create-skill

create-skill is a skill for Claude Code, Codex from Open-Curiosity/gini-agent. It costs 30 tokens per session (1,868 once invoked), scanned A, original, MIT.

A skill for writing a new SKILL.md file or converting an older skill into Anthropic’s Agent Skills format. SKILL.md is the instruction file an agent uses to understand a skill.

In plain words
What is it for?
Use it when authoring a skill from a prompt or migrating a legacy instruction file, with optional scripts and environment requirements.
Why use it?
It helps ensure the resulting skill has the required structure, naming, description, and optional metadata.

Skill for Claude CodeCodex

About the project

Gini Agent is a personal AI-agent runtime that manages conversations, runs, tasks, approvals, memory, skills, jobs, tools, traces, audit events, and runtime health across its clients. It is for an agent that can remember, learn from task outcomes, and operate through desktop or mobile interfaces with user controls. Catalogue add-ons extend the runtime with skills and instructions.

Open-Curiosity/gini-agent · 1,869 stars · on GitHub

Install

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.

agentmods
npx agentmods add skills/open-curiosity/gini-agent/create-skill
Any agent
npx skills add Open-Curiosity/gini-agent --skill create-skill
Clone the repo
git clone --depth 1 https://github.com/Open-Curiosity/gini-agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for create-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-curiosity/gini-agent/create-skill.svg)](https://agentmods.dev/skills/open-curiosity/gini-agent/create-skill)
Your own site
<a href="https://agentmods.dev/skills/open-curiosity/gini-agent/create-skill"><img src="https://agentmods.dev/badge/skills/open-curiosity/gini-agent/create-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,868 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.01868
Opus 5 $0.00015 $0.00934
Sonnet 5 $0.00006 $0.00374
Haiku 4.5 $0.00003 $0.00187

Measured 5d ago against content hash ed43af22d80a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-skill scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`gh`, `jq`, or `curl`, record those under `prerequisites.commands` and
skills/meta/create-skill/SKILL.md · 188 lines

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.

Create Skill

You author new skills from a prompt and migrate legacy skills to the Anthropic Agent Skills specification. The goal is one spec-compliant SKILL.md plus optional scripts the agent can later run.

When To Use

  • User asks "create a skill for X" or "add a skill that does X".
  • User pastes a SKILL.md that is missing required fields or uses the legacy top-level fields (version, author, platforms, prerequisites, requires.connectors).
  • User asks "make this work" while looking at a non-spec SKILL.md.

Spec Reference

Required top-level frontmatter keys (Anthropic Agent Skills spec):

  • name — max 64 chars, lowercase + digits + hyphens, must equal the parent directory name.
  • description — max 1024 chars.

Optional spec keys:

  • license — free-form string.
  • compatibility — max 500 chars; human summary of environment needs.
  • metadata — arbitrary; Gini extensions live under metadata.gini.*.
  • allowed-tools — space-separated list of tool names the skill plans to invoke (advisory; recorded in audit trail).

Gini extensions (under metadata.gini):

  • version, author, platforms
  • prerequisites: { commands, env }
  • requires.credentials: [<credential-name>] — the credential names the skill needs, referenced by name (e.g. [LINEAR_API_KEY] for an api-key credential, [google-workspace-oauth] for the Google oauth2 credential). This is the current, preferred form.
  • requires.connectors: [{ provider, scopes? }] — still accepted for backward compatibility during the migration window; prefer requires.credentials.

Procedure

  1. Confirm the user's intent. If the request is "create a skill that posts to Slack", clarify whether the skill should also read messages, list channels, etc. — surface the cardinality so the design is right.

  2. Decide whether the skill needs a credential. Use requires.credentials only when the skill needs a configured account, credential, remote API, or connector-backed local integration. Each entry is a credential NAME — LINEAR_API_KEY for an api-key credential, google-workspace-oauth for the Google oauth2 credential. Check the configured credentials in GET /api/connectors to find the right name. If the skill only needs local commands such as git, gh, jq, or curl, record those under prerequisites.commands and set requires.credentials: []. If the skill truly needs a credential that hasn't been configured yet, name it the way the credential will be stored (the env-var name for an api-key) and tell the user to add it. Do not ask the user to pick between install/skip on unknown credentials — default to forward motion. (requires.connectors: [{ provider }] is still accepted for backward compatibility, but requires.credentials is preferred.)

Read the full file on GitHub · 188 lines

Changes

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.

  1. 5d ago First seen · 188 lines · 30 tokens per session scan A ed43af22d80a

Subscribe to this mod's changes

create-skill is a skill published in the GitHub repository Open-Curiosity/gini-agent (1,869 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,868 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

gno

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…

gmickel/gno · 86 tokens

vibelution-continuous-optimization-loop

Runs one evidence-driven Vibelution optimization iteration from the ROI backlog: pick one todo item, worktree isolate, implement, machine-verify, merge, update STATE. Use when the user starts /loop for project improvement, continuous optimization, or agent-dev ROI backlog work.

CCDawn/Vibelution · 65 tokens

personal-assistant

Use this skill whenever the user acts like Bamboo is their personal assistant. Triggers include stating commitments, deadlines, appointments, or recurring routines ("remind me to...", "I need to... by Friday", "every Monday I..."), asking to be reminded of something, agenda questions ("what's on my plate", "what's due…

bigduu/Bamboo-agent · 137 tokens

review

Review code changes, pull requests, patches, or a scoped code area for actionable correctness, security, compatibility, and test risks with file and line evidence. Use for review or audit requests; do not use for general proofreading, feature implementation, or debugging a reported failure when the user wants a fix.

bigduu/Bamboo-agent · 62 tokens

debug

Diagnose a concrete failure, regression, crash, hang, flaky test, or incorrect runtime behavior by reproducing it, testing hypotheses, and identifying the evidence-backed root cause. Use when symptoms or failing output exist; do not use for feature implementation without a failure, general code review, or a conceptual…

bigduu/Bamboo-agent · 64 tokens

plan

Build an executable implementation, migration, or rollout plan from read-only repository exploration, including constraints, dependencies, ordered changes, verification, risks, and rollback points. Use when the user asks for a plan or decomposition before implementation; do not use when they want a small change…

bigduu/Bamboo-agent · 68 tokens