Agent skill

Clay Advanced Troubleshooting

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

Deep-debug complex Clay enrichment failures, provider degradation, and data flow issues.

MITAuto-check passedDevelopment

Install Clay Advanced Troubleshooting

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

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

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace clay-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/clay-advanced-troubleshooting .claude/skills/clay-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
clay-advanced-troubleshooting
GitHub stars
2.8k
Token cost
~2.3k tokens
SKILL.md length
287 words
Files
2 (incl. references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Deep-debug complex Clay enrichment failures, provider degradation, and data flow issues.

  • Works in 5 steps: Isolate the Failure Layer → Diagnose Enrichment Column Failures → Debug HTTP API Column Issues → …
  • Standard troubleshooting fails
  • SKILL.md covers Overview, Prerequisites, Instructions and Error Handling, plus 4 more sections
  • Calls curl and jq; reaches community.clay.com and api.clay.com; needs CLAY_API_KEY

What it does

Clay Advanced Troubleshooting is an agent skill from jeremylongshore/tons-of-skills-marketplace. Deep-debug complex Clay enrichment failures, provider degradation, and data flow issues. Use when standard troubleshooting fails, investigating intermittent enrichment failures, or preparing detailed evidence for Clay support escalation. Trigger with phrases like "clay hard bug", "clay mystery error", "clay impossible to debug", "difficult clay issue", "clay deep 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/implementation-guide.md`). Compatibility notes: Designed for Claude Code

It sits in Development. 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
  • Investigating intermittent enrichment failures
  • Preparing detailed evidence for Clay support escalation
  • With phrases like clay hard bug

Example prompts

  • “clay hard bug”
  • “clay mystery error”
  • “clay impossible to debug”
  • “/clay-advanced-troubleshooting”

Requirements

  • A credential in CLAY_API_KEY
  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Grep, Bash(curl:*), Bash(node:*)

Workflow steps

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

  1. Isolate the Failure Layer
  2. Diagnose Enrichment Column Failures
  3. Debug HTTP API Column Issues
  4. Debug Claygent Failures
  5. Build a Support Escalation Package

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(curl:*)
    • Bash(node:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • jq

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • community.clay.com
    • api.clay.com
    • api.hubapi.com

    Also links to:

    • university.clay.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • CLAY_API_KEY

    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

Clay Advanced Troubleshooting loads about 2.3k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 287 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
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
~3.4k

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). 287 words, ~2,297 tokens.

Download SKILL.mdSave it as .claude/skills/clay-advanced-troubleshooting/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
clay-advanced-troubleshooting
description
Deep-debug complex Clay enrichment failures, provider degradation, and data flow issues. Use when standard troubleshooting fails, investigating intermittent enrichment failures, or preparing detailed evidence for Clay support escalation. Trigger with phrases like "clay hard bug", "clay mystery error", "clay impossible to debug", "difficult clay issue", "clay deep debug".
allowed-tools
Read, Grep, Bash(curl:*), Bash(node:*)
compatibility
Designed for Claude Code
version
1.14.0
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, clay, debugging, scaling

Clay Advanced Troubleshooting

Overview

Deep debugging techniques for complex Clay issues that resist standard troubleshooting. Covers provider-level isolation, waterfall diagnosis, HTTP API column debugging, Claygent failure analysis, and Clay support escalation with proper evidence.

Prerequisites

  • Access to Clay table with the failing enrichments
  • curl and jq for API testing
  • Understanding of Clay's enrichment architecture (providers, waterfall, columns)
  • Browser developer tools for network inspection

Instructions

Step 1: Isolate the Failure Layer
bash
#!/bin/bash
# clay-layer-test.sh — test each integration layer independently
set -euo pipefail

echo "=== Layer Isolation Test ==="

# Layer 1: Webhook delivery
echo "Layer 1: Webhook"
WEBHOOK_CODE=$(curl -s -o /dev/null -w "%{http_code}" \
  -X POST "$CLAY_WEBHOOK_URL" \
  -H "Content-Type: application/json" \
  -d '{"_debug": true, "domain": "google.com"}')
echo "  Webhook: $WEBHOOK_CODE"

# Layer 2: Enterprise API (if applicable)
if [ -n "${CLAY_API_KEY:-}" ]; then
  echo "Layer 2: Enterprise API"
  API_RESULT=$(curl -s -X POST "https://api.clay.com/v1/companies/enrich" \
    -H "Authorization: Bearer $CLAY_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"domain": "google.com"}')
  echo "  API response keys: $(echo "$API_RESULT" | jq 'keys')"
fi

# Layer 3: HTTP API callback endpoint
echo "Layer 3: Callback endpoint"
CALLBACK_CODE=$(curl -s -o /dev/null -w "%{http_code}" \
  -X POST "${CLAY_CALLBACK_URL:-http://localhost:3000/api/clay/enriched}" \
  -H "Content-Type: application/json" \
  -d '{"_debug_test": true}')
echo "  Callback: $CALLBACK_CODE"

echo ""
echo "First failing layer = root cause location"
Step 2: Diagnose Enrichment Column Failures

