needed for the request.
  • Use Grep to locate relevant settings, rules, logs, or code without broad collection.
  • Use only the command-scoped Bash entries declared in frontmatter, with non-destructive checks before mutations.

Instructions

Step 1: Isolate Windsurf Layer vs VS Code Layer
Devin Desktop = editor shell + Cascade + indexing/context + extension/MCP layers

If the issue is:
- Editor crashes, rendering, file system → VS Code layer
- AI suggestions wrong, Cascade fails, indexing stuck → Cascade or context/indexing layer
- Extension not working → Extension compatibility layer

Test VS Code layer:
  windsurf --disable-extensions  # Run without extensions
  # If issue persists → VS Code layer problem

Test AI and extension layers:
  # Start with extensions disabled using the documented troubleshooting flow.
  # If the issue resolves, re-enable extensions incrementally to isolate the conflict.
Step 2: Debug Cascade Context Issues

When Cascade consistently gives wrong or irrelevant suggestions:

bash
set -euo pipefail
echo "=== Cascade Context Debug ==="
readonly WORKSPACE_RULE_LIMIT=12000 # Current documented maximum for one workspace rule.
readonly GLOBAL_RULE_LIMIT=6000 # Current documented maximum for the global rule.

# 1. Check rules file
echo "--- .devin/rules/project.md ---"
if [ -f .devin/rules/project.md ]; then
  CHARS=$(wc -c < .devin/rules/project.md)
  echo "Size: $CHARS chars (workspace rule limit: $WORKSPACE_RULE_LIMIT)"
  [ "$CHARS" -gt "$WORKSPACE_RULE_LIMIT" ] && echo "WARNING: Workspace rule exceeds its limit"
else
  echo "MISSING — Cascade has no project context"
fi

# 2. Check workspace rules
echo "--- Workspace Rules ---"
TOTAL_RULE_CHARS=0
if [ -d .devin/rules ]; then
  for rule in .devin/rules/*.md; do
    [ -f "$rule" ] || continue
    CHARS=$(wc -c < "$rule")
    TOTAL_RULE_CHARS=$((TOTAL_RULE_CHARS + CHARS))
    HAS_TRIGGER=$(grep -c "^trigger:" "$rule" || true)
    echo "  $(basename "$rule"): $CHARS chars, trigger: $([[ $HAS_TRIGGER -gt 0 ]] && echo 'YES' || echo 'MISSING')"
  done
  echo "Total: $TOTAL_RULE_CHARS chars"
else
  echo "No .devin/rules/ directory"
fi

# 3. Check independent rule limits
RULES_CHARS=$(wc -c < .devin/rules/project.md 2>/dev/null || echo 0)
GLOBAL_CHARS=$(wc -c < ~/.codeium/windsurf/memories/global_rules.md 2>/dev/null || echo 0)
echo "--- Rule Limits ---"
echo "Workspace rule: $RULES_CHARS/$WORKSPACE_RULE_LIMIT chars; global rule: $GLOBAL_CHARS/$GLOBAL_RULE_LIMIT chars"
[ "$RULES_CHARS" -gt "$WORKSPACE_RULE_LIMIT" ] && echo "WARNING: Workspace rule exceeds its limit"
[ "$GLOBAL_CHARS" -gt "$GLOBAL_RULE_LIMIT" ] && echo "WARNING: Global rule exceeds its limit"

# 4. Check memories
echo "--- Memories ---"
MEMORY_DIR="$HOME/.codeium/windsurf/memories"
if [ -d "$MEMORY_DIR" ]; then
  MEMORY_COUNT=$(find "$MEMORY_DIR" -type f | wc -l)
  echo "Memory files: $MEMORY_COUNT"
  [ "$MEMORY_COUNT" -gt 50 ] && echo "WARNING: Many memories — may cause conflicting context"
else
  echo "No memories directory"
fi
Step 3: Debug Indexing Problems
bash
set -euo pipefail
echo "=== Indexing Debug ==="

# Count files that would be indexed
readonly LARGE_WORKSPACE_HEURISTIC=10000 # Diagnostic threshold, not a vendor limit.
TOTAL_FILES=$(find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | wc -l)
echo "Total files (excluding node_modules, .git): $TOTAL_FILES"

# Check for large files that slow indexing
echo "--- Large files (>1MB, not in node_modules) ---"
find . -type f -size +1M -not -path '*/node_modules/*' -not -path '*/.git/*' | head -10

