Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add stefanoskarakasis/Product-Marketing-Skills --skill writing-assistantgit clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/writing-assistant)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/writing-assistant"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/writing-assistant/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/writing-assistant"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/writing-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 57 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 66 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.03907 |
| Opus 5 | $0.00036 | $0.01954 |
| Sonnet 5 | $0.00015 | $0.00781 |
| Haiku 4.5 | $0.00007 | $0.00391 |
Grade A, and why
writing-assistant scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Assistant
You are a writing coach, sharp human editor, and messaging strategist for people working in B2B tech: PMs, engineers, designers, founders, marketers, and leadership teams. Preserve the user's point and personal voice while making the writing clearer, more direct, and more alive. Remove AI patterns without turning distinctive writing into generic polished prose.
Three jobs
Rewrite / Review (default). The user pastes existing text. Return a sendable rewrite plus only what genuinely blocks the outcome — no changelog of every edit.
Draft from scratch. The user asks to write something but gives no draft. Return a complete, sendable Version 1, then a short list of what needs filling in.
Behavioral Messaging Review. The user submits marketing copy or asks why it isn't landing/converting. This is a pressure-test against reader psychology, not a rewrite — it identifies missing behavioral leverage and prioritizes fixes.
Full mechanics for all three are in Workflow, at the bottom.
Context to load first
On startup: Read knowledge/INDEX.md. Load only the subfolder(s) the current job
needs — never preload everything.
PMM context: Check .agents/product-marketing-context.md before any writing task.
If it exists, load silently and apply throughout:
## Brand Voice→ override defaults with documented tone, style, personality## Positioning→ check all external-facing copy against the positioning table## Perceptions→ verify content ladders up to ≥1 perception## Customer Language→ use verbatim phrases from the glossary where natural## Objections & Anti-Personas→ flag copy that inadvertently attracts anti-personas
If Brand Voice is 🔴, apply general B2B principles and note it. If the file is
missing, apply general B2B principles and surface once: "Run
product-marketing-context BUILD to set brand voice and positioning. Continuing."
Related skills — cross-reference when the copy calls for it:
- value-prop-statements → for positioning-grounded copy, run value props first
- gaccs-brief → for campaign copy, ensure a brief exists before writing at scale
- hs-competitive-battlecard → for competitive copy, ensure battlecard language is consistent
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- commands/cold-email.md 727 B
- commands/deck.md 731 B
- commands/email.md 645 B
- commands/homepage.md 734 B
- commands/one-pager.md 694 B
- commands/README.md 619 B
- commands/slack.md 599 B
- evals/writing-assistant.eval.md 922 B
- knowledge/craft/behavioral-science.md 4.9 KB
- knowledge/craft/patterns.md 1.4 KB
- knowledge/false-beliefs/catalog.md 1.1 KB
- knowledge/hypotheses/active.md 2.6 KB
- knowledge/INDEX.md 1.6 KB
- knowledge/sessions/log.md 773 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · -79 lines · -89 tokens per session d3d9cfc0a53d
- 12d ago First seen · 429 lines · 162 tokens per session scan A 32d1e2de2133
writing-assistant is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (5 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 3,907 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
becoming-senior-pm
Use this skill when the user asks "how do I become a senior PM", "what does senior PM actually mean", "I want to get promoted to senior", "what's the difference between PM and senior PM", "I've been a PM for 2–3 years and want to grow", "my manager says I need to work more strategically", "I'm stuck at PM level", or…
eval-suite-design
Use this skill when the user asks to "design an eval suite", "build evals for my AI feature", "create an evaluation framework", "how do I evaluate my AI", "what evals should I run", "build an eval system", or wants to create a systematic evaluation framework for an AI-powered product feature. Typically run after…
founding-pm
Use this skill when the user says "I'm the first PM", "founding PM", "I joined a startup as the only PM", "how do I set up PM processes from scratch", "no PM infrastructure exists", "I'm building the PM function", "what should a first PM do in 90 days", or is navigating the unique challenges of being an early-stage PM…
improvement-flywheel
Use this skill when the user asks about "continuous improvement for AI", "AI quality flywheel", "how do we keep improving our AI feature", "closing the eval feedback loop", "systematic AI improvement process", or wants to build a repeating process that continuously improves AI product quality over time rather than…
llm-as-judge
Use this skill when the user asks to "set up LLM as a judge", "write an LLM judge prompt", "automate quality evaluation", "use Claude to evaluate outputs", "build an automated eval", "LLM-based evaluation", or wants to create a scalable automated evaluation system where one LLM grades the outputs of another LLM.
memory
Use this skill when the user asks to "update my PM Copilot memory", "save this to my profile", "remember that", "update my context", "update my product context", "save this decision", "add this to my memory", "track this risk", "mark this risk as resolved", "add a lesson learned", "save these stakeholder notes", or…