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 deepklarity/harness-kit --skill hk-skill-creatorgit clone --depth 1 https://github.com/deepklarity/harness-kitWrote 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/deepklarity/harness-kit/hk-skill-creator)<a href="https://agentmods.dev/skills/deepklarity/harness-kit/hk-skill-creator"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-skill-creator/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/deepklarity/harness-kit/hk-skill-creator"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 53 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00113 | $0.02786 |
| Opus 5 | $0.00056 | $0.01393 |
| Sonnet 5 | $0.00023 | $0.00557 |
| Haiku 4.5 | $0.00011 | $0.00279 |
Grade A, and why
hk-skill-creator 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 9d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hk-skill-creator — Create and Improve Skills
Create new skills and iteratively improve existing ones through a structured draft-test-evaluate-improve loop.
Context
<skill_context> $ARGUMENTS </skill_context>
If the context above describes what skill to create or improve, proceed. If empty or unclear, ask the user what they want the skill to do.
The Core Loop
The process of creating a skill:
- Understand what the skill should do, with concrete examples
- Draft the SKILL.md and any bundled resources
- Test by running Claude-with-the-skill on realistic prompts
- Evaluate outputs qualitatively (does it do what the user wants?) and quantitatively (assertions)
- Improve based on feedback — generalize, don't overfit
- Repeat until the user is satisfied
- Optimize the description for reliable triggering
Figure out where the user is in this process and help them progress. Maybe they want a skill from scratch — help narrow intent, draft, test. Maybe they already have a draft — go straight to eval/iterate. Maybe they just want to vibe — be flexible.
Communication Style
Skills are used by people across a wide range of technical familiarity. Pay attention to context cues:
- "evaluation" and "benchmark" are borderline but OK to use without explanation
- For "JSON", "assertion", "frontmatter" — look for cues the user knows these before using them without a brief definition
- When in doubt, briefly explain terms inline
- Match the user's register — if they're casual, be casual back
Step 1: Capture Intent
Start by understanding what the skill should enable. The conversation might already contain a workflow to capture (e.g., "turn this into a skill"). If so, extract answers from context first — tools used, sequence of steps, corrections made, input/output formats. The user fills gaps, then confirms before proceeding.
Questions to resolve:
- What should this skill enable Claude to do?
- When should this skill trigger? (what user phrases/contexts)
- What's the expected output format or behavior?
- Are there concrete examples of input/output?
What ships with it
3 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.
- 9d ago First seen · 230 lines · 113 tokens per session scan A 625c90ced6b7
hk-skill-creator is a skill published in the GitHub repository deepklarity/harness-kit (96 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 2,786 once invoked, about $0.0006 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
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
neuron-structured-output
Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property…
neuron-test-engineer
Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI…
neuron-agent-builder
Create and configure Neuron AI agents with providers, tools, instructions, and memory. Use this skill whenever the user mentions building agents, creating AI assistants, setting up LLM-powered chat bots, configuring chat agents, or wants to create an agent that can talk, use tools, or handle conversations. Also…
neuron-debugger
Debug and monitor Neuron AI applications with Inspector APM, event observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, Inspector, or needs to understand why an agent is behaving a certain way. Also trigger for…
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.