Agent skill

Employer Brand

by shawnpang in shawnpang/startup-founder-skills

When the user needs to create or improve content that shapes how candidates and the public perceive the company as a place to work.

MITAuto-check passedWriting & Content

Install Employer Brand

skills CLI
$ npx skills add shawnpang/startup-founder-skills --skill employer-brand -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shawnpang/startup-founder-skills employer-brand --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shawnpang/startup-founder-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/employer-brand .claude/skills/employer-brand && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
employer-brand
GitHub stars
343
Token cost
~2.3k tokens
SKILL.md length
1,006 words
Files
1
Skills in repo
50
Repo updated
First seen
Licence
MIT

At a glance

When the user needs to create or improve content that shapes how candidates and the public perceive the company as a place to work.

  • Works in 6 steps: Identify the authentic story — Ask the… → Choose the content format — Select from:… → Draft the content — Write using the… → …
  • Needs to create
  • SKILL.md covers When to Use, Context Required, Workflow and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Employer Brand is an agent skill from shawnpang/startup-founder-skills. When the user needs to create or improve content that shapes how candidates and the public perceive the company as a place to work.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content. The repository describes itself as: AI agent skills for tech startup founders — fundraising, sales, product, recruiting, engineering, legal, ops, and growth. Works with Claude Code, Cursor, Codex, and any Agent… The licence is MIT.

When your agent uses it

  • Needs to create
  • Improve content that shapes how candidates and the public perceive the company as a place to work

Example prompts

  • “/employer-brand”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Identify the authentic story — Ask the user what is genuinely true and distinctive about working at this company. Employer brand must be…
  2. Choose the content format — Select from: careers page, values document, engineering blog post, "day in the life" feature, team spotlight…
  3. Draft the content — Write using the Voice-Evidence-Proof framework (see below). Lead with what candidates care about (impact, growth…
  4. Ground every claim in evidence — For each cultural claim, attach a specific example, policy, or anecdote. "We value work-life balance"…
  5. Calibrate the tone — Match the company's actual communication style. A developer tools startup sounds different from a healthcare company…
  6. Review for authenticity — Flag any claims that feel aspirational rather than current. Mark those explicitly or remove them. Candidates…

What it can do on your machine

Read from SKILL.md and the folder at commit 4ad31b4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Employer Brand loads about 2.3k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 1,006 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shawnpang/startup-founder-skills at commit 4ad31b4, republished under its MIT licence (© shawnpang). 1,006 words, ~2,304 tokens.

Download SKILL.mdSave it as .claude/skills/employer-brand/SKILL.md (or your agent's skills folder).
name
employer-brand
description
When the user needs to create or improve content that shapes how candidates and the public perceive the company as a place to work.
related
job-description, content-strategy
reads
startup-context

Employer Brand

When to Use

Activate when the user asks to write careers page copy, create a culture document, draft an engineering blog post, build "day in the life" content, document company values, or generally improve how the company presents itself to prospective hires. Also activate when the user is struggling to differentiate their startup from competitors in the talent market.

Context Required

  • From startup-context: Company name, mission, stage, team size, founding story, values (stated or practiced), remote/hybrid/onsite policy, notable perks, and any existing brand voice guidelines.
  • From user: The specific content type needed, target audience (engineers, designers, go-to-market, general), existing content to build on (if any), and what makes the company genuinely distinctive as a workplace.

Workflow

  1. Identify the authentic story — Ask the user what is genuinely true and distinctive about working at this company. Employer brand must be rooted in reality or it backfires at onboarding. Probe for specific stories, rituals, and decisions that reveal culture.
  2. Choose the content format — Select from: careers page, values document, engineering blog post, "day in the life" feature, team spotlight, hiring process transparency post, or culture deck.
  3. Draft the content — Write using the Voice-Evidence-Proof framework (see below). Lead with what candidates care about (impact, growth, people, flexibility), not what the company cares about (mission statements in a vacuum).
  4. Ground every claim in evidence — For each cultural claim, attach a specific example, policy, or anecdote. "We value work-life balance" becomes "We have no meetings on Wednesdays and our average team member works 42 hours/week."
  5. Calibrate the tone — Match the company's actual communication style. A developer tools startup sounds different from a healthcare company. Avoid generic startup voice.
  6. Review for authenticity — Flag any claims that feel aspirational rather than current. Mark those explicitly or remove them. Candidates trust specificity and distrust superlatives.

Output Format

The deliverable depends on the content type:

  • Careers page: Full page copy in markdown, section by section, ready for a designer to lay out.
  • Values document: 4-6 values with definitions, behavioral examples, and counter-examples.
  • Blog post: A complete draft with headline, intro, body sections, and closing CTA.
  • Day in the life: A narrative feature with time stamps, quotes, and concrete details.
  • Culture deck: Slide-by-slide content outline with speaker notes.

