Borrowing it
Nothing to install: this file belongs to mazumba/opencode-dockerized. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mazumba/opencode-dockerized/main/.opencode/config/skills/skill-creator/SKILL.mdgit clone --depth 1 https://github.com/mazumba/opencode-dockerizedWrote 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/mazumba/opencode-dockerized/skill-creator)<a href="https://agentmods.dev/skills/mazumba/opencode-dockerized/skill-creator"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/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/mazumba/opencode-dockerized/skill-creator"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/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 | $0.00064 | $0.00681 |
| Opus 5.5 | $0.00026 | $0.00272 |
| Sonnet 5.5 | $0.00013 | $0.00136 |
| Haiku 4.5 | $0.00006 | $0.00068 |
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 13d 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill creator
Builds one skill folder: a lean SKILL.md plus disclosed files reached by pointers. writing-for-agents is the writing reference (pointers, information hierarchy, completion criteria, pruning); its SKILL-MECHANICS.md covers frontmatter, invocation and leading words. Load both before drafting.
Steps
- Capture intent. Pin down what the skill does, its trigger branches (the distinct situations and the words a user actually types), its exclusions, and its output. IF the request is vague ("a skill for APIs"): ask 1-2 targeted questions about domain, triggers and output before drafting. Done when every trigger branch and the output contract can be stated in one line each.
- Choose invocation and scope. Model-invoked or user-invoked, per
SKILL-MECHANICS.md. Project scope (.opencode/skills/) or this container's shared config (.opencode/config/skills/). Done when both are decided. - Research (conditional). IF the domain is unfamiliar: gather its precise terms and named failure modes via @librarian (external) or @explorer (project-specific). Done when you hold enough terms for the vocabulary payload and 5-10 named anti-patterns, each passing the practitioner test in
references/anatomy.md. - Draft
SKILL.md. Follow the section order and formats inreferences/anatomy.md. Use numbered steps for workflows, reference for knowledge domains, or both; keep only what every branch needs in the file. - Disclose. Move material that only some branches reach (pattern libraries, long examples, checklists, scripts, templates) into sibling files behind pointers that say when to read them. File layout, optional
GOTCHAS.md,config.jsonand memory files:references/layout.md. Done whenSKILL.mdis under 200 lines and every disclosed file has a pointer stating its read condition. - Validate. Check the draft against every entry in
references/watchlist.mdand fix each hit. Check frontmatter:nameis kebab-case, 1-64 chars, equal to the directory name;descriptionis 1024 chars or fewer. Done when the watchlist is clean. - Trial (conditional). IF subagents are available: run 3 prompts a real user would type (one casual, one imprecise, one formal). Done when each one triggers the skill and the output matches its output contract.
- Report. List the created paths and the final description, and tell the user to restart opencode so it loads the skill.
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.
- 13d ago First seen · 20 lines · 64 tokens per session scan A 38ab2558cb71
skill-creator is a skill published in the GitHub repository mazumba/opencode-dockerized (6 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 681 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 2026-10-13.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.