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 niki914/zafiro --skill skill-creatorgit clone --depth 1 https://github.com/niki914/zafiroWrote 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/niki914/zafiro/skill-creator)<a href="https://agentmods.dev/skills/niki914/zafiro/skill-creator"><img src="https://agentmods.dev/badge/skills/niki914/zafiro/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/niki914/zafiro/skill-creator"><img src="https://agentmods.dev/badge/skills/niki914/zafiro/skill-creator.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 | $0.00076 | $0.02508 |
| Opus 5.5 | $0.00030 | $0.01003 |
| Sonnet 5.5 | $0.00015 | $0.00502 |
| Haiku 4.5 | $0.00008 | $0.00251 |
Grade A, and why
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 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
A skill for creating new skills and iteratively improving them.
At a high level, the process of creating a skill goes like this:
- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill
- Create a few test prompts and run them with the skill in play
- Help the user evaluate the results both qualitatively and quantitatively
- Rewrite the skill based on feedback from the user's evaluation
- Repeat until you're satisfied
- Expand the test set and try again at larger scale
Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. Maybe they're like "I want to make a skill for X" — help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run the prompts, and repeat. Maybe they already have a draft — then go straight to the eval/iterate part of the loop. And if they say "I don't need to run a bunch of evaluations, just vibe with me", do that instead.
Where skills live here
- Skills live under
/data/data/com.niki914.zafiro/files/skills/. A skill is a directory<skills-root>/<id>/holding aSKILL.md; the id may be one or two levels deep (<repo>/<skill>). - If that path ever differs (debug build, fork), don't guess: the skills root is the parent of the
<dir>that the skills list shows for any skill, andload_skillreturns a skill's absolute dir. - Create and edit skills with python (or terminal): write the files directly under the skills root. There is no separate "skill tool" — this is a plain filesystem job.
- A skill is discovered through its frontmatter (
name,description) plus the SKILL.md body. Optionalscripts/,references/, andassets/sit next to it. - Skills are read once at the start of each turn. A skill you write now becomes available from the next turn — tell the user when to expect it.
- Seed skills that ship with the app are protected: never overwrite one, pick a different id.
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 · 188 lines · 76 tokens per session scan A 80ad47c44f84
skill-creator is a skill published in the GitHub repository niki914/zafiro (263 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 2,508 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
testing-expert
Ultimate Kotlin testing skill. Use this whenever writing, reviewing, or debugging ANY Kotlin test — unit, integration, property-based, or coroutine. Covers TDD (RED/GREEN/REFACTOR), Kotest + MockK + Kover, anti-pattern detection, and four-pillar quality framework. Triggers on: write a test, add coverage, why is this…
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
tool-abuse-detection
Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…