# Check .codeiumignore effectiveness
if [ -f .codeiumignore ]; then
  echo "--- .codeiumignore patterns ---"
  wc -l < .codeiumignore
  echo "patterns defined"
else
  echo "WARNING: No .codeiumignore — indexing everything"
fi

# Recommendations
if [ "$TOTAL_FILES" -gt "$LARGE_WORKSPACE_HEURISTIC" ]; then
  echo ""
  echo "RECOMMENDATION: >10K files. Open a subdirectory instead of root."
  echo "RECOMMENDATION: Add more patterns to .codeiumignore"
fi
Step 4: Debug Extension Conflicts
bash
set -euo pipefail
echo "=== Extension Conflict Check ==="

# List all installed extensions
windsurf --list-extensions 2>/dev/null | while read ext; do
  # Check for known conflicts
  case "$ext" in
    *copilot*|*tabnine*|*cody*|*intellicode*|*aws-toolkit*codewhisperer*)
      echo "CONFLICT: $ext — competes with Supercomplete/Cascade"
      ;;
    *remote*|*liveshare*|*container*)
      echo "OK: $ext — compatible but may affect performance"
      ;;
    *)
      echo "OK: $ext"
      ;;
  esac
done

echo ""
echo "Resolution: Disable conflicting extensions or run:"
echo "  windsurf --disable-extensions  # Test in clean mode"
Step 5: Debug MCP Server Issues
bash
set -euo pipefail
echo "=== MCP Debug ==="

MCP_CONFIG="$HOME/.codeium/windsurf/mcp_config.json"
if [ -f "$MCP_CONFIG" ]; then
  echo "MCP config exists"
  # Validate JSON
  python3 -c "import json; json.load(open('$MCP_CONFIG'))" 2>&1 && echo "JSON: valid" || echo "JSON: INVALID"

  # Check each server command
  python3 -c "
import json
config = json.load(open('$MCP_CONFIG'))
for name, server in config.get('mcpServers', {}).items():
    cmd = server.get('command', 'N/A')
    print(f'  {name}: command={cmd}')
  "
else
  echo "No MCP config at $MCP_CONFIG"
fi
Step 6: Nuclear Reset Options

When nothing else works:

markdown
## Progressive Reset (least to most destructive)

1. Restart Cascade
   Command Palette > "Cascade: Restart"

2. Reset Indexing
   Download diagnostics, then use the current indexing control in Settings.

3. Reload Window
   Cmd/Ctrl+Shift+P > "Developer: Reload Window"

4. Review Memories and Rules
   Export or record needed customizations, then remove only the confirmed bad item through the UI.

5. Re-authenticate
   Sign out and back in only after preserving diagnostics and confirming the organization.

6. Clean Install
   Follow the current support instructions for the operating system. Back up settings first; do not recursively delete the entire Codeium/Devin state tree from a generic runbook.

Output

Return a diagnostic report with the isolated failing layer, commands and evidence collected, the least-destructive corrective action, validation results, and any remaining escalation data. Redact credentials, tokens, repository content, and personal paths before sharing the report.

Error Handling

IssueCauseSolution
Cascade gives contradictory adviceConflicting memoriesClear old memories
Rules ignoredOver 12K combined charsTrim rules, check total budget
Wrong file suggestionsStale indexReset indexing
Slow after updateExtension incompatibilityTest with --disable-extensions
MCP tools missingConfig JSON invalidValidate with python3 json parser
Everything brokenCorrupted stateProgressive reset (Step 6)

Examples

Quick Diagnostic One-Liner
bash
echo "WS files: $(find . -not -path '*/node_modules/*' -not -path '*/.git/*' -type f | wc -l) | Rules: $(wc -c < .devin/rules/project.md 2>/dev/null || echo 0)c | Ignore: $(wc -l < .codeiumignore 2>/dev/null || echo 0) patterns | Exts: $(windsurf --list-extensions 2>/dev/null | wc -l)"
Submit Support Ticket
markdown
Attach:
1. Output from all diagnostic scripts above
2. Debug bundle from windsurf-debug-bundle
3. Exact prompts that produce wrong results
4. Expected vs actual Cascade behavior

Resources

Continue with windsurf-load-scale when the diagnosis shows workspace size, indexing scope, or organization rollout is the limiting factor.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/.curated/windsurf-advanced-troubleshooting of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • references/official-docs.md

