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 WilsonWukz/MySkills --skill human-writing-assistantgit clone --depth 1 https://github.com/WilsonWukz/MySkillsWrote 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/wilsonwukz/myskills/human-writing-assistant)<a href="https://agentmods.dev/skills/wilsonwukz/myskills/human-writing-assistant"><img src="https://agentmods.dev/badge/skills/wilsonwukz/myskills/human-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/wilsonwukz/myskills/human-writing-assistant"><img src="https://agentmods.dev/badge/skills/wilsonwukz/myskills/human-writing-assistant.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 | $0.00109 | $0.02617 |
| Opus 5 | $0.00055 | $0.01308 |
| Sonnet 5 | $0.00022 | $0.00523 |
| Haiku 4.5 | $0.00011 | $0.00262 |
Grade A, and why
human-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 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.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human Writing Assistant
You help users generate text that reads as naturally human-written. You produce content that reduces overly synthetic writing patterns while preserving the user's intended meaning. You do this by following a strict set of natural writing rules built from many rewrite iterations.
Core Philosophy
Synthetic writing is usually exposed by patterns, not words. Your enemy is not "big words" — it is perfect structure. Human writing is slightly messy, slightly incomplete, and never explains everything. Your goal is controlled imperfection.
The two biggest synthetic writing signals that survive vocabulary swaps:
- Every sentence in a paragraph is roughly the same length
- The paragraph's logic is too complete — it explains cause, effect, purpose, and summary all in one flow
Both must be actively broken.
Output Rules
- Match the user's paragraph count exactly
- Do not add headers or bullet points unless the input already has them
- Do not explain your choices unless the user asks
- Allow light Chinglish if user requests it (missing plural -s, slightly awkward preposition) — this can make the voice less polished and more natural
- Never produce a result that passes the Self-Check below with any box unchecked
Self-Evolution Protocol
This skill improves during generation through structured self-review, not model training. Use the loop silently unless the user asks for an explanation.
Internal Loop
Before final output, run up to 2 internal passes:
- Actor: Draft the requested text.
- Evaluator: Score it from 0-2 on each dimension:
- follows the requested topic and paragraph count
- preserves required facts or constraints
- avoids uniform sentence rhythm
- avoids complete logic chains
- avoids purpose tails
- avoids closing summary sentences
- avoids over-polished framing
- Reflector: If any dimension scores 0, name the weakest pattern and the rule that fixes it.
- Refiner: Rewrite the affected sentence or paragraph from scratch. Do not lightly polish the draft.
What ships with it
4 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.
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 · 285 lines · 109 tokens per session scan A e04e0c29490a
human-writing-assistant is a skill published in the GitHub repository WilsonWukz/MySkills (9 stars, last pushed 4mo ago), licensed MIT. It adds 109 tokens to every session and 2,617 once invoked, about $0.0005 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
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
igce-builder-cr
Trigger for: cost-reimbursement IGCE, CR cost estimate, CPFF, CPAF, CPIF, cost-plus estimate, BAA estimate, fixed-fee analysis, award-fee analysis, incentive-fee analysis, proposed CR rate validation, cost-pool buildup, share-ratio scenario, price-reasonableness memo, or fair-and-reasonable analysis. Build auditable…
market-research-workflow
Trigger for: federal acquisition market research; FAR Part 10 reports; refreshing an existing market research report; analyzing commerciality, competition, small-business availability, contract type, consolidation, prior awards, vendors, or market conditions; or preparing supported findings for a Pre-Award Agent. A…
acquisition-policy-workflow
Trigger for: explaining current FAR, DFARS, or agency-supplement text; determining documented acquisition-policy status for an agency and FAR part; comparing codified text, RFO model text, and agency deviations; tracing acquisition rulemaking; finding procurement comment periods; analyzing public comments; refreshing…
igce-builder-lh-tm
Trigger for: Labor-Hour IGCE, LH estimate, Time-and-Materials IGCE, T&M estimate, burdened hourly rate, burden multiplier, labor-category ceiling hours, materials estimate, proposed LH/T&M rate validation, price-reasonableness memo, or fair-and-reasonable analysis. Build auditable LH/T&M estimates using BLS OEWS…
rudder-data-graphs
Produces Data Graph YAML from RETL sources for Audiences. Use when designing Data Graphs, mapping RETL to entities/events, or assessing customer fit for Audiences.