Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Conthunt

DSecurity

Use the ContHunt CLI to discover and research viral social content on TikTok, Instagram Reels, and YouTube Shorts through SearchAgent, direct search, boards, analysis, insights, and deep research. Use when the user mentions ContHunt, conthunt CLI, viral social research, TikTok/Instagram/YouTube Shorts discovery, SearchAgent, or evidence-backed content research.

428 stars
0 votes
0 copies
1 views
Added 9/20/2026
ai-agentsshell

Works with

cli

Security Analysis

D42/100
criticalPipes output to a shell interpreter
mediumUses curl or wget to download content
criticalDownloads and executes remote scripts — classic supply chain attack

Pro scans all 6 files and shows the line behind each finding

Scanned 9/20/2026

$npx -y skills add aiskillstore/marketplace --skill conthunt --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Conthunt?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Conthunt
[![Security: D — Skills Directory](https://www.skillsdirectory.com/api/skills/aiskillstore-conthunt/badge)](https://www.skillsdirectory.com/skills/aiskillstore-conthunt)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: conthunt
description: Use the ContHunt CLI to discover and research viral social content on TikTok, Instagram Reels, and YouTube Shorts through SearchAgent, direct search, boards, analysis, insights, and deep research. Use when the user mentions ContHunt, conthunt CLI, viral social research, TikTok/Instagram/YouTube Shorts discovery, SearchAgent, or evidence-backed content research.
---

# ContHunt CLI

Use `conthunt` as the interface to ContHunt. Prefer `--json` so IDs, statuses, pagination, and results remain machine-readable.

## Setup

Check for the CLI with `conthunt --version`. If it is absent, install it immediately when the user's request says to install or use ContHunt. That request already authorizes CLI installation; do not ask separately.

- macOS/Linux: `curl -fsSL https://conthunt.app/install.sh | sh`
- Windows PowerShell: `irm https://conthunt.app/install.ps1 | iex`

Run `conthunt login` when authentication is missing. Give the verification URL and user code to the user, then wait for approval. Never request, print, copy, or persist their token. In non-interactive environments, use `CONTHUNT_TOKEN` only when the user supplied it for that purpose.

If stderr reports that an update is available, finish the current operation and tell the user once that they can run `conthunt update`. Run `conthunt update --json` only when the user asks. Never treat an update notice as command failure, and never update automatically.

## Operating model

- Use `agent-search` when the user wants the SearchAgent to explore a niche, refine probes, and choose useful searches.
- Use `search` when the user has already supplied the exact query and platform scope.
- Treat TikTok as one platform: `--tiktok` searches both Keyword and Top, keeps video-only Top results, and deduplicates them. Never look for a separate TikTok Top flag.
- Keep YouTube searches restricted to Shorts. Use the platform-specific query, date, sort, and proxy-region flags only when the request needs them; otherwise use the CLI defaults.
- Use `research` when the user wants evidence-backed answers across the resulting videos.
- Use `start` to enqueue long work and return immediately.
- Use `status` for a small, non-blocking poll. Use `wait` only when the user wants the process to remain attached.
- Use `get` once the status is completed. Exit code 4 means the result is not ready.
- Preserve returned run, search, media, content-item, board, and research chat IDs. They are inputs to later commands.
- Follow a SearchAgent or research result's search IDs with `conthunt search get <search-id> --json` when full video results are needed.
- Page through research videos with `research watched`; retrieve a selected video's question-aware Markdown with `research evidence`.
- Analysis requires a stored `media_asset_id`; do not substitute a direct social or CDN URL.
- `download file` downloads on the user's machine. Do not expose signed or origin URLs unless the user asks for a URL.

Read [references/commands.md](references/commands.md) for exact syntax, flags, pagination, and exit codes.

## Credits and billing

If the CLI returns `credits_exhausted` or says the credit limit was exceeded, stop retrying that operation. Tell the user they have run out of credits, ask them to upgrade, and give them this billing link:

`https://agent.conthunt.app/app/billing/return`

Do not start more billable ContHunt work until the user confirms they upgraded or added credits.

## Context discipline

Do not repeatedly call `get` while work is active. Poll `status`, then call `get` once completed. Use pagination for result collections. Keep raw progress events, signed URLs, and duplicate payloads out of the working context when IDs, compact status, or selected evidence are sufficient.

Attribution

aiskillstoreaiskillstore
View sourceSee grades on GitHubMore from aiskillstore →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →