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

Salary Negotiator

ASecurity

Prepare and execute compensation negotiations with market data, scripts, and counter-offer strategy.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgo

Works with

cli

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill salary-negotiator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Salary Negotiator?

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

Security grade badge for Salary Negotiator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-salary-negotiator/badge)](https://www.skillsdirectory.com/skills/aicodedecode-salary-negotiator)

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: salary-negotiator
description: Prepare and execute compensation negotiations with market data, scripts, and counter-offer strategy.
category: career
---

## Overview

Almost every offer is negotiable, and the first number is rarely the last. Yet
most candidates
accept the first offer because negotiating feels confrontational. This skill
reframes negotiation as
collaborative problem-solving: you and the employer both want you to sign, and
the only question is
the package. It covers research, anchoring, scripts for every stage, and the
counter-offer trap.

## When to use

- Evaluating a written offer and deciding whether/how to negotiate

- Answering "what are your salary expectations?" early in a process

- Juggling multiple offers for leverage

- Negotiating a raise or promotion internally

- Handling exploding offers and deadlines

## Core concepts

- - - **Never give the first number if you can avoid it.** "What's your expected
  salary?" → "I'd like
  to understand the full scope first — what's the budgeted range for this role?"
Whoever anchors
  first sets the frame.
- - - **Negotiate the total package.** Base, bonus, equity/RSUs, sign-on,
  relocation, remote
  flexibility, start date, title, review timeline. A "no" on base often becomes
a "yes" on sign-on
  or equity.
- - - **Market data is your leverage.** Levels.fyi, Glassdoor, Pave, peer
  conversations — come with a
  range, not a feeling. "Based on market data for this role in this market, I'm
targeting X-Y."
- - - **Silence is a tactic.** After you state your ask, stop talking. The urge
  to fill silence with
  concessions is the most expensive habit in negotiation.
- - - **Get it in writing.** Verbal promises evaporate. Every agreed term —
  including start dates and
  review timelines — goes into the written offer before you sign.
- - - **The walk-away number.** Decide your minimum acceptable package before
  negotiating. Without it,
  you'll rationalize a bad deal in the moment.

## Practical workflow

1. 1. 1. **Research.** Gather 3+ data points for the role, level, and market.
   Note the full range, not
   just the median — you negotiate against the top of the band, not the middle.
2. 2. 2. **Set your numbers.** Three figures: ideal (ask), target (happy to
   sign), walk-away (decline).
   Keep the walk-away private; it's your discipline tool.
3. 3. 3. **Deflect early salary questions.** Use the range-request script. If
   forced, give a wide,
   research-backed range with the top at your ideal — never a single number,
never your current
   salary (it's irrelevant and often illegal to ask for).
4. 4. 4. **Evaluate the written offer.** Score each component against your
   numbers. Identify the 2-3
   levers with the most upside (usually base + sign-on + equity).
5. 5. 5. **Make the counter.** One consolidated ask, framed collaboratively:
   "I'm excited about the
   role and the team. Based on my research and the scope, I'd be able to sign at
[X base, Y
   sign-on]. Can we get there?" Then silence.
6. 6. 6. **Handle the pushback.** Expect "this is our best offer" (often not
   true), "the band doesn't
   allow it" (ask about sign-on/equity, which often sit outside bands), or a
split-the-difference.
   Respond to each calmly, one round at a time — 2-3 rounds is normal.
7. 7. 7. **Close cleanly.** Once terms are agreed, confirm in writing, thank
   everyone, and stop
   negotiating. Post-acceptance renegotiation burns bridges.

## Common pitfalls

- - - **Accepting the first offer.** The first offer is a starting point by
  design. A polite counter
  almost never rescinds an offer — that fear is the employer's best negotiating
tool.
- - - **Negotiating against yourself.** "I was thinking maybe around X, but I'm
  flexible..." — you've
  just lowered your own anchor. State the ask and stop.
- - - **Revealing your current salary.** It anchors you to your past, not your
  market value. Deflect:
  "I'd prefer to focus on the market rate for this role."
- - - **Only negotiating base.** Candidates leave tens of thousands on the table
  ignoring sign-on
  bonuses, equity refreshers, and remote stipends.
- - - **Using a fake competing offer.** Lies get discovered and destroy trust.
  Real leverage only —
  even "I'm in late stages elsewhere" must be true.
- - - **Exploding-offer panic.** "Sign by Friday or it's gone" is usually
  negotiable: "I'm very
  interested — I need until [date] to make a thoughtful decision." Employers who
truly want you will
  wait a few days.

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', ...

698431 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 →