X Anthropics Skill Creator 80032f6

---
name: x-anthropics-skill-creator-80032f6
description: Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
---

### 导出副本边界与技能别名

迁移、安装、修复和经验回写只作用于当前加载的目标宿主技能副本。原 Codex 技能/MCP、下载的源码和 `original-skills` 均为来源材料，不因执行本副本而写入；只有用户另行明确要求配置 Codex 产品本身时，才按该产品流程处理指定目标。脚本需要安装目录或状态目录时，显式提供目标路径；不得从 `CODEX_HOME` 隐式推断写入位置。

跨技能名称可能沿用源库别名。先查 [技能别名表](../../skill-aliases.json)，优先选择同来源、同插件的条目，再使用其 `id` 调用或读取对应入口；不得假定旧 `$skill`、`superpowers:skill` 名称在新宿主直接注册。不能确定目标时先核对，不替换真实产品命令或 Shell 环境变量。

## 跨宿主使用约定

本副本供支持 Agent Skills 的客户端使用。先检查当前宿主实际提供的工具、权限和已连接服务，再执行正文工作流。原文中的宿主工具标识是能力参考；只有实际发现该工具时才可调用，其他宿主应使用经核验的等价 MCP、CLI 或 API。没有等价能力的步骤必须报告不可用，不能虚构调用或完成状态。

技能资源以本技能目录为基准；输出写入当前项目中用户指定的位置。通过技能名称或自然语言触发，具体快捷命令由宿主决定。涉及真实产品、模型 API、协议字段和官方网址的名称保持原意。授权、审批、隐私和工具范围限制在迁移后仍然有效；不得为兼容而扩大权限。具体依赖与迁移说明见同目录 `PORTABILITY.md`。

# Skill Creator

A skill for creating new skills and iteratively improving them.

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 an isolated agent 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), you can also run the skill description improver, which we have a whole separate script for, to optimize the triggering of the skill.

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 target assistant to do?
2. When should this skill trigger? (what user phrases/contexts)
3. What's the expected output format?
4. 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.md

Based on the user interview, 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 :)**

### 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:
1. **Metadata** (name + description) - Always in context (~100 words)
2. **SKILL.md body** - In context whenever skill triggers (<500 lines ideal)
3. **Bundled resources** - As needed (unlimited, scripts can execute without loading)

These word counts are approximate and you can feel free to go longer if needed.

**Key patterns:**
- Keep SKILL.md under 500 lines; if you're approaching this limit, add an additional layer of hierarchy along with clear pointers about where the model using the skill should go next to follow up.
- Reference files clearly from SKILL.md with guidance on when to read them
- For large reference files (>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
```
The executing assistant reads only the relevant reference file.

#### 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 a user-approved writable workspace, conventionally `<skill-name>-workspace/`. Use a sibling of the skill directory only when that location is writable and authorized. 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

Discover whether the current host provides isolated subagents or a documented CLI/API runner. When available, launch two isolated runs for each test case — 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 paired runs concurrently within the host's limits when possible, or use sequential isolated sessions. Without an isolated runner, use the limited-capability workflow below and do not claim an independent baseline comparison.

**With-skill run:**

```
Execute this task:
- Skill path: <path-to-skill>
- Task: <eval prompt>
- Input files: <eval files if any, or "none">
- Save outputs to: <workspace>/iteration-<N>/eval-<ID>/with_skill/outputs/
- Outputs to save: <what the user cares about — e.g., "the .docx file", "the final CSV">
```

**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-path> <workspace>/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

Inspect actual run results for token usage and elapsed time. Save available measurements to `timing.json`; absent telemetry is unavailable, not zero. The following values illustrate the schema, not guaranteed host fields:

```json
{
  "total_tokens": 84852,
  "duration_ms": 23332,
  "total_duration_seconds": 23.3
}
```

Capture ephemeral telemetry when emitted and retain logs where supported. Missing metrics must be reported and omitted from efficiency comparisons. Check the benchmark script's numeric inputs before aggregating incomplete telemetry.

### 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 <workspace>/iteration-N --skill-name <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 regardless of skill (non-discriminating), high-variance evals (possibly flaky), and time/token tradeoffs.

4. **Launch the viewer** with both qualitative outputs and quantitative data. This is a POSIX-shell example; use the actual host's process launcher with equivalent arguments and track its process handle. Without background-process/browser support, use the static-file variant:
   ```bash
   nohup python <skill-creator-path>/eval-viewer/generate_review.py \
     <workspace>/iteration-N \
     --skill-name "my-skill" \
     --benchmark <workspace>/iteration-N/benchmark.json \
     > /dev/null 2>&1 &
   VIEWER_PID=$!
   ```
   For iteration 2+, also pass `--previous-workspace <workspace>/iteration-<N-1>`.

   **Cowork / headless environments:** If `webbrowser.open()` is not available or the environment has no display, use `--static <output_path>` to write a standalone HTML file instead of starting a server. Feedback will be downloaded as a `feedback.json` file when the user clicks "Submit All Reviews". After download, copy `feedback.json` into the workspace directory for the next iteration to pick up.

Note: please use generate_review.py to create the viewer; there's no need to write custom HTML.

5. **Tell the user** something like: "I've opened the results in your browser. There are two tabs — 'Outputs' lets you click through each test case and leave feedback, 'Benchmark' shows the quantitative comparison. When you're done, come back here and let me know."

### What the user sees in the viewer

The "Outputs" tab shows one test case at a time:
- **Prompt**: the task that was given
- **Output**: the files the skill produced, rendered inline where possible
- **Previous Output** (iteration 2+): collapsed section showing last iteration's output
- **Formal Grades** (if grading was run): collapsed section showing assertion pass/fail
- **Feedback**: a textbox that auto-saves as they type
- **Previous Feedback** (iteration 2+): their comments from last time, shown below the textbox

The "Benchmark" tab shows the stats summary: pass rates, timing, and token usage for each configuration, with per-eval breakdowns and analyst observations.

Navigation is via prev/next buttons or arrow keys. When done, they click "Submit All Reviews" which saves all feedback to `feedback.json`.

### Step 5: Read the feedback

When the user tells you they're done, read `feedback.json`:

```json
{
  "reviews": [
    {"run_id": "eval-0-with_skill", "feedback": "the chart is missing axis labels", "timestamp": "..."},
    {"run_id": "eval-1-with_skill", "feedback": "", "timestamp": "..."},
    {"run_id": "eval-2-with_skill", "feedback": "perfect, love this", "timestamp": "..."}
  ],
  "status": "complete"
}
```

Empty feedback means the user thought it was fine. Focus your improvements on the test cases where the user had specific complaints.

Stop only the viewer process you launched using its recorded handle. POSIX example:

```bash
kill $VIEWER_PID 2>/dev/null
```

---

## Improving the skill

This is the heart of the loop. You've run the test cases, the user has reviewed the results, and now you need to make the skill better based on their feedback.

### How to think about improvements

1. **Generalize from the feedback.** The big picture thing that's happening here is that we're trying to create skills that can be used a million times (maybe literally, maybe even more who knows) across many different prompts. Here you and the user are iterating on only a few examples over and over again because it helps move faster. The user knows these examples in and out and it's quick for them to assess new outputs. But if the skill you and the user are codeveloping works only for those examples, it's useless. Rather than put in fiddly overfitty changes, or oppressively constrictive MUSTs, if there's some stubborn issue, you might try branching out and using different metaphors, or recommending different patterns of working. It's relatively cheap to try and maybe you'll land on something great.

2. **Keep the prompt lean.** Remove things that aren't pulling their weight. Make sure to read the transcripts, not just the final outputs — if it looks like the skill is making the model waste a bunch of time doing things that are unproductive, you can try getting rid of the parts of the skill that are making it do that and seeing what happens.

3. **Explain the why.** Try hard to explain the **why** behind everything you're asking the model to do. Today's LLMs are *smart*. They have good theory of mind and when given a good harness can go beyond rote instructions and really make things happen. Even if the feedback from the user is terse or frustrated, try to actually understand the task and why the user is writing what they wrote, and what they actually wrote, and then transmit this understanding into the instructions. If you find yourself writing ALWAYS or NEVER in all caps, or using super rigid structures, that's a yellow flag — if possible, reframe and explain the reasoning so that the model understands why the thing you're asking for is important. That's a more humane, powerful, and effective approach.

4. **Look for repeated work across test cases.** Read the transcripts from the test runs and notice if the subagents all independently wrote similar helper scripts or took the same multi-step approach to something. If all 3 test cases resulted in the subagent writing a `create_docx.py` or a `build_chart.py`, that's a strong signal the skill should bundle that script. Write it once, put it in `scripts/`, and tell the skill to use it. This saves every future invocation from reinventing the wheel.

This task is pretty important (we are trying to create billions a year in economic value here!) and your thinking time is not the blocker; take your time and really mull things over. I'd suggest writing a draft revision and then looking at it anew and making improvements. Really do your best to get into the head of the user and understand what they want and need.

### The iteration loop

After improving the skill:

1. Apply your improvements to the skill
2. Rerun all test cases into a new `iteration-<N+1>/` directory, including baseline runs. If you're creating a new skill, the baseline is always `without_skill` (no skill) — that stays the same across iterations. If you're improving an existing skill, use your judgment on what makes sense as the baseline: the original version the user came in with, or the previous iteration.
3. Launch the reviewer with `--previous-workspace` pointing at the previous iteration
4. Wait for the user to review and tell you they're done
5. Read the new feedback, improve again, repeat

Keep going until:
- The user says they're happy
- The feedback is all empty (everything looks good)
- You're not making meaningful progress

---

## Advanced: Blind comparison

For situations where you want a more rigorous comparison between two versions of a skill (e.g., the user asks "is the new version actually better?"), there's a blind comparison system. Read `agents/comparator.md` and `agents/analyzer.md` for the details. The basic idea is: give two outputs to an independent agent without telling it which is which, and let it judge quality. Then analyze why the winner won.

This is optional, requires subagents, and most users won't need it. The human review loop is usually sufficient.

---

## Description Optimization

The description field in SKILL.md frontmatter is the primary mechanism that helps the target host decide whether to invoke a skill. After creating or improving a skill, offer to optimize the description for better triggering accuracy.

### Step 1: Generate trigger eval queries

Create 20 eval queries — a mix of should-trigger and should-not-trigger. Save as JSON:

```json
[
  {"query": "the user prompt", "should_trigger": true},
  {"query": "another prompt", "should_trigger": false}
]
```

The queries must be realistic and something a user of the target host would actually type. Not abstract requests, but requests that are concrete and specific and have a good amount of detail. For instance, file paths, personal context about the user's job or situation, column names and values, company names, URLs. A little bit of backstory. Some might be in lowercase or contain abbreviations or typos or casual speech. Use a mix of different lengths, and focus on edge cases rather than making them clear-cut (the user will get a chance to sign off on them).

Bad: `"Format this data"`, `"Extract text from PDF"`, `"Create a chart"`

Good: `"ok so my boss just sent me this xlsx file (its in my downloads, called something like 'Q4 sales final FINAL v2.xlsx') and she wants me to add a column that shows the profit margin as a percentage. The revenue is in column C and costs are in column D i think"`

For the **should-trigger** queries (8-10), think about coverage. You want different phrasings of the same intent — some formal, some casual. Include cases where the user doesn't explicitly name the skill or file type but clearly needs it. Throw in some uncommon use cases and cases where this skill competes with another but should win.

For the **should-not-trigger** queries (8-10), the most valuable ones are the near-misses — queries that share keywords or concepts with the skill but actually need something different. Think adjacent domains, ambiguous phrasing where a naive keyword match would trigger but shouldn't, and cases where the query touches on something the skill does but in a context where another tool is more appropriate.

The key thing to avoid: don't make should-not-trigger queries obviously irrelevant. "Write a fibonacci function" as a negative test for a PDF skill is too easy — it doesn't test anything. The negative cases should be genuinely tricky.

### Step 2: Review with user

Present the eval set to the user for review using the HTML template:

1. Read the template from `assets/eval_review.html`
2. Replace the placeholders:
   - `__EVAL_DATA_PLACEHOLDER__` → the JSON array of eval items (no quotes around it — it's a JS variable assignment)
   - `__SKILL_NAME_PLACEHOLDER__` → the skill's name
   - `__SKILL_DESCRIPTION_PLACEHOLDER__` → the skill's current description
3. Write `eval_review_<skill-name>.html` under the writable workspace or resolved OS temporary directory. Open it using an available file/browser tool or return its real file link; do not assume macOS `open`.
4. The user can edit queries, toggle should-trigger, add/remove entries, then click "Export Eval Set"
5. Locate the actual exported `eval_set.json` through the browser's reported download location or the user-supplied file. Do not assume a Downloads directory; resolve duplicates by the actual export timestamp.

This step matters — bad eval queries lead to bad descriptions.

### Step 3: Run the optimization loop

Tell the user: "This will take some time — I'll run the optimization loop in the background and check on it periodically."

The bundled description-optimization scripts specifically invoke `claude -p`, parse its output, and create temporary `.claude/commands` entries. Verify that CLI, authentication, supported model, and writable authorized test project first. Running them from another assistant host still measures Claude triggering, not that host. For another host use its verified runner and explicitly adapt the evaluator; renaming a binary does not make schemas equivalent. If unavailable, report automatic description optimization as blocked and continue manual drafting/review.

For the verified Claude backend, save the eval set to the workspace, then run in the background:

```bash
python -m scripts.run_loop \
  --eval-set <path-to-trigger-eval.json> \
  --skill-path <path-to-skill> \
  --model <verified-claude-model-id> \
  --max-iterations 5 \
  --verbose
```

Use a model ID accepted by the selected backend and record it with results. Do not pass the current assistant's model ID to another provider merely because it appears in this session.

While it runs, periodically tail the output to give the user updates on which iteration it's on and what the scores look like.

This handles the full optimization loop automatically. It splits the eval set into 60% train and 40% held-out test, evaluates the current description (running each query 3 times to get a reliable trigger rate), then calls Claude to propose improvements based on what failed. It re-evaluates each new description on both train and test, iterating up to 5 times. When it's done, it opens an HTML report in the browser showing the results per iteration and returns JSON with `best_description` — selected by test score rather than train score to avoid overfitting.

### How skill triggering works

For the bundled Claude evaluator, the original triggering model is described below; verify current behavior and do not assume another host shares it. Skills appear in Claude's `available_skills` list with their name + description, and Claude decides whether to consult a skill based on that description. The important thing to know is that Claude only consults skills for tasks it can't easily handle on its own — simple, one-step queries like "read this PDF" may not trigger a skill even if the description matches perfectly, because Claude can handle them directly with basic tools. Complex, multi-step, or specialized queries reliably trigger skills when the description matches.

This means your eval queries should be substantive enough that Claude would actually benefit from consulting a skill. Simple queries like "read file X" are poor test cases — they won't trigger skills regardless of description quality.

### Step 4: Apply the result

Take `best_description` from the JSON output and update the skill's SKILL.md frontmatter. Show the user before/after and report the scores.

---

### Package and Present

When Python and writable storage are available, package the skill. Present the actual artifact with the current host's file-delivery capability (`present_files` only if exposed), or provide its real file path. Report specific packaging/delivery limitations:

```bash
python -m scripts.package_skill <path/to/skill-folder>
```

After packaging, direct the user to the resulting `.skill` file path so they can install it.

---

## Adapt to verified runtime capabilities

Choose these branches from actual capabilities, not product-name assumptions:

- **No isolated runner:** run sequential self-checks, show prompt and output, and skip independent baseline benchmarks and blind comparison.
- **No browser/display:** use `generate_review.py --static <output_path>` when HTML delivery is available; otherwise present outputs and collect feedback in the conversation. Creating a file is not proof it was opened.
- **No token/timing telemetry:** retain output grading and report unavailable efficiency metrics.
- **No authenticated Claude CLI:** skip the bundled description optimizer unless a tested backend adapter exists. The core draft → test → review → improve loop remains available.
- **Read-only installed skill:** preserve its original name, copy to an authorized writable workspace or resolved OS temporary directory, edit/package the copy, then deliver to the chosen output location.
- **Limited subagent capacity:** schedule paired runs within the limit or use sequential isolated sessions.
- **User review:** generate the bundled viewer before revising based only on your own judgment whenever the runtime can produce and deliver it.

The original Claude.ai and Cowork variants illustrate these capability combinations; their names are not guarantees about the current host.

---

## Reference files

The agents/ directory contains instructions for specialized subagents. Read them when you need to spawn the relevant subagent.

- `agents/grader.md` — How to evaluate assertions against outputs
- `agents/comparator.md` — How to do blind A/B comparison between two outputs
- `agents/analyzer.md` — How to analyze why one version beat another

The references/ directory has additional documentation:
- `references/schemas.md` — JSON structures for evals.json, grading.json, etc.

---

Repeating one more time the core loop here for emphasis:

- Figure out what the skill is about
- Draft or edit the skill
- Run an isolated agent with access to the skill on test prompts
- With the user, evaluate the outputs:
  - Create benchmark.json and run `eval-viewer/generate_review.py` to help the user review them
  - Run quantitative evals
- Repeat until you and the user are satisfied
- Package the final skill and return it to the user.

Please add steps to your TodoList, if you have such a thing, to make sure you don't forget. When using an available task-list tool, include "Create evals JSON and run `eval-viewer/generate_review.py` so human can review test cases".

Good luck!