In the Clay UI, click on red/error cells to see detailed error messages:

yaml
# Common enrichment column error patterns and root causes:
errors:
  "No data found":
    meaning: "Provider has no data for this input"
    check:
      - Is the input domain valid? (not personal email domain)
      - Is the input name spelled correctly?
      - Is the provider connected? (Settings > Connections)
    fix: "Add more waterfall providers for broader coverage"

  "Rate limit exceeded":
    meaning: "Provider API rate limit hit"
    check:
      - How many rows are processing simultaneously?
      - Is the provider's rate limit known? (see provider docs)
    fix: "Reduce table row count, add delay between batches"

  "Invalid API key":
    meaning: "Provider connection lost or key expired"
    check:
      - Go to Settings > Connections
      - Click on the failing provider
      - Test the connection
    fix: "Reconnect with a valid API key"

  "Timeout":
    meaning: "Provider took too long to respond"
    check:
      - Is the provider's status page showing issues?
      - Is the input data unusually complex?
    fix: "Retry the column on failed rows (click cell > retry)"

  "Column dependency not met":
    meaning: "A column this enrichment depends on hasn't completed yet"
    check:
      - Check column order (left to right execution)
      - Is the prerequisite column populated?
    fix: "Reorder columns so dependencies run first"
Step 3: Debug HTTP API Column Issues
typescript
// debug/http-api-column.ts — replicate Clay's HTTP API column call locally
async function debugHTTPAPIColumn(
  url: string,
  method: string,
  headers: Record<string, string>,
  body: Record<string, string>,
  sampleRow: Record<string, string>,
): Promise<void> {
  // Replace {{column_name}} placeholders with sample data
  let resolvedUrl = url;
  let resolvedBody = JSON.stringify(body);

  for (const [key, value] of Object.entries(sampleRow)) {
    const placeholder = `{{${key}}}`;
    resolvedUrl = resolvedUrl.replace(placeholder, value);
    resolvedBody = resolvedBody.replace(new RegExp(placeholder.replace(/[{}]/g, '\\$&'), 'g'), value);
  }

  console.log('Resolved URL:', resolvedUrl);
  console.log('Resolved body:', JSON.parse(resolvedBody));

  const res = await fetch(resolvedUrl, {
    method,
    headers: { ...headers, 'Content-Type': 'application/json' },
    body: method !== 'GET' ? resolvedBody : undefined,
  });

  console.log('Status:', res.status);
  console.log('Response:', await res.text());
}

// Test with your actual column config and sample row data
await debugHTTPAPIColumn(
  'https://api.hubapi.com/crm/v3/objects/contacts',
  'POST',
  { 'Authorization': 'Bearer your-hubspot-key' },
  { email: '{{Work Email}}', firstname: '{{first_name}}' },
  { 'Work Email': 'test@example.com', 'first_name': 'Jane' },
);
Step 4: Debug Claygent Failures

Common Claygent issues and diagnosis:

yaml
claygent_debugging:
  empty_results:
    symptom: "Claygent returns empty or 'Could not find information'"
    diagnosis:
      - Test the prompt manually in Clay's Claygent builder (click cell > edit)
      - Try the URL in a browser — is the website accessible?
      - Check if the website blocks bots (CloudFlare challenge page)
    fixes:
      - Use Navigator mode for JavaScript-heavy sites
      - Simplify the prompt to a single question
      - Add fallback sources: "If not on the website, check LinkedIn/Crunchbase"

  inconsistent_results:
    symptom: "Same prompt returns different data each time"
    diagnosis:
      - Claygent uses web search which can vary
      - Dynamic website content changes between requests
    fixes:
      - Make prompts more specific (exact page URL vs general domain)
      - Add structured output format: "Return as JSON with keys: funding_amount, date, investors"

  high_credit_cost:
    symptom: "Claygent consuming too many credits"
    diagnosis:
      - Each Claygent call costs credits + 1 action
      - Running on all rows including low-value ones
    fixes:
      - Add conditional run: "Only run if ICP Score >= 60"
      - Cache results: don't re-run on already-researched companies
Step 5: Build a Support Escalation Package
markdown
## Clay Support Escalation

**Account:** [your email]
**Plan:** [Starter/Explorer/Pro/Enterprise]
**Date:** [YYYY-MM-DD]

### Issue Description
[One paragraph describing what's broken]

### Impact
- Rows affected: [count]
- Duration: [how long has this been happening]
- Credits impacted: [estimated wasted credits]

### Steps to Reproduce
1. [Step 1]
2. [Step 2]
3. [Expected result vs actual result]

### Evidence
- Table URL: [link to affected Clay table]
- Screenshot of error cells: [attached]
- Column configuration: [which enrichment, which provider]
- Sample input data that fails: [3-5 rows]
- Sample input data that works: [3-5 rows for comparison]

### What I've Already Tried
1. [Reconnected provider API key]
2. [Tested with different input data]
3. [Checked Clay status page — no incidents reported]
4. [Tested provider API independently — works fine]

