skill-creator

Instructions for creating, changing, and checking Comis skills, which are Markdown files that teach an agent reusable workflows. They cover skill structure, metadata, design choices, and validation.

In plain words
What is it for?
Creating a skill from a workflow, improving an existing skill, checking its manifest, and choosing how much detail or flexibility its instructions should contain.
Why use it?
They help developers make skills that agents can discover and follow reliably without changing application code.

Skill for Claude CodeCodex

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/comisai/comis/skill-creator
Any agent
npx skills add comisai/comis --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/comisai/comis

Made for: Claude Code, Codex.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,213 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00082 $0.03213
Opus 5 $0.00041 $0.01606
Sonnet 5 $0.00016 $0.00643
Haiku 4.5 $0.00008 $0.00321

Measured 2d ago against content hash c94442f24983, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/init-skill.py, scripts/validate-skill.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/daemon/bundled-skills/skill-creator/SKILL.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creator

Create, validate, and iterate on Comis prompt skills.

How Skills Work

Skills are Markdown instruction files that extend what the agent can do. When a user sends a message, the agent scans available skill descriptions and, if one matches, reads its SKILL.md and follows the instructions step by step. Skills are the primary way to teach the agent new capabilities without changing code.

Skills are hot-reloaded -- save a file and it's available immediately, no restart needed.

Core Principles

The context window is a public good

Skills share the context window with the system prompt, conversation history, other skills' metadata, and the user's request. Challenge each piece of information: "Does the agent really need this?" and "Does this paragraph justify its token cost?" Default assumption: the agent is already very smart -- only add context it doesn't already have. Prefer concise examples over verbose explanations.

Set appropriate degrees of freedom

Match the level of specificity to the task's fragility:

  • High freedom (text-based instructions): Multiple approaches are valid, decisions depend on context. Like an open field -- many routes work.
  • Medium freedom (pseudocode or parameterized scripts): A preferred pattern exists but some variation is acceptable.
  • Low freedom (specific scripts, exact sequences): Operations are fragile, consistency is critical. Like a narrow bridge -- guardrails needed.

What NOT to include

A skill should only contain files that directly support its function. Do not create:

  • README.md, CHANGELOG.md, INSTALLATION_GUIDE.md, or any auxiliary documentation
  • User-facing docs about the process that went into creating the skill
  • Setup/testing procedures (those belong in the iteration loop, not the skill)

Private vs Shared Skills

Skills can live in two places. Default to private unless the user explicitly asks for a shared skill.

Private skills (default)

Created in the agent's own workspace under skills/.

Read the full file on GitHub · 326 lines

Files

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.

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. 2d ago First seen · 326 lines · 82 tokens per session scan A c94442f24983

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository comisai/comis (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 82 tokens to every session and 3,213 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

llmtornado-tutorial-generator

Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.

lofcz/LLMTornado · 31 tokens

org-sync

Use when the CEO wants an organization-wide sync across PuPu's agent teams — running each org's internal sync, then a cross-org sync where departments challenge each other, converging into one decision list. Triggers: "跑一次 org sync", "全局同步", "组织盘点", "/org-sync", "各部门现在什么情况", "有什么要我拍板的".

haoxiang-xu/PuPu · 82 tokens

release-feature-audit

Use when a new PuPu feature finishes implementation and needs its consistency audit before its ticket is marked done — "audit #123", "审计这个功能", "这个 feature 过一遍检查" — or when release-close-sprint roll-call finds a new feature that was never audited. Also covers standalone i18n checks ("漏翻了吗", "检查 i18n"), which used to be…

haoxiang-xu/PuPu · 94 tokens

gitnexus-impact-analysis

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?".

haoxiang-xu/PuPu · 50 tokens

growth-analyst

Use when analyzing PuPu's open-source growth or health for the founder — GitHub traffic, downloads/installs, releases, community, or contributor activity — or when producing a growth report or weekly COO report. Repo is haoxiang-xu/PuPu. Triggers: "how is PuPu growing?", "are people installing PuPu?", "which release…

haoxiang-xu/PuPu · 102 tokens

test-api

Use when running QA / regression tests against PuPu, when verifying a code change actually works in the running app, or when reading PuPu UI/state without screenshotting manually. Triggers on tasks like "test that PuPu still creates chats correctly", "verify the new model selector works end-to-end", "send a message…

haoxiang-xu/PuPu · 110 tokens