复制安装命令
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
A model-agnostic agent-skills platform.
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
来源文件:README.md
A model-agnostic agent-skills platform. The canonical layer is harness-free by construction; Claude Code is currently the verified-native harness. Other harnesses remain engineering candidates until their native-path integration is verified; source research alone is never presented as public support.
Version semantics: the release badge is this marketplace's display version. npm packages, including the
ccpiCLI and publishable plugins, retain their own package versions; they are intentionally not expected to equal the display version. The version-surface checker governs the display surfaces without rewriting package semver.
Inside Claude Code, one command installs the whole marketplace:
/plugin marketplace add jeremylongshore/claude-code-plugins
Or use the CLI:
pnpm add -g @intentsolutionsio/ccpi
ccpi install devops-automation-pack
Browse the marketplace · Explore plugins · Download bundles
Killer Skill of the Week — no-ai-slop by Peter Yang
Strip AI slop from any draft — named-pattern edits that keep the writer's real voice
no-ai-slop does two jobs and refuses to fake a third. In Edit mode it makes the minimum effective edit — cutting throat-clearing, weak verbs, and abstract nouns while deliberately preserving the writer's cadence, bluntness, humor, and honest admissions, so a rough draft still sounds like the same person afterward. In Detect mode it names each AI-slop pattern it finds, quotes the offending line, and gives the fix in a few words — and pointedly does NOT score the draft or guess whether an AI wrote it. That restraint is the whole point: AI detectors guess; named patterns are evidence the reader can check. MIT-licensed, single focused skill, actively maintained by Peter Yang.
"AI detectors guess. Named patterns are evidence the user can check." — Peter Yang
Grade: A | Week of July 22, 2026 (W30) | View on GitHub
Previous picks: tonone, mnemos, databricks-pack, kobiton-automate, skyvern, code-cleanup, web-analytics, token-optimizer, executive-assistant-skills, skill-creator, cursor-pack, crypto-portfolio-tracker. See all at tonsofskills.com.
Every number below names the cohort it counts and the command that reproduces it — an unlabeled count is how a corpus ends up with five contradictory answers to "how many skills."
| Count | Cohort | Reproduce with |
|---|---|---|
| 442 | catalog plugins (catalog-entry cohort) | node scripts/generate-readme-toc.mjs over marketplace.extended.json |
| 3,067 | marketplace-visible skills (distinct) | node -e "import('./scripts/corpus-resolver.mjs').then(m=>console.log(m.resolveCorpus('marketplace-visible').length))" |
| 347 | agent definitions in plugins | git ls-files 'plugins/**' | grep '/agents/.*\.md' |
| 19 | plugin categories | ls -d plugins/*/ |
Across 396 published packages in the claude-code-plugins namespace. Updated daily by GitHub Actions.
| Window | All packages | Established (>30d) |
|---|---|---|
| Last 24 hours | 962 | 962 |
| Last 7 days | 2,920 | 2,916 |
| Last 30 days | 12,868 | 12,779 |
"Established" excludes packages first published within the last 30 days, so a bulk-publish event doesn't dominate the headline.
Top 10 by last 30 days:
Last refreshed 2026-08-19T03:03:05.709Z.
Five real questions, five doors — each resolves to a live, generated surface, never a hand-maintained list:
The 19 categories below link into the live marketplace. Plugin counts are the catalog-entry cohort — regenerated from marketplace.extended.json by this generator; the catalog itself lives on tonsofskills.com, never in this file (§ 6A of the platform blueprint).
| Category | Plugins | |
|---|---|---|
| 🤖 | AI & Machine Learning | 36 |
| 🎭 | AI Agents & Agency | 10 |
| 🔌 | API Development | 26 |
| 💼 | Business Tools | 6 |
| 👥 | Community | 21 |
| ₿ | Crypto & Web3 | 27 |
| 💾 | Database | 26 |
| 🎨 | Design | 2 |
| 🔧 | DevOps & Infrastructure | 36 |
| 📚 | Examples & Templates | 5 |
| 🧩 | MCP Servers | 16 |
| 📦 | Packages | 5 |
| ⚡ | Performance | 25 |
| ✅ | Productivity | 30 |
| 🎁 | SaaS Skill Packs | 106 |
| 🔐 | Security | 27 |
| ✨ | Skill Enhancers | 9 |
| 🧪 | Testing | 28 |
| 📁 | Analytics | 1 |
Four artifact classes live in this repository, distinguished on sight and never blurred — provenance is a truth requirement here, not a UX nicety:
| Class | What it is | How the reader can tell |
|---|---|---|
| Canonical skill | First-party, harness-free, the source of truth | No .source.json in its plugin directory |
| Generated adapter | A thin, machine-produced harness projection | Lives under a generated path with a "generated — do not edit" header |
| First-party package | An Intent Solutions distribution (npm, cowork zip) | @intentsolutionsio scope, IS-authored license |
| Upstream mirror | Somebody else's work, hosted mirror-by-default | .source.json present — upstream author, license, and pinned commit recorded |
Not yet certified. The certification program (tiers T0–T4 with retained, hash-matched evidence) is a later epic of the platform blueprint; until its report exists, no artifact on this surface claims a tier. This line is rendered from the absence of certification-report.json — honestly, not cosmetically.
Start with the contribution guide, then the intake and review standards every submission passes through:
External plugins are hosted mirror-by-default: the contributor's repository stays the source of truth, every mirrored source is pinned in a content lockfile, and upstream credit — author, license, resolved commit — is recorded in the mirror itself. Improvements flow by upstreaming to the author's repository, never by silently editing the mirror. The full decision record is the external-sync model.
