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 agentmods add skills/cxcscmu/skilllearnbench/skill-creatornpx skills add cxcscmu/SkillLearnBench --skill skill-creatorgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWhat 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 | $0.00073 | $0.01004 |
| Opus 5 | $0.00036 | $0.00502 |
| Sonnet 5 | $0.00015 | $0.00201 |
| Haiku 4.5 | $0.00007 | $0.00100 |
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.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
A guide for creating well-structured, reusable Claude Code skills.
Communicating with the user
Pay attention to context cues to gauge familiarity. Keep explanations accessible — don't assume deep technical knowledge unless the user demonstrates it.
Creating a skill
Capture Intent
Understand what the skill should enable. Extract from the current task context:
- What should this skill enable Claude to do?
- When should this skill trigger? (what user phrases / contexts)
- What's the expected output format or artifact?
Interview and Research
Proactively think about edge cases, input/output formats, success criteria, and dependencies before writing. If useful libraries or APIs are involved, check what's available in the environment first.
Write the SKILL.md
Based on the task requirements, fill in these components:
- name: Skill identifier (must match the folder name)
- description: When to trigger, what it does. This is the primary triggering mechanism — include both what the skill does AND specific contexts for when to use it. To combat undertriggering, make the description a little "pushy": instead of "How to do X", write "How to do X. Use this skill whenever the user mentions X, Y, or Z, even if they don't explicitly ask for it."
- the rest of the skill body
Skill Writing Guide
Anatomy of a Skill
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter (name, description required)
│ └── Markdown instructions
└── Bundled Resources (optional)
├── scripts/ - Executable code for deterministic/repetitive tasks
├── references/ - Docs loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts)
Progressive Disclosure
Skills use a three-level loading system:
- Metadata (name + description) — Always in context (~100 words)
- SKILL.md body — In context whenever skill triggers (<500 lines ideal)
- Bundled resources — Loaded on demand (unlimited size)
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.
- 2d ago First seen · 126 lines · 73 tokens per session scan A 3a842ee18c01
skill-creator is a skill published in the GitHub repository cxcscmu/SkillLearnBench (82 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,004 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 2026-08-30.
Other skills, from other repositories
creating-skills
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.
Context Doctor
Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.
image-generation
Generate images from text prompts (and optionally edit/remix input images). Use when the user asks to create, generate, draw, render, or edit an image, illustration, logo, icon, diagram, or photo.
adding-models
Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior. Covers runtime catalog sources, CI test matrices, and handle validation.
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
writing-bench-task-judge
Use when writing or modifying checkgoals() / getanswer() / App check methods in benchenv/task/, or when reviewing a draft task's judge correctness. Triggers include adding a new task, editing a judge method, or diagnosing a judge false-positive/negative.