Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tomzx/agentsnpx agentmods add skills/tomzx/agents/create-skillWrote 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/tomzx/agents/create-skill)<a href="https://agentmods.dev/skills/tomzx/agents/create-skill"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-skill/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/tomzx/agents/create-skill"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-skill.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 | $0.00073 | $0.03288 |
| Opus 5.5 | $0.00029 | $0.01315 |
| Sonnet 5.5 | $0.00015 | $0.00658 |
| Haiku 4.5 | $0.00007 | $0.00329 |
Grade A, and why
create-skill 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 22d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d
Create Skill
Authors a new skill by first discovering existing skills that solve a similar problem, studying each one's strengths and weaknesses, then synthesizing the single best skill from what was learned.
The premise is that a skill written from scratch is usually weaker than one built by combining the best techniques already proven across several existing skills. This skill automates that synthesis.
Prerequisites
- Working directory is the root of the
tomzx/agentsrepository (the skill library root) $1: the name or concept of the skill to create (e.g.create-skill, or "a skill that summarizes meetings")- The Skills CLI available as
npx skillsfor searching and fetching candidates into a temp directory, never installed into this library (its global scope resolves to~/.agents/skills) - No skill with the chosen name already exists at
skills/$1/SKILL.md
How This Skill Relates to Others
| Skill | Relationship |
|---|---|
find-skills |
Delegated to for discovery. Its search logic (local library scan plus npx skills find) is the input to this skill. |
compare-skills |
Borrows the evaluation dimensions (instruction quality, structure, completeness, safety) for scoring candidates. |
improve-skill |
Shares the definition of "high-value, low-risk" and the hard constraint of confining edits to one skill directory. |
review-skills |
The new skill is checked against its duplicate detector at the end so the synthesis does not collide with an existing skill. |
What Counts as a Strong Synthesis
A good synthesis takes the strongest part from each candidate and combines them into one coherent skill, not a patchwork of copied sections.
| Quality | What to Look For |
|---|---|
| Best-of-breed sections | Take the clearest prerequisites, the most specific steps, the best output template, and the strongest examples, even if each comes from a different candidate |
| Conflict resolution | When candidates disagree, pick the approach that is clearer, more specific, and better aligned with the rest of the library, and record why |
| Structural coherence | One consistent voice, one section ordering, one frontmatter style, matching the house conventions of neighboring skills |
| Coverage | The union of edge cases and error handling from all candidates, deduplicated and pruned to what is realistic |
| Conventions | Repo style applied throughout: one sentence per line, no em-dashes, concise prose, correct frontmatter |
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.
- 22d ago Changed · +17 lines b8c86dae3b2d
- 25d ago Changed bcf65ce85a46
- 28d ago First seen · 293 lines · 73 tokens per session scan A 07847ad192be
create-skill is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 3,288 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 2026-10-01.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…