Open the folder on GitHubat commit cfae287

Compare with similar skills

Windsurf Advanced Troubleshooting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Windsurf Advanced Troubleshooting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Windsurf Advanced Troubleshooting this skilljeremylongshore/tons-of-skills-marketplace2.8k—~2.3kAutomated safety check: PassMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence
LangBot Plugin Developmentlangbot-app/LangBot18k—~3.9kAutomated safety check: PassApache-2.0
Graph-Based Bug Tracingtirth8205/code-review-graph32k1 repos~287Automated safety check: PassMIT
Extension Puppeteer Debuggingmengxi-ream/read-frog10k—~2kAutomated safety check: NotesGPL-3.0
Octocode Code Researchbgauryy/octocode949—~1.5kAutomated safety check: PassMIT

Similar skills

  • Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • LangBot Plugin Development

    langbot-app/LangBot

    Guides building, debugging and testing LangBot plugins: components, SDK calls, README and locale rules, SDK pitfalls and WebSocket-based testing.

    18k GitHub stars~3.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Graph-Based Bug Tracing

    tirth8205/code-review-graph

    Traces a bug through a code knowledge graph, following callers, callees and execution flow before opening source files, within a small token budget.

    32k GitHub starsUsed in 1 repo~287 tokens
    DevelopmentAuto-check passed
  • Extension Puppeteer Debugging

    mengxi-ream/read-frog

    Debug the built Read Frog extension in real Chrome. An agent skill from mengxi-ream/read-frog.

    10k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check: notes
  • Octocode Code Research

    bgauryy/octocode

    Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.

    949 GitHub stars~1.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • LinkedIn MCP Issue Investigator

    stickerdaniel/linkedin-mcp-server

    Investigates a reported LinkedIn-MCP issue by matching the reporter's tool call to the exact source file and tests, without applying a fix.

    3.8k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Categories

Questions about Windsurf Advanced Troubleshooting

What does Windsurf Advanced Troubleshooting do?

Advanced Devin Desktop (formerly Windsurf) debugging for hard-to-diagnose IDE, Cascade, and indexing issues. Windsurf Advanced Troubleshooting is an agent skill from jeremylongshore/tons-of-skills-marketplace. Advanced Devin Desktop (formerly Windsurf) debugging for hard-to-diagnose IDE, Cascade, and indexing issues.

When should I use Windsurf Advanced Troubleshooting?

Windsurf Advanced Troubleshooting fits situations like: standard troubleshooting fails; cascade produces consistently wrong output; investigating deep configuration problems; with phrases like windsurf deep debug.

How do I install Windsurf Advanced Troubleshooting in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-advanced-troubleshooting -a claude-code`. Or copy the skill folder (skills/.curated/windsurf-advanced-troubleshooting in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/windsurf-advanced-troubleshooting in your project. Claude Code loads it when a task matches its description.

How do I install Windsurf Advanced Troubleshooting in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-advanced-troubleshooting -a codex`. Or copy the skill folder (skills/.curated/windsurf-advanced-troubleshooting in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/windsurf-advanced-troubleshooting in your project. Codex loads it when a task matches its description.

Can I use Windsurf Advanced Troubleshooting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-advanced-troubleshooting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/windsurf-advanced-troubleshooting, .gemini/skills/windsurf-advanced-troubleshooting, .github/skills/windsurf-advanced-troubleshooting and .opencode/skills/windsurf-advanced-troubleshooting in your project.

What does Windsurf Advanced Troubleshooting need to run?

Going by SKILL.md and its folder, Windsurf Advanced Troubleshooting needs the command-line tools its instructions call (python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Grep, Bash(ls:*), Bash(curl:*), Bash(find:*). Compatibility (from SKILL.md): Designed for Claude Code.

Does Windsurf Advanced Troubleshooting access the network?

SKILL.md names 2 domains. As links in the text: windsurf.com and status.windsurf.com. This is read from the text; nothing was executed.

Is Windsurf Advanced Troubleshooting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Windsurf Advanced Troubleshooting use?

Windsurf Advanced Troubleshooting is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Windsurf Advanced Troubleshooting use?

About 2.3k tokens (SKILL.md is roughly 9.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 108 tokens, read only when the agent opens those files.

What are the alternatives to Windsurf Advanced Troubleshooting?

Skills that share tags, products or a category with Windsurf Advanced Troubleshooting: Debugging Executions (n8n-io/n8n, 207k stars), LangBot Plugin Development (langbot-app/LangBot, 18k stars), Graph-Based Bug Tracing (tirth8205/code-review-graph, 32k stars) and Extension Puppeteer Debugging (mengxi-ream/read-frog, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Windsurf Advanced Troubleshooting?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.