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

Daily

ASecurity

Run Zalo's daily content hour for the Zalo Kabche brand from ANY working directory — including Telegram/bridge sessions rooted at ~/dev. Invoke when Zalo says /daily, "what's today", "daily check-in", "today's reel", or opens a session to do his content hour. This is a thin router: the real procedure lives in ~/dev/zalo-kabche-brand/.claude/skills/daily/SKILL.md and is followed verbatim. Inside that repo, the repo-scoped skill wins and this one is unused.

2 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsgonoderailsgit

Security Analysis

A100/100

Scanned 9/27/2026

$npx -y skills add zalogarcia/zalo-claude-code-setup --skill daily --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Daily?

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

Security grade badge for Daily
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/zalogarcia-daily/badge)](https://www.skillsdirectory.com/skills/zalogarcia-daily)

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: daily
description: >
  Run Zalo's daily content hour for the Zalo Kabche brand from ANY working
  directory — including Telegram/bridge sessions rooted at ~/dev. Invoke when
  Zalo says /daily, "what's today", "daily check-in", "today's reel", or opens a
  session to do his content hour. This is a thin router: the real procedure
  lives in ~/dev/zalo-kabche-brand/.claude/skills/daily/SKILL.md and is followed
  verbatim. Inside that repo, the repo-scoped skill wins and this one is unused.
---

# /daily (from anywhere)

The brand machine's daily loop lives in the `zalo-kabche-brand` repo. This skill
exists only so `/daily` also works from a session rooted elsewhere — mainly the
Telegram bridge, whose cwd is `~/dev`. **Do not restate the procedure here.**
Read the repo's files and follow them exactly; they are the single source of
truth and they change without this file changing.

## Router

`BRAND=~/dev/zalo-kabche-brand`

1. Read `$BRAND/.claude/skills/daily/SKILL.md`: the actual procedure. Follow it
   start to finish, its close step's commit and push included (step 4).
2. Read `$BRAND/.claude/CLAUDE.md` — the repo runbook/guardrails do NOT auto-load
   in a session rooted outside the repo, so load them explicitly before producing
   anything (evergreen rule, why-first, fakeness filter, spoken-register rule,
   teleprompter formatting).
3. Every path in those files is repo-relative — prefix with `$BRAND/`
   (`process/cycle-state.md` → `~/dev/zalo-kabche-brand/process/cycle-state.md`).
4. Git runs with `-C $BRAND` (`git -C ~/dev/zalo-kabche-brand add <files>`), never
   a bare `cd`. The repo skill's close step commits and pushes in that repo; do both,
   without asking. That push is a standing exception Zalo recorded on 2026-09-23 (item (e)
   in `~/.claude/CLAUDE.md` "Git & Deployment"); the repo is private (`gh repo view`,
   2026-09-23). It covers only this close-step push of `zalo-kabche-brand`; any other push,
   deploy or migration a run touches still needs his go-ahead.
5. The freestyle REEL CARD ships with every run (`$BRAND/.claude/skills/freestyle-reel/SKILL.md`,
   CARD mode) — it is part of the repo skill's contract, not an extra.

## Telegram shape (when running from the bridge)

Zalo is on his phone. The repo skill's "≤5 lines" announcement is the whole
reply — cycle day, today's ONE task, what's already prepped, the 15-min
fallback — then the REEL CARD as its own short block. No headers, no tables, no
walls of text.

**Announce first, prep second.** If the machine-side prep for today's task is
heavy (mining a transcript, drafting a script, rendering b-roll, batching
reels), send the announcement + card immediately, then hand the prep to a
background worker (`node ~/dev/claude-telegram-bridge/bg.mjs "<self-contained task>"`)
so the chat stays reachable. Never make him wait on a render to learn what
today's task is.

If he replies with a take (video/audio/transcript), that's RATE mode of the
freestyle-reel skill — same router rules apply.

Attribution

zalogarciazalogarcia
View sourceSee grades on GitHubMore from zalogarcia →
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 →