Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Morning Briefing

ASecurity

Invoke as `/catalyst-dev:morning-briefing` to produce today's briefing locally and fan it out to Slack DM, Slack channel, Notion page, and a Loom recording script. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.

20 stars
0 votes
0 copies
2 views
Added 9/3/2026
ai-agentsgobashgit

Works with

claude codemcp

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add coalesce-labs/catalyst --skill morning-briefing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Morning Briefing?

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

Security grade badge for Morning Briefing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/coalesce-labs-morning-briefing/badge)](https://www.skillsdirectory.com/skills/coalesce-labs-morning-briefing)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: morning-briefing
description:
  Generate a daily briefing markdown at thoughts/briefings/YYYY-MM-DD.md with six sections —
  Review yesterday, Surface decisions, Plan today, relay-dispatch candidates, Friction since last
  briefing, and Learnings since last briefing — synthesized from Linear, GitHub,
  Granola, Google Drive, Google Calendar, and the compound-engineering stores in parallel. Then
  fans the briefing out to four destinations (Slack DM, Slack channel, Notion page, Loom script
  file). Use when the user says "morning briefing" / "run my briefing", or on a weekday-morning
  schedule via the CMA Routine wrapping this same skill.
disable-model-invocation: true
allowed-tools: Bash, Read, Write, Edit, Grep, Glob, mcp__linear__*, mcp__notion__*
---

# Morning Briefing — canonical markdown + fan-out

Invoke as `/catalyst-dev:morning-briefing` to produce today's briefing locally and fan it out to Slack DM, Slack channel, Notion page, and a Loom recording script.

**Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.

## Flags

| Flag | Meaning |
|---|---|
| `--date YYYY-MM-DD` | Target date. Default: today (UTC). |
| `--dry-run` | Write to `/tmp/morning-briefing-<date>.md` instead of `thoughts/briefings/`. |

## Load on demand

| when | read |
| -- | -- |
| gathering yesterday/today from Linear, GitHub, Granola, Drive, Calendar | `references/gather.md` |
| surfacing decisions — ADR drift, blocked PRs, judgment calls, compound proposals | `references/decisions.md` |
| the ADR-drift detector's frontmatter contract, output shape, and config resolution | `references/adr-drift.md` |
| the friction / learnings "since last briefing" digests | `references/digests.md` |
| suggesting which tickets look ready for a relay-ticket dispatch | `references/suggest-dispatch.md` |
| rendering the markdown, or fanning it out to Slack/Notion/Loom | `references/render-fanout.md` |
| this host might have no cloud mirror, or a Linear read looks stale | the `steward` skill's cloud-detection reference (canonical) |

## Loop

1. **Prelude** — start a session, resolve the output path for `$DATE`.
2. **Gather** — five sources in parallel, each degrading silently to `{}` if its credentials are absent (`references/gather.md`).
3. **Decisions + digests** — ADR drift, blocked PRs, judgment calls, compound proposals, friction/learnings windows (`references/decisions.md`, `references/digests.md`).
4. **Suggest relay-dispatch candidates** — tickets that look ready for `/relay-ticket` (`references/suggest-dispatch.md`).
5. **Render + fan out** — merge fragments, render the markdown, append the digests, fan out, and end the session (`references/render-fanout.md` — this is the last step; do not end the session again after it).

## Invariants

- **Single-ticket Linear reads go through the replica, gated by cloud-detection.** List/search calls (this skill's normal shape — an activity window, not one ticket) have no replica form yet and correctly stay on `linearis` directly, per the `linearis` skill's "Reading Linear" contract — that is not a shortcut.
- **"Suggest relay-dispatch candidates" names candidates for `/relay-ticket <TICKET>`**, never the legacy orchestrator or a retired background-dispatch path (CTL-2218).
- Every gather/fan-out helper degrades to an empty or skipped result rather than failing the whole run — the briefing always lands locally.

## Output contract

YAML frontmatter validated against the briefing frontmatter schema this skill carries (`assets/templates/briefing-frontmatter.schema.json`) (required: `date`, `generated_by`, `decisions`; optional `output_status`). Six `## ...` body sections: the four `render.sh` owns (Review yesterday, Surface decisions, Plan today, and the relay-dispatch-candidates section — `render.sh` still hardcodes its heading as `## Suggest orchestrator runs`, a residual label tracked in `references/suggest-dispatch.md`, not a live dependency) plus the two compound digests. `Plan today` carries a `### Retro signals` sub-section. Empty render sources render `_no data_`; empty compound stores render `_none_`. A companion `<date>-loom-script.md` lands beside the briefing whenever the loom fan-out runs (always — it has no credential prerequisite).

Pending compound-engineering ADR proposals (`thoughts/shared/compound/pending/*.md`) surface as `decisions:` entries so `briefing-followup`'s `action-compound.sh` can apply/edit/defer/reject them — the human-gated ADR approval surface.

## Pointers

`catalyst-dev:briefing-followup` (consumes this skill's output) · `catalyst-dev:linearis` · `relay-ticket` (what "suggest relay-dispatch candidates" points at) · `catalyst-dev:ticket-retro`.

Attribution

coalesce-labscoalesce-labs
View sourceMore from coalesce-labs →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →