Trellis Session Insight
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
Diagnose and fix Groq API errors with real error codes and solutions.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill groq-common-errors -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace groq-common-errors --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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/groq-common-errors .claude/skills/groq-common-errors && rm -rf skills-srcUse ~/.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/
Install the "groq-common-errors" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/groq-common-errors into .claude/skills/groq-common-errors/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "groq-common-errors", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/groq-common-errorsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill groq-common-errors -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace groq-common-errors --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/.curated/groq-common-errors .agents/skills/groq-common-errors && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "groq-common-errors" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/groq-common-errors into .agents/skills/groq-common-errors/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "groq-common-errors", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill groq-common-errors -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace groq-common-errors --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/.curated/groq-common-errors .cursor/skills/groq-common-errors && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "groq-common-errors" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/groq-common-errors into .cursor/skills/groq-common-errors/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "groq-common-errors", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jeremylongshore/tons-of-skills-marketplace.git --path skills/.curated/groq-common-errors--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill groq-common-errors -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace groq-common-errors --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/.curated/groq-common-errors .gemini/skills/groq-common-errors && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "groq-common-errors" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/groq-common-errors into .gemini/skills/groq-common-errors/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "groq-common-errors", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jeremylongshore/tons-of-skills-marketplace groq-common-errorsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill groq-common-errors -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/.curated/groq-common-errors .github/skills/groq-common-errors && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "groq-common-errors" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/groq-common-errors into .github/skills/groq-common-errors/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "groq-common-errors", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill groq-common-errors -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace groq-common-errors --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/.curated/groq-common-errors .opencode/skills/groq-common-errors && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "groq-common-errors" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/groq-common-errors into .opencode/skills/groq-common-errors/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "groq-common-errors", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
groq-common-errorsDiagnose and fix Groq API errors with real error codes and solutions.
Groq Common Errors is an agent skill from jeremylongshore/tons-of-skills-marketplace. Diagnose and fix Groq API errors with real error codes and solutions. Use when encountering Groq errors, debugging failed requests, or troubleshooting integration issues. Trigger with phrases like "groq error", "fix groq", "groq not working", "debug groq", "groq 429".
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/error-reference.md` and `references/sdk-error-handling.md`). Compatibility notes: Designed for Claude Code
It sits in Development, covering Debugging. 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.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepBash(curl:*)From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
curljqFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.groq.comAlso links to:
console.groq.comstatus.groq.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
GROQ_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Designed for Claude Code
From compatibility in the SKILL.md frontmatter.
Groq Common Errors loads about 1.3k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 419 words of instructions outside code blocks.
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.
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.
The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 419 words, ~1,255 tokens.
.claude/skills/groq-common-errors/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Comprehensive reference for Groq API error codes, their root causes, and proven fixes. Groq returns standard HTTP status codes with structured error bodies and rate-limit headers. This skill walks the diagnosis from raw error string to fix, then hands off to the full per-status reference for depth.
Every Groq error body follows one shape — read the code and type first:
{
"error": {
"message": "Rate limit reached for model `llama-3.3-70b-versatile`...",
"type": "tokens",
"code": "rate_limit_exceeded"
}
}GROQ_API_KEY exported in the environment (keys start with gsk_).curl and jq available for the diagnostic probes below.groq-sdk (TypeScript) or groq (Python) installed.Capture the failing status and body. Read the raw error response — the HTTP status plus the code/type fields determine the whole diagnosis path.
Confirm the key works before assuming anything deeper:
set -euo pipefail
# Verify API key is valid — expect a model count, not an auth error
curl -s https://api.groq.com/openai/v1/models \
-H "Authorization: Bearer $GROQ_API_KEY" | jq '.data | length'Confirm the model still exists. Many 400s are deprecated model IDs — list the live models and Grep your codebase for any stale ID:
curl -s https://api.groq.com/openai/v1/models \
-H "Authorization: Bearer $GROQ_API_KEY" | jq '.data[].id' | sortMap the status to a fix using the table below, then drill into references/error-reference.md for the exact error string, causes, and copy-paste fix.
For SDK integrations, branch on the typed exception classes — see references/sdk-error-handling.md.
A diagnosis that names the error class, the root cause, and the concrete fix — for example: "429 on TPM: token budget exhausted; add the single-retry handleRateLimit wrapper and honor retry-after," or "400: mixtral-8x7b-32768 is deprecated; switch to llama-3.3-70b-versatile." When run against real code, the output is the edited call site plus a verification curl that returns 200.
