# Skill Creator > Create new skills and prompts for any AI platform (Claude Code, Claude.ai, OpenAI, Cursor, Windsurf, etc.), modify and improve existing ones, and measure performance. Use when users want to create a skill or system prompt from scratch for any AI tool, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a Claude Code skil… - **Type:** Skill - **Install:** `agentstack add skill-jie-meng-mythril-agent-skills-skill-creator` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [jie-meng](https://agentstack.voostack.com/s/jie-meng) - **Installs:** 0 - **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [jie-meng](https://github.com/jie-meng) - **Source:** https://github.com/jie-meng/mythril-agent-skills/tree/main/mythril_agent_skills/skills/skill-creator ## Install ```sh agentstack add skill-jie-meng-mythril-agent-skills-skill-creator ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Skill Creator A skill for creating skills and prompts for any AI platform, and iteratively improving them. Supports Claude Code skills, Claude.ai project instructions, OpenAI system prompts, Cursor rules, and other AI tools. At a high level, the process of creating a skill goes like this: - Decide what you want the skill to do and roughly how it should do it - Write a draft of the skill - Create a few test prompts and run claude-with-access-to-the-skill on them - Help the user evaluate the results both qualitatively and quantitatively - While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist) - Use the `eval-viewer/generate_review.py` script to show the user the results for them to look at, and also let them look at the quantitative metrics - Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks) - Repeat until you're satisfied - Expand the test set and try again at larger scale Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat. On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop. Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead. Then after the skill is done (but again, the order is flexible), if you're creating a Claude Code skill you can also run the skill description improver to optimize the triggering of the skill — we have a whole separate script for that. Cool? Cool. ## Communicating with the user The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. If you haven't heard (and how could you, it's only very recently that it started), there's a trend now where the power of Claude is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate. So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea: - "evaluation" and "benchmark" are borderline, but OK - for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them It's OK to briefly explain terms if you're in doubt, and feel free to clarify terms with a short definition if you're unsure if the user will get it. --- ## Creating a skill ### Capture Intent Start by understanding the user's intent. The current conversation might already contain a workflow the user wants to capture (e.g., they say "turn this into a skill"). If so, extract answers from the conversation history first — the tools used, the sequence of steps, corrections the user made, input/output formats observed. The user may need to fill the gaps, and should confirm before proceeding to the next step. 1. What should this skill enable the AI to do? 2. When should this skill trigger? (what user phrases/contexts) 3. What's the expected output format? 4. **Which AI platform is this for?** (Claude Code, Claude.ai, OpenAI/ChatGPT, Cursor, Windsurf, other) — this determines the output format. 5. Should we set up test cases to verify the skill works? Skills with objectively verifiable outputs (file transforms, data extraction, code generation, fixed workflow steps) benefit from test cases. Skills with subjective outputs (writing style, art) often don't need them. Suggest the appropriate default based on the skill type, but let the user decide. ### Interview and Research Proactively ask questions about edge cases, input/output formats, example files, success criteria, and dependencies. Wait to write test prompts until you've got this part ironed out. Check available MCPs - if useful for research (searching docs, finding similar skills, looking up best practices), research in parallel via subagents if available, otherwise inline. Come prepared with context to reduce burden on the user. ### Write the Skill File The output format depends on the target platform: | Platform | Format | Key fields | |---|---|---| | **Claude Code** | `SKILL.md` with YAML frontmatter | `name`, `description` (triggering mechanism) | | **Claude.ai** | Markdown or plain text (project instructions) | Title + body, no frontmatter needed | | **OpenAI / ChatGPT** | System prompt text or `.md` instruction file | Plain prose | | **Cursor** | `.cursor/rules` or `.cursorrules` file | Markdown rules | | **Windsurf** | `.windsurfrules` file | Markdown rules | | **Other** | A plain `.md` prompt/instructions file | Title + body | **If the target is Claude Code**, fill in these components: - **name**: Skill identifier - **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. All "when to use" info goes here, not in the