Seven Claude Code skills for the work a PM actually does.
Outreach follow-ups, LinkedIn drafts, contract review, dispute letters, interview prep, long-form articles, and a writing audit that catches the machine tells before anything goes out. Every one of them started as a skill I use daily. They have been de-identified so you can anchor them in your work instead of inheriting mine.
Installs the seven skills, asking before it overwrites any you already have
Tells you what each skill is for
About 2 minutes. It asks before anything system-wide, and never asks for a password or API key.
Install claude-skills-pm for me (https://github.com/debashisn94/claude-skills-pm): seven open-source skills for product and writing work (anti-ai-audit, cold-outreach-followup, contract-review, dispute-letter, linkedin-post, medium-article, pm-prep).
1. Clone the repo and read README.md.
2. If you are Claude Code, copy every folder in skills/ into ~/.claude/skills/. If a skill with the same name is already there, ask me before overwriting it. If you are another agent, run `npx skills add https://github.com/debashisn94/claude-skills-pm`, and tell me plainly if your agent cannot load skills.
3. Tell me to restart my agent, then list the seven skills with one line each on when to reach for it.
4. Mention the optional voice corpus (voice-corpus/README.md): a few samples of my own writing that make the writing skills sound like me.
Ground rules: only download from the GitHub links above. Ask me before using sudo, installing anything system-wide (Homebrew, Node, Python, ffmpeg) or changing files outside the install folder. Never ask me to paste a password or API key into this chat. When you finish, tell me what you installed, where it lives, and the one command I run to use it. If you cannot run terminal commands, give me the exact steps to run myself instead.
MIT licensed. v0.1, seven skills, stable in daily use.
~/code
$git clone https://github.com/debashisn94/claude-skills-pm.gitCloning into 'claude-skills-pm'...$tree claude-skills-pmskills/ anti-ai-audit/ SKILL.md references/ cold-outreach-followup/SKILL.md contract-review/SKILL.md dispute-letter/SKILL.md linkedin-post/SKILL.md medium-article/SKILL.md pm-prep/SKILL.mdvoice-corpus/ README.mdLICENSE$cp -r claude-skills-pm/skills/* ~/.claude/skills/# Restart Claude Code and the seven show up.
7 skillsMITv0.1
01What it is
A skill is a folder. The value is in what it says.
A Claude Code skill is a folder with a SKILL.md in it. Claude reads the description, works out when the skill applies, and follows the instructions inside. That is the whole mechanism, and it is why the interesting part is the writing rather than the plumbing.
Each of these came out of my own week and got edited every time it produced something I would not have sent. Hundreds of real runs across job applications, vendor disputes, LinkedIn posts, Medium drafts, cold emails and contract reviews. What survived that is what sits in the repo.
Then I stripped my data out of them. The examples carry placeholders like [your metric] and [counterparty] on purpose, so the structure travels and the specifics stay yours.
01A folderskill-name/
02with a SKILL.md in itSKILL.md
03Claude reads the descriptionworks out when the skill applies
04and follows the instructions insideThat is the whole mechanism
02The seven
The seven.
Invoke one directly with a slash command, or describe the task and let Claude route to it.
01+ references/
/anti-ai-audit
A 14-section audit against the patterns that make writing read as machine-written: banned words, em dashes, neat tricolons, callback closers, endings that tie up too tidily. It runs before anything public-facing ships. The full style guide travels with it as a reference file the audit loads.
02
/linkedin-post
LinkedIn drafts in your voice. Tone-mode aware, so a career post and a craft post do not come out sounding identical, and it hands the result to anti-ai-audit before you ever see it.
03
/medium-article
Long-form drafts in your voice, taken to publication-ready. Also handles the outline-to-article expansion when you already know the shape.
04
/cold-outreach-followup
The D+3, D+10 and D+21 follow-up sequence for job applications and prospecting. Each touch escalates the ask instead of repeating the last email in different words.
05
/dispute-letter
Dispute letters written to survive a tribunal. Evidence cited, a number anchored, a deadline set, escalation signalled. Deposits, refunds, billing, vendors.
06
/contract-review
Risk flagging for MSAs, NDAs, employment agreements, contractor ICAs and severance. It marks the clauses worth arguing over and drafts the counter-ask.
07
/pm-prep
PM interview prep: case studies, product design, A/B test design, KPI trees, RICE, market segmentation, behavioural stories.
Anywhere you like. The repo is small, seven folders and a licence.
2
Copy
cp -r claude-skills-pm/skills/* ~/.claude/skills/
Drops each skill folder into your own skills directory.
3
Restart
/skill-name
Restart Claude Code and the seven show up. Call one with /skill-name, or just say what you need and let it pick.
04Layout
How the repo is laid out.
Each skill is a folder with a SKILL.md plus whatever reference docs it needs. Nothing gets compiled, so an edit takes effect the next time Claude Code loads.
These carry structure, not my personal data. A dispute letter skill that already knows my landlord is useless to you. So the examples are blanks, and the first thing worth doing is filling them with your own stories, numbers and phrasing.
The three voice-anchored skills, anti-ai-audit, linkedin-post and medium-article, get noticeably sharper if you add a voice corpus: a small folder of writing you published before you started using AI. It is optional and everything works without it. I think the corpus is where most of the gain sits, though it is honestly the part I have tested least on writing other than my own.
The convention for it lives in voice-corpus/README.md.
anti-ai-auditlinkedin-postmedium-article
voice-corpus/README.mdOptional. Everything works without it.
06Where it stands
Where it stands.
v0.1
Seven skills, stable
All seven are in daily use and de-identified for public use. MIT licensed, so fork and republish as you like.
Next
A scored voice-match variant
Drafts scored against your own published writing rather than checked against a list of tells. No date on it yet.
Install them, then start cutting the bits that do not sound like you.
If a skill gets something wrong for your work, that is a signal about your work, and the fix is usually four lines in a markdown file. Open an issue if you want a second pair of eyes on it.