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

Career Coach

ASecurity

Clarify career direction, set goals, and build actionable development plans through structured coaching.

2 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 aicodedecode/awesome-muse-skills --skill career-coach --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Career Coach?

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

Security grade badge for Career Coach
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-career-coach/badge)](https://www.skillsdirectory.com/skills/aicodedecode-career-coach)

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: career-coach
description: Clarify career direction, set goals, and build actionable development plans through structured coaching.
category: career
---

## Overview

Career coaching is not advice-giving — it's structured thinking with a partner.
This skill runs
coaching-style conversations: clarifying what the user actually wants (versus
what they think they
should want), diagnosing what's blocking them, and converting insight into a
concrete 30/60/90-day
plan. It asks more than it tells.

## When to use

- Feeling stuck, restless, or unsure about next career moves

- - Deciding between competing offers or paths (IC vs management, startup vs big
  tech)

- Planning skill development for a promotion or pivot

- Working through burnout, boredom, or a difficult manager

- Annual career reflection and goal-setting

## Core concepts

- - - **Values before tactics.** Decisions made on salary or prestige alone tend
  to unravel. Surface
  what actually matters: autonomy, mastery, impact, stability, recognition,
craft — then evaluate
  options against those, not against each other.
- - - **The energy audit.** Track for two weeks: which tasks energize, which
  drain. Career clarity
  often hides in the pattern of a normal fortnight, not in grand introspection.
- - - **Regret minimization.** For big decisions, ask: "at 80, which choice
  would I regret not
  trying?" It cuts through short-term fear reliably.
- - - **Reversible vs irreversible.** Most career moves are reversible (two-way
  doors). Treat them as
  experiments with a time box, not life sentences. Reserve agonizing for the
genuinely
  hard-to-reverse ones.
- - - **The 3-bucket plan.** Every development plan needs: learn (skills),
  demonstrate (visible
  proof), and connect (relationships/sponsors). People who only do bucket one
stall.
- - - **Coaching questions over answers.** "What would good look like in 12
  months?" "What's the
  smallest step that would tell you this is the right direction?" The user owns
the answer; the
  coach owns the question quality.

## Practical workflow

1. 1. 1. **Establish the real topic.** Ask what brought them here now, and
   what's at stake. Distinguish
   "I need a decision by Friday" from "I'm exploring."
2. 2. 2. **Clarify the desired outcome.** Push past vagueness: "a better job"
   becomes "a staff-level IC
   role at a mid-size SaaS with real technical ownership by Q2."
3. 3. 3. **Diagnose, don't prescribe.** Explore: What's working? What's
   draining? What have they
   already tried? What are they afraid is true? Listen for the gap between
stated goals and revealed
   preferences.
4. 4. 4. **Generate options.** Brainstorm 3-4 genuinely different paths (not
   variations of one).
   Include one "wild card" to break anchoring.
5. 5. 5. **Test with small experiments.** Convert each option into a 2-week
   test: informational
   interviews, a side project, shadowing, a course module. Decisions get easier
with data.
6. 6. 6. **Build the 30/60/90 plan.** Concrete actions with dates: 30 days
   (quick wins + experiments),
   60 days (deeper bets), 90 days (decision point or milestone). Each item has
an owner (them) and a
   success signal.
7. 7. 7. **Schedule the check-in.** Coaching without follow-up is conversation.
   Set a review point and
   define what "on track" looks like.

## Common pitfalls

- - - **Solving before understanding.** Jumping to "you should do X" in the
  first five minutes. The
  first job is diagnosis.
- - - **Confusing venting with coaching.** Letting the session become a
  complaint loop with no forward
  motion. Acknowledge, then pivot: "given that's true, what's one thing in your
control?"
- - - **Advice that ignores constraints.** Recommending a pay-cut pivot to
  someone with a mortgage and
  no runway. Always surface financial, family, and visa constraints early.
- - - **Infinite exploration.** Some people research forever to avoid deciding.
  Time-box exploration
  and force small experiments.
- - - **Measuring the wrong thing.** Tracking applications sent instead of
  conversations had, or
  courses completed instead of skills demonstrated. Define outcome metrics, not
activity metrics.
- - - **Neglecting the sponsor problem.** Individual effort stalls without
  advocates. Every plan
  should include building relationships with people who influence the user's
trajectory.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
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 →