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 warmth-and-competencegit 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/warmth-and-competence)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/warmth-and-competence"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/warmth-and-competence/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/warmth-and-competence"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/warmth-and-competence.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 | $0.00000 | $0.02268 |
| Opus 5 | $0.00000 | $0.01134 |
| Sonnet 5 | $0.00000 | $0.00454 |
| Haiku 4.5 | $0.00000 | $0.00227 |
Grade A, and why
warmth-and-competence 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warmth and competence
Source: points/core-rules.md rule 15 ("show competence AND warmth in a single sentence" — Kramon's hardest rule). Grounded in Susan Fiske's stereotype-content model from Princeton — humans evaluate every new face on two axes: warmth (intent — friend or foe?) and competence (capability — can they actually do it?).
The premise
Cold writing reads as cold-but-impressive. Eager writing reads as warm-but-unserious. The hardest move in business writing is to score high on both axes in the same sentence — a sentence that proves you're capable AND that the recipient is going to like working with you.
The two failure modes are equally bad and unequally visible:
-
The consultant trap (high competence, low warmth): you sound like the smartest person in the meeting, but the recipient instinctively doesn't want you on their team. Common in MBA-trained writers, ex-management-consultants, finance veterans.
-
The intern trap (high warmth, low competence): you sound thoughtful and friendly, but the recipient instinctively doesn't trust you to ship. Common in early-career writers, recent grads, anyone overcorrecting from the consultant trap.
The recipient registers the verdict in roughly one second. The writer never recovers in the same email.
What signals each axis
Warmth signals (do I want to work with this person?)
Up:
- Specific shared experiences ("I grew up in your hometown, too" — Konrad's "like you" rule, with a real shared detail)
- Honest self-assessment ("I'm three weeks into this and still figuring it out")
- A genuine moment of humor or vulnerability
- Acknowledging the recipient's time, not just their status
- "I'd love to hear what you think" (when genuine)
- Crediting others for things you didn't do alone
- A specific concrete detail only a real person would include
- Door-open-for-no in the ask ("I know it's a big ask, no is a perfectly fine answer")
Down:
- Pure transactional language ("seeking 30 minutes for X")
- Obvious flattery ("your work has been transformational")
- "Hope to leverage your network" — language that's clearly extractive
- Robotic structure ("Background: …; Ask: …; Next steps: …")
- No first-person voice — passive, third-person, or pluralized "we" when you mean "I"
- Talking about yourself non-stop with no curiosity about the recipient
- "I appreciate your time" — performative, every cold email says it
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 · 186 lines · 0 tokens per session scan A f39a88d48396
warmth-and-competence is a skill published in the GitHub repository kalyvask/winning-writing (13 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,268 tokens. 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
umap-learn
Use UMAP-learn for nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows.
bulk-rnaseq
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and…
shap
Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global SHAP visualizations.
genomic-intelligence
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…