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 kalyvask/winning-writing --skill winning-writing-criticgit clone --depth 1 https://github.com/kalyvask/winning-writingWrote 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/kalyvask/winning-writing/winning-writing-critic)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/winning-writing-critic"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/winning-writing-critic/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/kalyvask/winning-writing/winning-writing-critic"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/winning-writing-critic.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 | $0.00109 | $0.01165 |
| Opus 5 | $0.00055 | $0.00583 |
| Sonnet 5 | $0.00022 | $0.00233 |
| Haiku 4.5 | $0.00011 | $0.00117 |
Grade A, and why
winning-writing-critic 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 12d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Winning Writing critic
Source: every file in points/. This skill is the orchestrator — it pulls from all of them.
What it does
Given any draft, score it against the full Winning Writing rubric, then rewrite it. The output is two things: a numbered critique and a clean rewrite.
The rubric
Score each dimension 0–10. Anything below 7 needs work.
1. Main point (0–10)
- Is there a single clear main point?
- Is it in the first sentence?
- Could the reader summarize it in 6 words?
2. Audience (0–10)
- Does the writer know who's reading this?
- Is it written for them, not at them?
- Would the reader feel "one in a million" or "one of a million"?
3. BLUF (0–10)
- Is the conclusion up front?
- Or is there organ music — buildup, throat-clearing, qualification?
4. Length (0–10)
- Is this as short as it can be without losing substance?
- Cold email under 200 words? Op-ed under 800?
5. Story vs. resume (0–10)
- Is there a specific scene with date, place, sensory detail?
- Or is it a list of accomplishments?
6. "Like you" / connection (0–10)
- Is there a specific, genuine bridge between writer and reader?
- Not generic ("we both believe in AI")
- Not self-diminishing ("but at a smaller scale")
7. Why-you / why-now (0–10)
- What makes this writer uniquely qualified to say this?
- Why is this timely?
8. The ask or offer (0–10)
- Is the ask small and specific?
- Is there an offer, or is the writer only taking?
- Door open for no?
9. Tone (0–10)
- Conversational, warm, human?
- Confident but humble?
- On their toes, not on their heels?
- Says what they like AND would like — not only what they don't?
10. Jargon (0–10, deducting)
- Banned words present? (See banned-jargon.md)
- AI tells? ("It's not just X — it's Y," "delve," "tapestry")
- Wordy phrases?
11. Specifics (0–10)
- Real names, real numbers, real interviews?
- Or vague abstractions?
12. Sentence rhythm (0–10)
- Vary in length?
- Read aloud — does it have music?
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.
- 12d ago First seen · 132 lines · 109 tokens per session scan A d615f77f3446
winning-writing-critic is a skill published in the GitHub repository kalyvask/winning-writing (14 stars, last pushed 6d ago), licensed MIT. It adds 109 tokens to every session and 1,165 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 2026-08-30.
Other skills, from other repositories
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
project-retrospective
Generate a LESSONS.md from a finished project: what worked, what didn't, what to reuse, what to retire — formatted for next-project carry-over.
template-selector
Recommend the right skill bundle, agent, and workflow sequence for a new project — so media professionals can start producing instead of browsing a 394-skill library.
multi-author-harmonizer
Reviews a text written or assembled by multiple authors and produces a detailed inconsistency report — flagging voice shifts, terminology mismatches, tonal clashes, and formatting discrepancies — with specific harmonisation recommendations for each.
jargon-flagger
Scans a draft and flags every instance of technical jargon, unexplained acronyms, and insider language that a general-audience reader would not understand — with a plain-language alternative for each.
passive-voice-checker
Identifies every passive-voice construction in a draft, assesses whether each weakens or serves the prose, and offers active-voice alternatives for those that should be changed — while leaving justified passives alone.