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

Dept Resume

ASecurity

Read dept-state.md and spawn a Dept Head with a lean briefing. Department-operations parallel of /pd-resume.

3 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add Tekkiiiii/the-agency --skill dept-resume --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dept Resume?

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

Security grade badge for Dept Resume
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tekkiiiii-dept-resume/badge)](https://www.skillsdirectory.com/skills/tekkiiiii-dept-resume)

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: dept-resume
description: Read dept-state.md and spawn a Dept Head with a lean briefing. Department-operations parallel of /pd-resume.
category: dept-ops
version: 1.0.0
---

# dept-resume

Spawns a Dept Head agent for the given department with a pre-built briefing from `dept-state.md`. Lean context, fast start.

## Usage

```
/dept-resume [dept-slug]
/dept-resume content-creation
/dept-resume engineering
/dept-resume all
```

## Argument Resolution

| Argument | Action |
|---|---|
| `[dept-slug]` | Resume exactly one department |
| `all` | Resume all active departments (spawns in parallel) |
| no arg | Fail with usage hint |

## What It Does

1. Reads `~/.agency/agents/{dept}/state/dept-state.md`
2. Checks `~/.agency/agents/{dept}/state/incoming/` for pending inter-spawn tasks
3. Checks `~/.claude/agents/{dept}/state/dev-plan.md` for existence (dev-plan-absent check)
4. Spawns the Dept Head with dept-state.md inline — no extra reads on spawn
5. Dept Head boots per `core/runbooks/dept-boot-sequence.md` Mode 1

## Dev-Plan-Absent Check

After reading dept-state.md (Step 1), check whether `~/.claude/agents/{dept}/state/dev-plan.md` exists.

- **If absent** (and the initiative has 3+ D3 tracks): inject into the Dept Head spawn prompt:
  "DEV-PLAN ABSENT — generate ~/.claude/agents/{dept}/state/dev-plan.md before dispatching
  any Dept-Coords. Apply the two-condition parallel rule (see task-decomposition-methodology.md)
  to assign layers. After generating the dev-plan, run /save-state and respawn to enter
  the deployment phase with a clean context."
- **If absent** (simple initiative, <3 D3 tracks): skip dev-plan generation — not required
  for single-track or dual-track initiatives.
- **If present**: inject a one-line note: "Dev-plan: ~/.claude/agents/{dept}/state/dev-plan.md
  (present — read before dispatching Dept-Coords)"

This mirrors the pd-resume dev-plan-absent trigger, applied to department operations.

## Dept Head Boot Context

The spawn prompt includes:
- dept-state.md content (inline, no file read needed)
- incoming task count and any HIGH-priority items
- The dept head's agent definition path

**Target context on spawn: ~400 tokens.** Everything else is lazy-loaded per Mode 2 (Route).

## Output

```
dept-resume done — {dept}
  Head: {head-agent-name}
  Priority: {current-priority from dept-state}
  Active coords: {n or "none"}
  Incoming tasks: {n or "none"}
```

## Notes

- If `dept-state.md` doesn't exist, output: `No dept-state found for {dept}. Run /dept-wrap to initialize.`
- Dept Heads do NOT start their session by reading every pipeline and protocol file — that is lazy-loaded
- The incoming check is part of the boot sequence and runs before any other dept work

## References

- Dept boot sequence: `core/runbooks/dept-boot-sequence.md`
- Dept-Coord protocol: `core/runbooks/dept-coord-protocol.md`
- Parallel: `/pd-resume` for project directors, `/dept-status` for read-only check

Attribution

TekkiiiiiTekkiiiii
View sourceSee grades on GitHubMore from Tekkiiiii →
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', ...

698461 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 →