MIT for the repository scaffolding and first-party tooling; each plugin carries its own license in its manifest, and mirrored plugins keep their upstream license verbatim.
name: clay-common-errors
description: 'Diagnose and fix the most common Clay errors and integration issues.
Use when encountering Clay errors, debugging failed enrichments,
or troubleshooting webhook delivery problems.
Trigger with phrases like "clay error", "fix clay", "clay not working",
"debug clay", "clay enrichment failed", "clay webhook error".
'
allowed-tools: Read, Grep, Bash(curl:*)
version: 1.14.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- clay
- debugging
compatibility: Designed for Claude CodeQuick reference for the top 12 most common Clay errors across webhooks, enrichment columns, HTTP API columns, Claygent, and CRM integrations. Each error includes the exact symptom, root cause, and fix.
Symptom: Data sent to webhook URL but rows never appear in table.
Cause: Invalid JSON payload or missing Content-Type header.
Fix:
# Always include Content-Type header
curl -X POST "$CLAY_WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{"email": "test@example.com", "domain": "example.com"}'
# Validate JSON before sending
echo '{"email": "test@example.com"}' | jq . || echo "Invalid JSON!"
Symptom: 404 Not Found when POSTing to webhook URL.
Cause: Table was deleted, webhook was replaced, or URL was copied incorrectly.
Fix: Open the Clay table, click + Add > Webhooks > Monitor webhook, and re-copy the URL. Each table has a unique webhook ID.
Symptom: Enrichment column returns empty for most rows.
Cause: Input data quality is poor (personal email domains, invalid domains, missing fields).
Fix:
// Pre-validate before sending to Clay
const personalDomains = ['gmail.com', 'yahoo.com', 'hotmail.com', 'outlook.com', 'icloud.com'];
function isEnrichable(row: { domain?: string; email?: string }): boolean {
if (!row.domain || !row.domain.includes('.')) return false;
if (personalDomains.some(d => row.domain!.endsWith(d))) return false;
if (row.email && personalDomains.some(d => row.email!.endsWith(d))) return false;
return true;
}
Symptom: Enrichment stops mid-table with credit error.
Cause: Monthly credit allowance exhausted.
Fix: Check credit balance in Settings > Plans & Billing. Options:
Symptom: Webhook stops accepting new submissions silently.
Cause: Each webhook source has a hard limit of 50,000 submissions.
Fix: Create a new webhook source on the same table. The 50K limit persists even after deleting rows -- you must create a fresh webhook.
Symptom: Red error indicator on HTTP API enrichment column cells.
Cause: Target API URL is wrong, auth header is incorrect, or response format unexpected.
Fix:
curl -X POST "https://api.example.com/endpoint" \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"test": "data"}'
Symptom: Claygent column returns empty or generic responses.
Cause: Prompt is too vague, company is too small/private, or website blocks bots.
Fix:
Symptom: Credits consumed on rows that were already enriched.
Cause: Table-level auto-update is ON and a column was edited, triggering re-enrichment.
Fix: Go to Table Settings and toggle auto-update OFF at the table level. Then enable auto-run only on specific columns that need it. The table-level setting is the parent: if OFF, no columns auto-run.
Symptom: 429 Too Many Requests when sending data via webhook.
Cause: Explorer plan has a 400 records/hour throttle.
Fix:
// Add delay between webhook submissions
async function sendWithThrottle(rows: any[], webhookUrl: string) {
for (const row of rows) {
const res = await fetch(webhookUrl, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify(row),
});
if (res.status === 429) {
const retryAfter = parseInt(res.headers.get('Retry-After') || '60');
console.log(`Rate limited. Waiting ${retryAfter}s...`);
await new Promise(r => setTimeout(r, retryAfter * 1000));
}
await new Promise(r => setTimeout(r, 250)); // 250ms between requests
}
}
Symptom: Same contact appears multiple times in HubSpot/Salesforce.
Cause: No deduplication key configured in the CRM push action.
Fix: When configuring the CRM action column, use email as the unique identifier and select Update existing record if found rather than always creating new.
Symptom: Data appears in wrong columns after CSV import.
Cause: CSV headers don't match Clay column names exactly.
Fix: Normalize headers before import: trim whitespace, match case exactly. "Company Name" and "company_name" are treated as different columns.
Symptom: Formula column displays #ERROR or #REF.
Cause: Column name referenced in formula was renamed or deleted.
Fix: Edit the formula column and update all column references to match current names. Clay formulas reference columns by their display name (case-sensitive).
| Symptom | Quick Check | Likely Fix |
|---|---|---|
| Red cell indicator | Click cell for error detail | Fix API config or input data |
| Empty enrichment | Check provider connection | Reconnect in Settings > Connections |
| No new rows from webhook | Test webhook URL with curl | Re-create webhook source |
| Credits depleting fast | Check waterfall depth | Reduce to 2 providers, add conditions |
Produce a redacted diagnostic record with table/environment, observed symptom, correlation ID, likely cause, containment action, data-certification state, and named escalation owner. Avoid including raw contacts, CRM records, credentials, or complete provider responses in tickets and shared logs.
When CRM sync duplicates a contact, pause the affected action, verify the deduplication key with a synthetic row, and repair/update the existing record before resuming. When credits drain unexpectedly, disable auto-runs, preserve the table state, and review conditions and waterfall behavior before retrying.
For systematic debugging, see clay-debug-bundle.
评论 (0)
暂无评论,成为第一个评论者吧!