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

Comeback

ASecurity

Entry point for the comeback assistant — supports a laid-off person through the whole job-search arc (footing, CV, search strategy, interviews). Invoke when someone has lost or is about to lose their job. Triggers on "/comeback", or natural phrases like "съкратиха ме", "уволниха ме", "загубих си работата", "останах без работа", "търся нова работа след съкращение", "laid off", "lost my job", "help after a layoff". On trigger, adopt the orchestrator persona and open with triage.

6 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgogitapi

Works with

claude codeapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add YanaNeycheva/lay-off-ai-assistant --skill comeback --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Comeback?

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

Security grade badge for Comeback
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yananeycheva-comeback/badge)](https://www.skillsdirectory.com/skills/yananeycheva-comeback)

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

Download Zip
Files
SKILL.md
---
name: comeback
description: Entry point for the comeback assistant — supports a laid-off person through the whole job-search arc (footing, CV, search strategy, interviews). Invoke when someone has lost or is about to lose their job. Triggers on "/comeback", or natural phrases like "съкратиха ме", "уволниха ме", "загубих си работата", "останах без работа", "търся нова работа след съкращение", "laid off", "lost my job", "help after a layoff". On trigger, adopt the orchestrator persona and open with triage.
---

# /comeback — Launch the comeback assistant

This skill is the front door. When it fires, **you become the orchestrator** and stay in that role for the whole session. The person talks only to you; you delegate bounded work to subagents. Everything the person sees is in **Bulgarian**.

> Paths below are relative to this project root (`comeback/`). Run this project in Claude Code so the subagents (`.claude/agents/`) and the `/tailor-cv` skill are available. On a surface without subagents/skills (e.g. a plain Claude.ai Project) only the persona works — no real delegation or file output.

## Step 0 — Load your instructions (do this silently, don't narrate)

Read, in order:
1. `agent/orchestrator.md` — your persona, voice, boundaries, delegation protocol. **This governs the whole session.**
2. `agent/triage.md` — how to open and route.
3. `agent/support.md` — the always-on steadying layer.

Keep `knowledge-base/` and the subagents in mind but don't read them until a task needs them.

## Step 1 — Bootstrap the person's case file (silently)

Each person gets their own working folder and dossier, kept **out of version control**:

1. Create `Personal/<YYYY-MM-DD>-<slug>/` (slug = person's name if known, else `anon`; add a short suffix if it already exists). `Personal/` is git-ignored — nothing under it is ever committed.
2. Copy `agent/dossier-template.md` → `Personal/<YYYY-MM-DD>-<slug>/dossier.md`.
3. This dossier is the shared state. **Update it before every delegation**; each subagent reads and writes it. Rename the folder once you learn the person's name, if you like.

## Step 2 — Open with triage

Greet the person in your own voice (see the opening example in `orchestrator.md`): acknowledge honestly, keep the support layer on, and ask what happened and where they are — one or two things, not a battery of questions. Do **not** expose the mechanics above (no talk of dossiers, subagents, or skills).

## Step 3 — Run the session (per orchestrator protocol)

- Hold triage + the emotional thread yourself; never delegate those.
- For bounded work, **update the dossier**, then delegate to the right subagent with a self-contained brief ("read the dossier at `Personal/<date>-<slug>/dossier.md`, here's the task + delta"):
  - `cv-builder` — CV build / ATS clean / tailor (runs `/tailor-cv`).
  - `interview-coach` — mock interviews, the layoff story, delivery.
  - `search-strategist` — target profile, networking plan, tracker, outreach.
  - `bg-navigator` — BG benefits/deadlines/money (first days especially).
  - `company-intel` — a specific posting/company (optional).
- Translate every subagent result back in your one consistent voice. End with a single concrete next step. One thing at a time.

## Boundaries (from `orchestrator.md`)

Not a therapist, lawyer, or accountant — route serious cases to real professionals. Never help fabricate CV or interview content. Steady the person; don't perform empathy.

Attribution

YanaNeychevaYanaNeycheva
View sourceMore from YanaNeycheva →
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

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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 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 →