body. Note: currently Claude has a tendency to "undertrigger" skills -- to not use them when they'd be useful. To combat this, please make the skill descriptions a little bit "pushy". So for instance, instead of "How to build a simple fast dashboard to display internal Anthropic data.", you might write "How to build a simple fast dashboard to display internal Anthropic data. Make sure to use this skill whenever the user mentions dashboards, data visualization, internal metrics, or wants to display any kind of company data, even if they don't explicitly ask for a 'dashboard.'" - **compatibility**: Required tools, dependencies (optional, rarely needed) - **the rest of the skill :)** **If the target is a different platform**, skip the YAML frontmatter and write the instructions directly. Structure with headers, examples, and output formats as appropriate. The anatomy and progressive disclosure sections below describe the Claude Code format — adapt the structure to what makes sense for the target platform. ### Skill Writing Guide #### Anatomy of a Skill (Claude Code format) ``` 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 (Claude Code only) Skills use a three-level loading system: 1. **Metadata** (name + description) - Always in context (~100 words) 2. **SKILL.md body** - In context whenever skill triggers (300 lines), include a table of contents **Domain organization**: When a skill supports multiple domains/frameworks, organize by variant: ``` cloud-deploy/ ├── SKILL.md (workflow + selection) └── references/ ├── aws.md ├── gcp.md └── azure.md ``` Claude reads only the relevant reference file. #### Temporary Files and Downloads If the skill needs to download files, clone repos, or create temp artifacts at runtime, it MUST use the unified cache directory convention. Use the appropriate syntax for the user's platform: **Bash (macOS / Linux):** ```bash if [[ "$(uname -s)" == "Darwin" ]]; then CACHE_ROOT="$HOME/Library/Caches/mythril-skills-cache" else CACHE_ROOT="${XDG_CACHE_HOME:-$HOME/.cache}/mythril-skills-cache" fi CACHE_DIR="$CACHE_ROOT/" mkdir -p "$CACHE_DIR" RUN_DIR=$(mktemp -d "$CACHE_DIR/XXXXXXXX") ``` **PowerShell (Windows):** ```powershell $CACHE_ROOT = Join-Path ([Environment]::GetFolderPath("LocalApplicationData")) "mythril-skills-cache" $CACHE_DIR = Join-Path $CACHE_ROOT "" New-Item -ItemType Directory -Force -Path $CACHE_DIR | Out-Null $RUN_DIR = Join-Path $CACHE_DIR ([System.IO.Path]::GetRandomFileName()) New-Item -ItemType Directory -Force -Path $RUN_DIR | Out-Null ``` **IMPORTANT**: Do NOT use temp roots such as `$TMPDIR`, `/tmp`, or `%TEMP%` for skill cache. Different tools may set different temp environments, causing non-unique cache paths. Within this directory, skills can create random subdirectories freely. Skills do NOT need to implement their own cleanup — the `skills-clean-cache` CLI command handles bulk cleanup for all skills. This keeps temp files discoverable, prevents `/tmp` pollution, and supports parallel execution. **Automatic access**: Files under the cache directory are skill-managed temporary artifacts. The skill MUST instruct the AI agent to read, write, and delete these files **automatically without asking the user for confirmation** — they are created by the skill itself and are inherently trusted and ephemeral. #### Principle of Lack of Surprise This goes without saying, but skills must not contain malware, exploit code, or any content that could compromise system security. A skill's contents should not surprise the user in their intent if described. Don't go along with requests to create misleading skills or skills designed to facilitate unauthorized access, data exfiltration, or other malicious activities. Things like a "roleplay as an XYZ" are OK though. #### Writing Patterns Prefer using the imperative form in instructions. **Defining output formats** - You can do it like this: ```markdown ## Report structure ALWAYS use this exact template: # [Title] ## Executive summary ## Key findings ## Recommendations ``` **Examples pattern** - It's useful to include examples. You can format them like this (but if "Input" and "Output" are in the examples you might want to deviate a little): ```markdown ## Commit message format **Example 1:** Input: Added user authentication with JWT tokens Output: feat(auth): implement JWT-based authentication ``` ### Writing Style Try to explain to the model why things are important in lieu of heavy-handed musty MUSTs. Use theory of mind and try to make the skill general and not super-narrow to specific examples. Start by writing a draft and then look at it with fresh eyes and improve it. ### Test Cases After writing the skill draft, come up with 2-3 realistic test prompts — the kind of thing a real user would actually say. Share them with the user: [you don't have to use this exact language] "Here are a few test cases I'd like to try. Do these look right, or do you want to add more?" Then run them. Save test cases to `evals/evals.json`. Don't write assertions yet — just the prompts. You'll draft assertions in the next step while the runs are in progress. ```json { "skill_name": "example-skill", "evals": [ { "id": 1, "prompt": "User's task