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 Abhillashjadhav/AI-PM-essential-skills --skill human-product-writergit clone --depth 1 https://github.com/Abhillashjadhav/AI-PM-essential-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/abhillashjadhav/ai-pm-essential-skills/human-product-writer)<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/human-product-writer"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/human-product-writer/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/abhillashjadhav/ai-pm-essential-skills/human-product-writer"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/human-product-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00112 | $0.01144 |
| Opus 5.5 | $0.00045 | $0.00458 |
| Sonnet 5.5 | $0.00022 | $0.00229 |
| Haiku 4.5 | $0.00011 | $0.00114 |
Grade A, and why
human-product-writer 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 1mo 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human Product Writer
Edit product writing so it sounds like a sharp practitioner wrote it, not a model performing confidence.
Input contract
Require:
- The draft to edit.
- The intended audience or publishing surface when it is not obvious.
- The outcome the reader should leave with when the draft has no clear point.
Do not invent personal experience, metrics, customer stories, source claims, or product outcomes. Mark unsupported placeholders instead.
Preserve first
Before editing, identify internally:
- the core product judgment;
- the strongest concrete fact or mechanism;
- 3 to 5 voice signals such as bluntness, spoken cadence, uncertainty, humour, specificity, or technical depth;
- any sentence that already sounds recognisably human.
Keep these intact unless they are unclear or inaccurate.
Evidence boundary
Treat the supplied draft and evidence as the factual boundary for the rewrite.
- Every number, named mechanism, quotation, customer result, causal claim, and product outcome in the edited draft must be traceable to the supplied material.
- Reordering, compressing, and clarifying supplied claims is allowed. Adding new factual content is not.
- If the user asks for proof that was not supplied, keep an explicit marker such as
[SOURCE NEEDED]or[METRIC NEEDED], or ask for the missing evidence. - Never turn an assumption into a result or a placeholder into a plausible-sounding number.
Remove these patterns
Reject or rewrite:
- binary contrast templates such as “It is not X. It is Y.”;
- faux-insight openings such as “What most people miss…”;
- throat-clearing such as “Here’s the thing” or “Let me be clear”;
- dramatic fragment stacks;
- noun-phrase colon reveals used for fake suspense;
- generic numbered or bullet structures when prose reads better;
- inflated words such as leverage, robust, transformative, game changer, cutting-edge, empower, streamline, or paradigm shift;
- weasel attribution such as “experts agree” or “studies show” without a named source;
- fake-profound endings and slogan-like mic drops;
- repetitive sentence shapes and over-polished symmetry;
- abstract claims when the draft contains a concrete mechanism, number, decision, failure, or trade-off.
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.
- 1mo ago Changed · +2 lines c9386af2fbde
- 2mo ago First seen · 118 lines · 112 tokens per session scan A 8d1e2ccf9a02
human-product-writer is a skill published in the GitHub repository Abhillashjadhav/AI-PM-essential-skills (9 stars, last pushed 17d ago), licensed MIT. It adds 112 tokens to every session and 1,144 once invoked, about $0.0004 per session on Opus 5.5. 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.
human-product-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| human-product-writerAbhillashjadhav/AI-PM-essential-skills | Skill | 9 | 17d ago | MIT | A | 112 | Claude Code |
| research-reportShenSeanChen/waku-agent | Skill | 2.2k | 17d ago | MIT | A | 0 | Claude Code, Codex |
| building-agentsericrisco/rsc-harness | Skill | 573 | yesterday | MIT | A | 85 | Claude Code, Codex |
| debloatLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 178 | Claude Code, Codex |
| re0-gitLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 61 | Claude Code, Codex |
| re0-importLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 84 | Claude Code, Codex |
| re0-workflowLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 86 | Claude Code, Codex |