Frameworks & Best Practices

The Voice-Evidence-Proof (VEP) Framework

Every employer brand claim needs three layers:

  • Voice: The claim stated in the company's natural tone. ("We ship fast and learn faster.")
  • Evidence: A concrete policy, practice, or structure that supports the claim. ("Our deploy pipeline runs 40+ times per day. Every engineer ships to production in their first week.")
  • Proof: A real story or data point that makes it undeniable. ("Last quarter, a new hire identified a UX issue on day 3 and had the fix live by day 5 — no approval chain needed.")
Careers Page Structure

A high-converting careers page follows this arc:

  1. Hero section: A bold statement about what working here means. Not the company mission — the employee promise. (e.g., "Build the future of [X] with people who actually care about the craft.")
  2. Why here: 3-4 tiles or sections covering the top reasons candidates join. Use the candidate's language: impact, ownership, growth, people, flexibility.
  3. How we work: Concrete details about rituals, tools, and cadences. Remote practices, meeting culture, shipping rhythm.
  4. Team spotlight: Photos, quotes, and short bios of real team members. Diverse representation matters.
  5. What we offer: Comp philosophy, benefits, equity, and learning budget — in specific terms, not vague promises.
  6. Open roles: Live job listings with clear titles and locations.
  7. Application process: What candidates can expect step-by-step with timeline estimates.
Show full SKILL.md (404 more words)Show less
Values Documentation Framework

Strong values have four properties:

  • Specific: "Default to transparency" is better than "Integrity."
  • Opinionated: A real value implies a trade-off. If no reasonable company would disagree, it's not a value — it's a platitude.
  • Behavioral: Each value should connect to observable actions. Define "what this looks like" and "what this does NOT look like."
  • Prioritized: When two values conflict, which one wins? Documenting this makes values real.

Example:

## Ship and Iterate
We choose progress over perfection. We'd rather learn from a live
feature than debate a hypothetical one.

What this looks like:
- Shipping an MVP to 10 customers before building the "full" version
- Writing a quick RFC instead of scheduling a meeting
- Celebrating a launched experiment that failed, because we learned

What this does NOT look like:
- Shipping broken code that erodes customer trust
- Skipping testing because "we move fast"
- Ignoring feedback because "we already shipped it"
Engineering Blog Post Framework

Engineering blog posts serve dual duty as employer brand and thought leadership.

  1. Start with the problem — Technical readers want to know the challenge before the solution.
  2. Show the constraints — What made this problem hard at your scale, stage, or domain?
  3. Walk through the decision — Show the trade-offs and alternatives you considered, not just the final choice.
  4. Be honest about what didn't work — Vulnerability builds trust. "Our first approach failed because..." is more compelling than a clean narrative.
  5. End with what's next — Open loops invite follow-up conversations and signal that interesting work continues.
"Day in the Life" Content Structure
  • Format: First-person narrative or interviewer-led Q&A, structured around a real or representative day.
  • Include: Specific tools, meetings (or lack thereof), lunch habits, collaboration moments, and a real challenge they worked through.
  • Avoid: Sanitized, marketing-approved-sounding quotes. Let personality come through.
  • Diversity: Feature team members across roles, levels, and backgrounds.
Anti-Patterns to Avoid
  • The aspiration trap: Writing about the culture you want instead of the culture you have. Candidates who join based on aspiration churn fast.
  • Superlative overload: "World-class team, cutting-edge technology, incredible culture." These words mean nothing without evidence.
  • Perks over substance: Leading with the ping-pong table, free lunch, or unlimited PTO instead of meaningful work, good management, and career growth.
  • Copying big tech: Your startup is not Google. Don't mimic their tone, perks list, or values format. Lean into what makes you different.
  • Stock photo culture: Use real photos of real team members or none at all. Staged stock photos actively hurt trust.
  • job-description — Every JD is an employer brand touchpoint. Ensure JD voice matches the careers page.
  • content-strategy — Employer brand content (blog posts, social) should integrate into the broader content calendar and distribution plan.

Examples

Prompt: "Write careers page copy for our developer tools startup. We're 20 people, Series A, remote-first."

Good output snippet:

# Build tools that developers actually love

We're a team of 20 building [product] — and we're looking for people
who care about developer experience as much as we do.

## Why engineers join us

**You'll ship to thousands of developers weekly.** Our CLI has 50K+
monthly active users. The feature you build on Monday gets feedback
in Slack by Thursday.

**You'll own entire systems.** We don't have ticket jockeys. Each
engineer owns a domain — from design through production monitoring.
Your last PR won't need four approvals to merge.

**You'll work with people who write well.** We're remote-first and
async-heavy. That means clear writing, thoughtful RFCs, and Loom
videos instead of status meetings.

Prompt: "Help us write our company values. We keep saying we have them but haven't documented anything."

Good output snippet:

Let's start by identifying what's actually true about how you operate
today — not what sounds good on a poster. I'll ask a few questions:

1. When your team disagrees on a decision, how does it get resolved?
2. What behavior have you praised in the last month?
3. What's something your team does that an outsider might find unusual?
4. When has the team made a hard trade-off, and which side did you land on?

Your answers will reveal the real values. Then we'll name them, define
them with behavioral examples, and pressure-test them with counter-
examples to make sure they're genuinely opinionated.