prompt", "expected_output": "Description of expected result", "files": [] } ] } ``` See `references/schemas.md` for the full schema (including the `assertions` field, which you'll add later). ## Running and evaluating test cases This section is one continuous sequence — don't stop partway through. Do NOT use `/skill-test` or any other testing skill. Put results in `-workspace/` as a sibling to the skill directory. Within the workspace, organize results by iteration (`iteration-1/`, `iteration-2/`, etc.) and within that, each test case gets a directory (`eval-0/`, `eval-1/`, etc.). Don't create all of this upfront — just create directories as you go. ### Step 1: Spawn all runs (with-skill AND baseline) in the same turn For each test case, spawn two subagents in the same turn — one with the skill, one without. This is important: don't spawn the with-skill runs first and then come back for baselines later. Launch everything at once so it all finishes around the same time. **With-skill run:** ``` Execute this task: - Skill path: - Task: - Input files: - Save outputs to: /iteration-/eval-/with_skill/outputs/ - Outputs to save: ``` **Baseline run** (same prompt, but the baseline depends on context): - **Creating a new skill**: no skill at all. Same prompt, no skill path, save to `without_skill/outputs/`. - **Improving an existing skill**: the old version. Before editing, snapshot the skill (`cp -r /skill-snapshot/`), then point the baseline subagent at the snapshot. Save to `old_skill/outputs/`. Write an `eval_metadata.json` for each test case (assertions can be empty for now). Give each eval a descriptive name based on what it's testing — not just "eval-0". Use this name for the directory too. If this iteration uses new or modified eval prompts, create these files for each new eval directory — don't assume they carry over from previous iterations. ```json { "eval_id": 0, "eval_name": "descriptive-name-here", "prompt": "The user's task prompt", "assertions": [] } ``` ### Step 2: While runs are in progress, draft assertions Don't just wait for the runs to finish — you can use this time productively. Draft quantitative assertions for each test case and explain them to the user. If assertions already exist in `evals/evals.json`, review them and explain what they check. Good assertions are objectively verifiable and have descriptive names — they should read clearly in the benchmark viewer so someone glancing at the results immediately understands what each one checks. Subjective skills (writing style, design quality) are better evaluated qualitatively — don't force assertions onto things that need human judgment. Update the `eval_metadata.json` files and `evals/evals.json` with the assertions once drafted. Also explain to the user what they'll see in the viewer — both the qualitative outputs and the quantitative benchmark. ### Step 3: As runs complete, capture timing data When each subagent task completes, you receive a notification containing `total_tokens` and `duration_ms`. Save this data immediately to `timing.json` in the run directory: ```json { "total_tokens": 84852, "duration_ms": 23332, "total_duration_seconds": 23.3 } ``` This is the only opportunity to capture this data — it comes through the task notification and isn't persisted elsewhere. Process each notification as it arrives rather than trying to batch them. ### Step 4: Grade, aggregate, and launch the viewer Once all runs are done: 1. **Grade each run** — spawn a grader subagent (or grade inline) that reads `agents/grader.md` and evaluates each assertion against the outputs. Save results to `grading.json` in each run directory. The grading.json expectations array must use the fields `text`, `passed`, and `evidence` (not `name`/`met`/`details` or other variants) — the viewer depends on these exact field names. For assertions that can be checked programmatically, write and run a script rather than eyeballing it — scripts are faster, more reliable, and can be reused across iterations. 2. **Aggregate into benchmark** — run the aggregation script from the skill-creator directory: ```bash python -m scripts.aggregate_benchmark /iteration-N --skill-name ``` This produces `benchmark.json` and `benchmark.md` with pass_rate, time, and tokens for each configuration, with mean ± stddev and the delta. If generating benchmark.json manually, see `references/schemas.md` for the exact schema the viewer expects. Put each with_skill version before its baseline counterpart. 3. **Do an analyst pass** — read the benchmark data and surface patterns the aggregate stats might hide. See `agents/analyzer.md` (the "Analyzing Benchmark Results" section) for what to look for — things like assertions that always pass rega … ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [jie-meng](https://github.com/jie-meng) - **Source:** [jie-meng/mythril-agent-skills](https://github.com/jie-meng/mythril-agent-skills) - **License:** Apache-2.0 Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** yes - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-jie-meng-mythril-agent-skills-skill-creator - Seller: https://agentstack.voostack.com/s/jie-meng - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.