veille
AI/Tech intelligence gathering from YouTube, Twitter, RSS, and GitHub.
Skill by LG15601
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lg15601-veille
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/veille
What's inside
- Skill name
veille- Description
- AI/Tech intelligence gathering from YouTube, Twitter, RSS, and GitHub. Daily automated monitoring of 10 YouTube channels, 14 Twitter accounts, 6 RSS feeds. Use when asked about AI news, competitor updates, or 'veille'.
- License
- MIT
- Instructions
- 35 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (4)
- SKILL.md
- daily-veille.sh · scripts/
- deep-research.sh · scripts/
- github-watcher.sh · scripts/
SKILL.md (first lines)
# Veille — Intelligence Gathering Automated daily intelligence from curated sources. ## Sources (from data/veille-sources.json) ### YouTube (10 channels) Anthropic, AI Explained, Matthew Berman, Fireship, Two Minute Papers, Wes Roth, David Ondrej, Cole Medin, IndyDevDan, All About AI ### Twitter/X (14 accounts) @AnthropicAI, @alexalbert__, @AmandaAskell, @daboross, @BarrettZoph, @kaborosBg, @OpenAI, @GoogleAI, @sama, @ylecun + 4 more ### RSS (6 feeds) Anthropic on HN, OpenAI Blog, Google AI Blog, HN AI, The Verge AI, TechCrunch AI ## Usage ```bash # Daily automated scan bash ~/.claude/skills/veille/scripts/daily-veille.sh # Deep research on specific topic bash ~/.claude/skills/veille/scripts/deep-research.sh "claude code new features" # GitHub repo watcher bash ~/.claude/skills/veille/scripts/github-watcher.sh ``` ## Output Daily digest in `output/YYYY-MM-DD.md` with: - RSS headlines (prioritized) - New YouTube videos from tracked channels - Twitter highlights (when API configured) - Actionable insights flagged
From LG15601/alba-blueprint, MIT.
More from LG15601/alba-blueprint
- 0.410score
client-manager
LG15601
CRM health scoring, relance checker, and report generator for Orchestra Intelligence clients.
SkillDFreshness: DClaude Code +9 - 0.410score
morning-brief
LG15601
Generate daily morning briefing from 6 real data sources: emails, calendar, GitHub, client pipeline, system health, Google Drive.
SkillDFreshness: DClaude Code +9 - 0.410score
health-check
LG15601
System health monitor with 10+ checks: disk, Docker, Alba agent, internet, Tailscale, LaunchAgents, secrets, memory, CPU.
SkillDFreshness: DClaude Code +9 - 0.410score
inbox-zero
LG15601
DPYS email classifier for 3 mailboxes.
SkillDFreshness: DClaude Code +9 - 0.407score
codex
LG15601
Codex CLI integration for PR code review and autonomous fix execution.
SkillDFreshness: DClaude Code +9 - 0.406score
apex
LG15601
10-step autonomous feature workflow: branch → analyze → plan → execute → validate → review → fix → test → verify → PR.
SkillDFreshness: DClaude Code +9 - 0.406score
simulate
LG15601
Run MiroFish social simulation to test public reaction before strategic decisions.
SkillDFreshness: DClaude Code +9 - 0.406score
daily-briefing
LG15601
Generate morning briefing with calendar, email, tasks, news, Twitter, Slack.
SkillDFreshness: DClaude Code +9 - 0.403score
nightly-routine
LG15601
Run nightly maintenance: update tools, monitor repos, consolidate memory, check competitors, cleanup.
SkillDFreshness: DClaude Code +9 - 0.403score
self-improve
LG15601
End-of-session self-improvement protocol.
SkillDFreshness: DClaude Code +9 - 0.403score
tool-discover
LG15601
Detect and register new tools when installed.
SkillDFreshness: DClaude Code +9 - 0.397score
clean-test-skill
LG15601
A benign skill for testing false-positive rates
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 1, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/LG15601/alba-blueprint
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from LG15601
- 0.410score
client-manager
LG15601
CRM health scoring, relance checker, and report generator for Orchestra Intelligence clients.
SkillDFreshness: DClaude Code +9 - 0.410score
morning-brief
LG15601
Generate daily morning briefing from 6 real data sources: emails, calendar, GitHub, client pipeline, system health, Google Drive.
SkillDFreshness: DClaude Code +9 - 0.410score
health-check
LG15601
System health monitor with 10+ checks: disk, Docker, Alba agent, internet, Tailscale, LaunchAgents, secrets, memory, CPU.
SkillDFreshness: DClaude Code +9 - 0.410score
inbox-zero
LG15601
DPYS email classifier for 3 mailboxes.
SkillDFreshness: DClaude Code +9 - 0.407score
codex
LG15601
Codex CLI integration for PR code review and autonomous fix execution.
SkillDFreshness: DClaude Code +9 - 0.406score
apex
LG15601
10-step autonomous feature workflow: branch → analyze → plan → execute → validate → review → fix → test → verify → PR.
SkillDFreshness: DClaude Code +9
Cite this page
veille skill. Agent Mart. https://agentmart.dev/skills/lg15601-veille (last updated 2026-10-24)