© shawnpang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/employer-brand of shawnpang/startup-founder-skills.

Open the folder on GitHubat commit 4ad31b4

Compare with similar skills

Employer Brand next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Employer Brand compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Employer Brand this skillshawnpang/startup-founder-skills343—~2.3kAutomated safety check: PassMIT
Socialcoreyhaines31/marketingskills54k4 repos~4.5kAutomated safety check: PassMIT
HumanizerAzure-Samples/interview-coach-agent-framework17338 repos~5.8kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
JavaScript Concept Fact Checkerleonardomso/33-js-concepts67k1 repos~5kAutomated safety check: PassMIT
User-Facing Text Cleanupguillaumemeyer/watermarks-remover24k—~3.5kAutomated safety check: PassMIT

Similar skills

  • Social

    coreyhaines31/marketingskills

    When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage.

    54k GitHub starsUsed in 4 repos~4.5k tokens
    Writing & ContentAuto-check passed
  • Humanizer

    Azure-Samples/interview-coach-agent-framework

    Official

    Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.

    173 GitHub starsUsed in 38 repos~5.8k tokens
    Writing & ContentAuto-check passed
  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed
  • JavaScript Concept Fact Checker

    leonardomso/33-js-concepts

    Verifies the technical accuracy of JavaScript concept pages by checking code examples, MDN and ECMAScript claims and external links through a five-phase method.

    67k GitHub starsUsed in 1 repo~5k tokens
    Writing & ContentAuto-check passed
  • User-Facing Text Cleanup

    guillaumemeyer/watermarks-remover

    Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

    24k GitHub stars~3.5k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Install Anti Slop

    trycompai/crm

    Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.

    11k GitHub starsUsed in 1 repo~881 tokens
    Writing & ContentAuto-check passed

More from shawnpang/startup-founder-skills

All 50 skills in this repo
  • Accelerator Application

    shawnpang/startup-founder-skills

    When the user wants to apply to startup accelerators, incubators, or fellowship programs.

    343 GitHub stars~2.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Architecture Design

    shawnpang/startup-founder-skills

    When the user needs to design or evaluate system architecture — service boundaries, data models, API contracts, infrastructure topology, database selection, or dependency analysis.

    343 GitHub stars~2.1k tokensUpdated 6 mo ago
    Auto-check passed
  • Board Update

    shawnpang/startup-founder-skills

    When the user needs to write a monthly or quarterly investor update, prepare a board deck, or communicate company progress to stakeholders.

    343 GitHub stars~2.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Churn Analysis

    shawnpang/startup-founder-skills

    When the user needs to identify at-risk accounts, understand why customers are leaving, reduce churn rate, build health scores, design save plays, or create win-back campaigns.

    343 GitHub stars~2.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Cicd Setup

    shawnpang/startup-founder-skills

    When the user needs to set up or improve CI/CD pipelines — GitHub Actions, GitLab CI, deployment automation, or says "set up CI", "automate deployment", "add tests to pipeline", "fix my build".

    343 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Code Review

    shawnpang/startup-founder-skills

    When the user asks for a code review, shares code for feedback, or says "review this", "check my code", "what's wrong with this".

    343 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Employer Brand

What does Employer Brand do?

When the user needs to create or improve content that shapes how candidates and the public perceive the company as a place to work. Employer Brand is an agent skill from shawnpang/startup-founder-skills. When the user needs to create or improve content that shapes how candidates and the public perceive the company as a place to work.

When should I use Employer Brand?

Employer Brand fits situations like: needs to create; improve content that shapes how candidates and the public perceive the company as a place to work.

How do I install Employer Brand in Claude Code?

Run `npx skills add shawnpang/startup-founder-skills --skill employer-brand -a claude-code`. Or copy the skill folder (skills/employer-brand in shawnpang/startup-founder-skills) into .claude/skills/employer-brand in your project. Claude Code loads it when a task matches its description.

How do I install Employer Brand in Codex?

Run `npx skills add shawnpang/startup-founder-skills --skill employer-brand -a codex`. Or copy the skill folder (skills/employer-brand in shawnpang/startup-founder-skills) into .agents/skills/employer-brand in your project. Codex loads it when a task matches its description.

Can I use Employer Brand in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shawnpang/startup-founder-skills --skill employer-brand -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/employer-brand, .gemini/skills/employer-brand, .github/skills/employer-brand and .opencode/skills/employer-brand in your project.

What does Employer Brand need to run?

SKILL.md names no scripts, command-line tools or credentials: Employer Brand is instructions for the agent only.

Does Employer Brand access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Employer Brand safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Employer Brand use?

Employer Brand is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Employer Brand use?

About 2.3k tokens (SKILL.md is roughly 9.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Employer Brand?

Skills that share tags, products or a category with Employer Brand: Social (coreyhaines31/marketingskills, 54k stars), Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars), Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars) and JavaScript Concept Fact Checker (leonardomso/33-js-concepts, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Employer Brand?

shawnpang (a GitHub user) maintains it in shawnpang/startup-founder-skills, which has 343 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on March 16, 2026.

Source: shawnpang/startup-founder-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.