### Environment
- Browser: [Chrome/Firefox/Safari + version]
- Plan tier: [with credit balance]
- Provider connections: [list connected providers]

Submit at: https://community.clay.com or support@clay.com

Error Handling

IssueCauseSolution
Intermittent enrichment failuresProvider rate limitingReduce concurrent rows, add delay
All rows failing suddenlyProvider API key expiredReconnect in Settings > Connections
Partial data returnedProvider has limited coverageAdd waterfall fallback provider
HTTP API column timeoutTarget API slowIncrease timeout or process async
Claygent blocked by websiteBot protectionUse Navigator mode or different data source

Output

Produce a redacted escalation packet with environment, table/column scope, symptom, safe correlation IDs, impact metrics, reproducer, containment action, and case owner. Remove webhook URLs, API keys, raw lead/CRM data, and any unapproved screenshots or samples before sharing the packet externally.

Examples

For a provider-wide failure, first reduce or pause affected automation, compare a synthetic input against the failing job, and collect the sanitized status and time window for support. If the issue only occurs for personal data or a restricted source, do not attach those rows; use a permitted representative or escalate through the data owner.

Resources

Next Steps

For high-volume scaling, see clay-load-scale.

© 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/clay-advanced-troubleshooting of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • references/implementation-guide.md

Open the folder on GitHubat commit cfae287

Compare with similar skills

Clay 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.

Clay Advanced Troubleshooting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Clay Advanced Troubleshooting this skilljeremylongshore/tons-of-skills-marketplace2.8k—~2.3kAutomated safety check: PassMIT
Backend Code Reviewlanggenius/dify158k—~676Automated safety check: PassCustom licence
Native Data FetchingCherryHQ/cherry-studio-app4k6 repos~2.9kAutomated safety check: NotesMIT
Twenty App Entity Developmenttwentyhq/twenty58k—~1.8kAutomated safety check: PassCustom licence
Go Pedantrychromedp/chromedp13k—~3.7kAutomated safety check: PassMIT
Gumroad Prod Consoleantiwork/gumroad9.8k—~2.9kAutomated safety check: NotesMIT

Similar skills

  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed
  • Native Data Fetching

    CherryHQ/cherry-studio-app

    A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.

    4k GitHub starsUsed in 6 repos~2.9k tokens
    DevelopmentAuto-check: notes
  • Guides changes to an existing Twenty app: adding or editing objects, layouts, logic functions and front components, with a plan stated before multi-entity edits.

    58k GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Go Pedantry

    chromedp/chromedp

    This skill should be used when the user is writing Go code and needs guidance on Go-specific pedantry: error wrapping with fmt.Errorf and %w, interface design (accept interfaces return structs)…

    13k GitHub stars~3.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Gumroad Prod Console

    antiwork/gumroad

    Execute read-only Ruby/Rails commands against Gumroad's production database for debugging and investigation.

    9.8k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check: notes
  • 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

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

Questions about Clay Advanced Troubleshooting

What does Clay Advanced Troubleshooting do?

Deep-debug complex Clay enrichment failures, provider degradation, and data flow issues. Clay Advanced Troubleshooting is an agent skill from jeremylongshore/tons-of-skills-marketplace. Deep-debug complex Clay enrichment failures, provider degradation, and data flow issues.

When should I use Clay Advanced Troubleshooting?

Clay Advanced Troubleshooting fits situations like: standard troubleshooting fails; investigating intermittent enrichment failures; preparing detailed evidence for Clay support escalation; with phrases like clay hard bug.

How do I install Clay Advanced Troubleshooting in Claude Code?

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

How do I install Clay Advanced Troubleshooting in Codex?

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

Can I use Clay 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 clay-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/clay-advanced-troubleshooting, .gemini/skills/clay-advanced-troubleshooting, .github/skills/clay-advanced-troubleshooting and .opencode/skills/clay-advanced-troubleshooting in your project.

What does Clay Advanced Troubleshooting need to run?

Going by SKILL.md and its folder, Clay Advanced Troubleshooting needs the command-line tools its instructions call (curl and jq) and credentials named CLAY_API_KEY. Our summary lists: A credential in CLAY_API_KEY. Its frontmatter pre-approves these tools: Read, Grep, Bash(curl:*), Bash(node:*). Compatibility (from SKILL.md): Designed for Claude Code.

Does Clay Advanced Troubleshooting access the network?

SKILL.md names 4 domains. In commands or code: community.clay.com, api.clay.com and api.hubapi.com; the agent is likely to contact these when it follows the instructions. As links in the text: university.clay.com. This is read from the text; nothing was executed.

Is Clay 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 Clay Advanced Troubleshooting use?

Clay 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 Clay 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 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Clay Advanced Troubleshooting?

Skills that share tags, products or a category with Clay Advanced Troubleshooting: Backend Code Review (langgenius/dify, 158k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Twenty App Entity Development (twentyhq/twenty, 58k stars) and Go Pedantry (chromedp/chromedp, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Clay 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.