Map the HTTP status to its cause; full error strings, rate-limit headers, and fixes live in references/error-reference.md.
| Status | Meaning | First move |
|---|---|---|
| 401 | Invalid / missing key | Confirm GROQ_API_KEY starts with gsk_; test with /models |
| 429 | RPM / TPM / RPD limit hit | Read retry-after; back off and single-retry |
| 400 | Deprecated model or bad params | List live models; replace stale IDs |
| 413 | Request over context window | Trim prompt (Llama models cap at 128K tokens) |
| 500 / 503 | Groq-side outage or overload | Retry with backoff; fall back model; check status page |
When the failure is transient (429/500/503), retry with backoff and honor retry-after rather than hammering. When it is structural (401/400/413), fix the request — retrying will not help.
Minimal end-to-end probe that isolates auth vs. model vs. payload problems:
# A 200 here means key + model + payload are all valid; a non-200 status
# tells you which layer failed.
curl -s -o /dev/null -w "%{http_code}" \
https://api.groq.com/openai/v1/chat/completions \
-H "Authorization: Bearer $GROQ_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"llama-3.1-8b-instant","messages":[{"role":"user","content":"ping"}],"max_tokens":5}'retry-after): see the 429 section of references/error-reference.md.groq-debug-bundle skill.© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in skills/.curated/groq-common-errors of jeremylongshore/tons-of-skills-marketplace.
Open the folder on GitHubat commit cfae287
Groq Common Errors 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Groq Common Errors this skilljeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Trellis Session Insightmindfold-ai/Trellis | 15k | 4 repos | ~1.7k | Automated safety check: Pass | AGPL-3.0 | |
| Native Data FetchingCherryHQ/cherry-studio-app | 4k | 6 repos | ~2.9k | Automated safety check: Notes | MIT | |
| Debugging Executionsn8n-io/n8n | 207k | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| Aoti Debugpytorch/pytorch | 104k | 1 repos | ~1.7k | Automated safety check: Pass | Custom licence | |
| Herdr Throwaway Reproductionherdrdev/herdr | 43k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 |
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
CherryHQ/cherry-studio-app
A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.
n8n-io/n8n
Debug failed or wrong-output workflow executions using executions tools.
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
herdrdev/herdr
Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.
ultralisp/ultralisp
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes
jeremylongshore/tons-of-skills-marketplace
Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.
jeremylongshore/tons-of-skills-marketplace
Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.
jeremylongshore/tons-of-skills-marketplace
Execute proactive auto-loading: automatically detects and loads agents.md files.
jeremylongshore/tons-of-skills-marketplace
Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.
jeremylongshore/tons-of-skills-marketplace
Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.
jeremylongshore/tons-of-skills-marketplace
Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.
Categories
Diagnose and fix Groq API errors with real error codes and solutions. Groq Common Errors is an agent skill from jeremylongshore/tons-of-skills-marketplace. Diagnose and fix Groq API errors with real error codes and solutions.
Groq Common Errors fits situations like: encountering Groq errors; debugging failed requests; troubleshooting integration issues; with phrases like groq error.
Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill groq-common-errors -a claude-code`. Or copy the skill folder (skills/.curated/groq-common-errors in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/groq-common-errors in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill groq-common-errors -a codex`. Or copy the skill folder (skills/.curated/groq-common-errors in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/groq-common-errors in your project. Codex loads it when a task matches its description.
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 groq-common-errors -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/groq-common-errors, .gemini/skills/groq-common-errors, .github/skills/groq-common-errors and .opencode/skills/groq-common-errors in your project.
Going by SKILL.md and its folder, Groq Common Errors needs the command-line tools its instructions call (curl and jq) and credentials named GROQ_API_KEY. Our summary lists: A credential in GROQ_API_KEY. Its frontmatter pre-approves these tools: Read, Grep, Bash(curl:*). Compatibility (from SKILL.md): Designed for Claude Code.
SKILL.md names 3 domains. In commands or code: api.groq.com; the agent is likely to contact it when it follows the instructions. As links in the text: console.groq.com and status.groq.com. This is read from the text; nothing was executed.
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.
Groq Common Errors is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.3k tokens (SKILL.md is roughly 5k 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 1.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Groq Common Errors: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Debugging Executions (n8n-io/n8n, 207k stars) and Aoti Debug (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.