Creates, improves, and tests Agent Skills for any domain — engineering, content creation, research, personal productivity, and beyond.
Phase 1: Understand → Phase 2: Design → Phase 3: Write
Phase 4: Test → Phase 5: Improve → Phase 6: Optimize
Jump in at the right phase based on where the user is:
Cool? Cool.
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:
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.
This phase uses the Inversion pattern — ask first, build later. If the current conversation already contains a workflow the user wants to capture (e.g., "turn this into a skill"), extract answers from the conversation history first before asking.
Ask these questions one at a time, wait for each answer. DO NOT proceed to Phase 2 until all required questions are answered.
Q1 (Required): What should this skill enable Claude to do?
Q2 (Required): When should it trigger? What would a user say to invoke it?
Q3 (Required): Which content pattern fits best?
Read references/content-patterns.md and recommend 1-2 patterns with brief reasoning. Let the user confirm before continuing.
Q4: What's the expected output format?
Q5: Should we set up test cases? Skills with objectively verifiable outputs (file transforms, data extraction, fixed workflows) benefit from test cases. Skills with subjective outputs (writing style, art direction) often don't need them. Suggest the appropriate default, but let the user decide.
Gate: All required questions answered + content pattern confirmed → proceed to Phase 2.
After the 5 questions, proactively ask 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.
Before writing, read:
references/content-patterns.md — apply the confirmed pattern's structurereferences/design_principles.md — 5 principles to followreferences/patterns.md — implementation patterns (config.json, gotchas, script reuse, etc.)Decide:
scripts/ / references/ / assets/)config.json setup is needed (user needs to provide personal config)Gate: Design decisions clear → proceed to Phase 3.
Based on the interview and design decisions, write the SKILL.md.
references/constraints_and_rules.md)[What it does] + [When to use] + [Trigger phrases]. Under 1024 characters, no XML angle brackets. Make it slightly "pushy" to combat undertriggering — see references/constraints_and_rules.md for guidance.Before writing, read:
references/content-patterns.md — apply the confirmed pattern's structure to the SKILL.md bodyreferences/design_principles.md — 5 design principlesreferences/constraints_and_rules.md — technical constraints, naming conventionsreferences/quick_checklist.md handy for pre-publication verificationskill-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)
Skills use a three-level loading system:
These word counts are approximate and you can feel free to go longer if needed.
Key patterns:
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.
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.
Prefer using the imperative form in instructions.
Defining output formats - You can do it like this:
## 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):
## Commit message format
**Example 1:**
Input: Added user authentication with JWT tokens
Output: feat(auth): implement JWT-based authentication
Gotchas section - Every skill should have one. Add it as you discover real failures:
## Gotchas
- **[Problem]**: [What goes wrong] → [What to do instead]
config.json setup - If the skill needs user configuration, check for config.json at startup and use AskUserQuestion to collect missing values. See references/patterns.md for the standard flow.
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.
If you find yourself stacking ALWAYS/NEVER, stop and ask: can I explain the reasoning instead? A skill that explains why is more robust than one that just issues commands.
Gate: Draft complete, checklist reviewed → proceed to Phase 4.
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.
{
"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).
IMPORTANT: After writing the skill draft, check if this skill is part of a Claude Code plugin. If the skill path contains .claude-plugins/ or plugins/, automatically perform a plugin integration check.
Check plugin integration if:
.claude-plugins/ or plugins/
Detect Plugin Context
# Look for plugin.json in parent directories
SKILL_DIR="path/to/skill"
CURRENT_DIR=$(dirname "$SKILL_DIR")
while [ "$CURRENT_DIR" != "/" ]; do
if [ -f "$CURRENT_DIR/.claude-plugin/plugin.json" ]; then
echo "Found plugin at: $CURRENT_DIR"
break
fi
CURRENT_DIR=$(dirname "$CURRENT_DIR")
done
Check for Related Components
commands/ directory - are there commands that should use this skill?agents/ directory - are there agents that should reference this skill?Verify Three-Layer Architecture
The plugin should follow this pattern:
Command (Orchestration) → Agent (Execution) → Skill (Knowledge)
Command Layer should:
Agent Layer should:
Skill Layer should:
Generate Integration Report
If this skill is part of a plugin, generate a brief report:
## Plugin Integration Status
Plugin: {name} v{version}
Skill: {skill-name}
### Related Components
- Commands: {list or "none found"}
- Agents: {list or "none found"}
### Architecture Check
- [ ] Command orchestrates workflow
- [ ] Agent executes autonomously
- [ ] Skill documents knowledge
- [ ] Clear separation of concerns
### Recommendations
{specific suggestions if integration is incomplete}
Offer to Fix Integration Issues
If you find issues:
Offer to create/fix these components following the three-layer pattern.
# After creating skill at: plugins/my-plugin/skills/api-helper/
# 1. Detect plugin
Found plugin: my-plugin v1.0.0
# 2. Check for related components
Commands found:
- commands/api-call.md (references api-helper ✅)
Agents found:
- agents/api-executor.md (references api-helper ✅)
# 3. Verify architecture
✅ Command delegates to agent
✅ Agent references skill
✅ Skill documents API only
✅ Clear separation of concerns
Integration Score: 0.9 (Excellent)
For detailed architecture guidance, see:
PLUGIN_ARCHITECTURE.md in project roottldraw-helper/ARCHITECTURE.md for reference implementationtldraw-helper/commands/draw.md for example commandAfter integration check, proceed with test cases as normal.
This section is one continuous sequence — don't stop partway through. Do NOT use /skill-test or any other testing skill.
Put results in <skill-name>-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.
