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 mshadmanrahman/pm-pilot --skill writing-stylegit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote 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/mshadmanrahman/pm-pilot/writing-style)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/writing-style"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/writing-style/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/mshadmanrahman/pm-pilot/writing-style"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/writing-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00514 |
| Opus 5 | $0.00023 | $0.00257 |
| Sonnet 5 | $0.00009 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
writing-style 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 10d 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.
What it actually says
Writing Style
TEMPLATE for voice-consistent writing. Configure once, apply everywhere.
Trigger
When writing long-form content (blog posts, articles, newsletters, LinkedIn posts).
Voice Profile Setup
To configure your voice, provide 2-3 sample posts that represent your best writing. The skill extracts:
- Tone: formal/casual/provocative/warm/authoritative
- Sentence patterns: short and punchy vs. long and flowing, fragment usage, rhetorical questions
- Vocabulary: technical depth, jargon level, signature phrases
- Structure: how you open, transition, and close
- Perspective: first person, second person, or mixed
Setup Process
1. User provides 2-3 writing samples
2. Analyze each sample for the 5 dimensions above
3. Create voice profile (stored in memory)
4. Confirm profile with user before applying
Voice Profile Format
voice:
tone: [e.g., "direct, warm, slightly irreverent"]
sentences: [e.g., "short paragraphs, 1-3 sentences each, frequent fragments"]
vocabulary: [e.g., "technical but accessible, avoids buzzwords, uses analogies"]
structure: [e.g., "hook with bold claim, build with examples, end with actionable takeaway"]
perspective: [e.g., "first person, speaks from experience"]
avoid: [e.g., "em dashes, exclamation marks, corporate jargon"]
signature: [e.g., "ends with a question to the reader"]
Application Process
- Load voice profile from memory.
- Draft content following the requested format.
- Self-review against all 5 dimensions.
- Adjust any deviations before presenting.
Rules
- Never override voice profile without explicit request.
- If no profile configured, ask for samples before writing.
- Flag when a requested format conflicts with the voice profile (e.g., formal voice + casual platform).
- Preserve the user's authentic voice. Enhance clarity, never change personality.
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.
- 10d ago First seen · 60 lines · 46 tokens per session scan A 74785b28fc8b
writing-style is a skill published in the GitHub repository mshadmanrahman/pm-pilot (20 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 514 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
analyze-codebase
Run comprehensive PLG analysis on a codebase to detect tech stack, existing growth features, and revenue opportunities. Use when the user says "analyze", "scan", "audit codebase", or "find growth opportunities".
build-implementation
Generate context-aware implementation prompts for a selected growth loop. Use when the user says "build", "implement", "generate code", "create prompt", or "how do I build this".
deploy-telemetry
Set up analytics and tracking infrastructure for growth loops. Use when the user says "deploy telemetry", "set up analytics", "tracking", "events", "push to supabase", or "skene push".
plan-growth-loop
Generate prioritized growth loops with implementation roadmaps based on codebase analysis. Use when the user says "plan", "growth loops", "prioritize", "what should I build", or "roadmap".
validate-loop
Check if growth loop requirements are actually implemented in the codebase. Use when the user says "validate", "check status", "skene status", "is it done", or "verify implementation".
initialize-config
Set up Skene configuration for a project. Use when starting a new PLG analysis, when .skene.config is missing, or when the user says "skene init", "set up skene", or "configure skene".