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 connection-findergit 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/connection-finder)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/connection-finder"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/connection-finder/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/connection-finder"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/connection-finder.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 | $0.00092 | $0.01346 |
| Opus 5 | $0.00046 | $0.00673 |
| Sonnet 5 | $0.00018 | $0.00269 |
| Haiku 4.5 | $0.00009 | $0.00135 |
Grade A, and why
connection-finder 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 11d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connection finder
Source: points/cold-email-rules.md rule 5 — "Compare yourself to the recipient — the 'like you' move."
Why this exists
Rachel Konrad's rule 5 is the most-failed rule in the playbook. Most "like you" lines are either:
- Generic — "Like you, I believe AI will transform the future." (Everyone believes that. Cut.)
- Self-diminishing — "Like you, but at a vastly smaller scale." (They already know that. Cut.)
- Boastful — "Like you, I'm super smart and super successful." (Backfires. Cut.)
What works: specific, genuine, slightly unexpected. A "like you" line should reference a sensory detail from your shared origin that cannot be sent to anyone else — a specific cuisine you both grew up with, a specific city you both lived in for a specific year, a specific job you both did before the one you're emailing about. That's the whole point.
What you need
This skill takes two inputs:
- Recipient dossier (from
recipient-research) - Writer's profile (
context/about-me.mdor equivalent)
If either is missing, run recipient-research first or ask the user to point you at their about-me file.
What to look for
Cross-reference the two profiles for overlap in these eight categories. The further down the list, the higher the leverage.
1. Career parallel (medium — common)
Worked at the same company, in the same industry, in similar roles. Use only if there's a specific overlap — same product, same team, same era.
2. Educational parallel (low — overused)
Same school. Useful only with a specific shared experience (same professor, same class, same dorm). "Stanford MBA" alone is too generic.
3. Geographic / origin parallel (medium — strong if specific)
Same hometown. Same immigration story. Lived in the same unusual place. Visited the same specific spot.
4. Formative experience parallel (high)
Both military veterans. Both first-generation immigrants. Both built something from zero. Both worked a manual-labor job before a desk job. Specific date or place beats abstract category.
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.
- 11d ago First seen · 110 lines · 92 tokens per session scan A bd95f004dd2f
connection-finder is a skill published in the GitHub repository kalyvask/winning-writing (13 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 1,346 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
domain
When you want to brainstorm and check available .com domains for a new project — brand naming, aftermarket pricing (HugeDomains / Afternic / Sedo / Dan), USPTO trademark screening, and social handle availability. Built on Laura Roeder's "work backwards from availability, not from a name you fell in love with"…
slide-deck
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDEDECKREPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand…
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
session-cleanup
Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation.…
deep-research
When you want multi-source, multi-step research on a topic — competitor research before a sales call, market research for a new business idea, positioning angles, due diligence on a partnership or podcast guest, tech decision research (which DB, which auth), or any "I need to actually understand X." Combines…