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: <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):
without_skill/outputs/.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.
{
"eval_id": 0,
"eval_name": "descriptive-name-here",
"prompt": "The user's task prompt",
"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.
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:
{
"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.
Once all runs are done:
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.
Aggregate into benchmark — run the aggregation script from the skill-creator directory:
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.
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.
Launch the viewer with both qualitative outputs and quantitative data:
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.
The "Outputs" tab shows one test case at a time:
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.
When the user tells you they're done, read feedback.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.
Kill the viewer server when you're done with it:
kill $VIEWER_PID 2>/dev/null
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.
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.
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.
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.
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.
After improving the skill:
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.--previous-workspace pointing at the previous iterationKeep going until:
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.
The description field in SKILL.md frontmatter is the primary mechanism that determines whether Claude invokes a skill. After creating or improving a skill, offer to optimize the description for better triggering accuracy.
Create 20 eval queries — a mix of should-trigger and should-not-trigger. Save as JSON:
[
{"query": "the user prompt", "should_trigger": true},
{"query": "another prompt", "should_trigger": false}
]
The queries must be realistic and something a Claude Code or Claude.ai user 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.
Present the eval set to the user for review using the HTML template:
assets/eval_review.html
__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/tmp/eval_review_<skill-name>.html) and open it: open /tmp/eval_review_<skill-name>.html
~/Downloads/eval_set.json — check the Downloads folder for the most recent version in case there are multiple (e.g., eval_set (1).json)This step matters — bad eval queries lead to bad descriptions.
Tell the user: "This will take some time — I'll run the optimization loop in the background and check on it periodically."
Save the eval set to the workspace, then run in the background:
python -m scripts.run_loop \
--eval-set <path-to-trigger-eval.json> \
--skill-path <path-to-skill> \
--model <model-id-powering-this-session> \
--max-iterations 5 \
--verbose
Use the model ID from your system prompt (the one powering the current session) so the triggering test matches what the user actually experiences.
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 with extended thinking 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.
Understanding the triggering mechanism helps design better eval queries. 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.
Take best_description from the JSON output and update the skill's SKILL.md frontmatter. Show the user before/after and report the scores.
Before packaging, run through references/quick_checklist.md to verify:
[What it does] + [When to use] + [Trigger phrases]
This checklist helps catch common issues before publication.
present_files tool is available)Check whether you have access to the present_files tool. If you don't, skip this step. If you do, package the skill and present the .skill file to the user:
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.
In Claude.ai, the core workflow is the same (draft → test → review → improve → repeat), but because Claude.ai doesn't have subagents, some mechanics change. Here's what to adapt:
Running test cases: No subagents means no parallel execution. For each test case, read the skill's SKILL.md, then follow its instructions to accomplish the test prompt yourself. Do them one at a time. This is less rigorous than independent subagents (you wrote the skill and you're also running it, so you have full context), but it's a useful sanity check — and the human review step compensates. Skip the baseline runs — just use the skill to complete the task as requested.
Reviewing results: If you can't open a browser (e.g., Claude.ai's VM has no display, or you're on a remote server), skip the browser reviewer entirely. Instead, present results directly in the conversation. For each test case, show the prompt and the output. If the output is a file the user needs to see (like a .docx or .xlsx), save it to the filesystem and tell them where it is so they can download and inspect it. Ask for feedback inline: "How does this look? Anything you'd change?"
Benchmarking: Skip the quantitative benchmarking — it relies on baseline comparisons which aren't meaningful without subagents. Focus on qualitative feedback from the user.
The iteration loop: Same as before — improve the skill, rerun the test cases, ask for feedback — just without the browser reviewer in the middle. You can still organize results into iteration directories on the filesystem if you have one.
Description optimization: This section requires the claude CLI tool (specifically claude -p) which is only available in Claude Code. Skip it if you're on Claude.ai.
Blind comparison: Requires subagents. Skip it.
Packaging: The package_skill.py script works anywhere with Python and a filesystem. On Claude.ai, you can run it and the user can download the resulting .skill file.
If you're in Cowork, the main things to know are:
--static <output_path> to write a standalone HTML file instead of starting a server. Then proffer a link that the user can click to open the HTML in their browser.generate_review.py (not writing your own boutique html code). Sorry in advance but I'm gonna go all caps here: GENERATE THE EVAL VIEWER BEFORE evaluating inputs yourself. You want to get them in front of the human ASAP!feedback.json as a file. You can then read it from there (you may have to request access first).package_skill.py just needs Python and a filesystem.run_loop.py / run_eval.py) should work in Cowork just fine since it uses claude -p via subprocess, not a browser, but please save it until you've fully finished making the skill and the user agrees it's in good shape.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 outputsagents/comparator.md — How to do blind A/B comparison between two outputsagents/analyzer.md — How to analyze why one version beat anotherThe references/ directory has additional documentation:
references/design_principles.md — Core design principles (Progressive Disclosure, Composability, Portability) and three common use case patterns (Document Creation, Workflow Automation, MCP Enhancement)references/constraints_and_rules.md — Technical constraints, naming conventions, security requirements, and quantitative success criteriareferences/quick_checklist.md — Comprehensive pre-publication checklist covering file structure, frontmatter, testing, and quality tiersreferences/schemas.md — JSON structures for evals.json, grading.json, etc.Repeating one more time the core loop here for emphasis:
eval-viewer/generate_review.py to help the user review themPlease add steps to your TodoList, if you have such a thing, to make sure you don't forget. If you're in Cowork, please specifically put "Create evals JSON and run eval-viewer/generate_review.py so human can review test cases" in your TodoList to make sure it happens.
Good luck!