skill-creator

name

skill-creator

description

Create, modify, and iteratively improve OpenCode skills (SKILL.md files). Use whenever the user wants to create a new skill from scratch, edit or optimize an existing skill, write or redesign a SKILL.md, design skill test cases, or improve a skill's description for better triggering. Also use proactively when the user describes a workflow they want to capture as a reusable skill, or when they ask how to make a skill trigger more reliably — even if they don't explicitly say "skill".

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 OpenCode (with the skill available) on them
• Help the user evaluate the results both qualitatively and quantitatively
• Rewrite the skill based on feedback from the user's evaluation
• Repeat until you're satisfied

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.

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. Pay attention to context cues to understand how to phrase your communication. In the default case:

• "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 OpenCode 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 and tools — if useful for research (searching docs, finding similar skills, looking up best practices), research in parallel via task 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 (kebab-case, matches the directory name, e.g. data-analysis)
• 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: models have a tendency to "undertrigger" skills — to not use them when they'd be useful. To combat this, make the skill descriptions a little bit "pushy". So for instance, instead of "How to build a simple fast dashboard to display internal data.", you might write "How to build a simple fast dashboard to display internal 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)

A skill is discovered by OpenCode as a directory containing a SKILL.md. It can be installed globally (~/.config/opencode/skills/<name>/) or per-project (.opencode/skills/<name>/). The name in frontmatter must match the directory name.

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)

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 model reads only the relevant reference file.

Principle of Lack of Surprise

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:

## 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

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: "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 refine expectations 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": []
    }
  ]
}

---

Running and evaluating test cases

This section is one continuous sequence — don't stop partway through.

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.).

Step 1: Spawn all runs (with-skill AND baseline) in the same turn

For each test case, spawn two task 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):

• 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.

{
  "eval_id": 0,
  "eval_name": "descriptive-name-here",
  "prompt": "The user's task prompt",
  "assertions": []
}

Step 2: While runs are in progress, draft expectations

Don't just wait for the runs to finish — use this time productively. Draft what "good" looks like for each test case and explain it to the user. If expectations already exist in evals/evals.json, review them and explain what they check.

Good expectations are objectively verifiable and have descriptive names — they should read clearly 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 expectations once drafted. Also explain to the user what they'll review — both the qualitative outputs and the expectations you'll check.

Step 3: As runs complete, capture timing data

When each subagent task completes, you receive a notification containing token and duration info. 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.

Step 4: Grade, aggregate, and review with the user

Once all runs are done:

1. Grade each run — spawn a grader task subagent (or grade inline) that evaluates each expectation against the outputs. For expectations 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 a comparison — summarize pass/fail, time, and tokens for each configuration (with-skill vs baseline), with the delta. Put each with_skill version before its baseline counterpart. You can store this as a small benchmark.md in the iteration directory.

3. Do an analyst pass — read the benchmark data and surface patterns the aggregate stats might hide: expectations that always pass regardless of skill (non-discriminating), high-variance evals (possibly flaky), and time/token tradeoffs.

4. Review with the user — present the results directly in the conversation. For each test case, show the prompt and the output (or save output files to disk and tell the user where they are so they can inspect them). Ask for feedback inline: "How does this look? Anything you'd change?"

What the user reviews

Show one test case at a time:

• Prompt: the task that was given
• Output: the files the skill produced, rendered inline where possible or linked on disk
• Formal Grades (if grading was run): assertion pass/fail
• Feedback: ask the user to tell you what to change

---

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 many times 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. But if the skill 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, try branching out and using different metaphors, or recommending different patterns of working.

2. Keep the prompt lean. Remove things that aren't pulling their weight. If it looks like the skill is making the model waste a bunch of time doing things that are unproductive, try getting rid of the parts of the skill that are making it do that and see 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. 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 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.

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. 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.

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. Review with the user again
4. 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

---

Headless / remote environments

If there's no browser or display, skip any browser-based reviewer entirely. Instead, present results directly in the conversation: for each test case, show the prompt and the output, and save any files the user needs to inspect to the filesystem and tell them where they are. Ask for feedback inline. You can still organize results into iteration directories on the filesystem.

---

How skill triggering works

Understanding the triggering mechanism helps design better test cases. Skills appear in OpenCode's available-skills list with their name + description, and OpenCode decides whether to consult a skill based on that description. The important thing to know is that OpenCode only consults skills for tasks it can't easily handle on its own — simple, one-step queries may not trigger a skill even if the description matches perfectly, because the model can handle them directly with basic tools. Complex, multi-step, or specialized queries reliably trigger skills when the description matches.

This means your test prompts should be substantive enough that OpenCode 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.

---

Repeating one more time the core loop here for emphasis:

• Figure out what the skill is about
• Draft or edit the skill
• Run OpenCode (with the skill available) on test prompts
• With the user, evaluate the outputs
• Repeat until you and the user are satisfied

Please add steps to your TodoList, if you have such a thing, to make sure you don't forget. If you're in a headless environment, specifically put "Run test cases and review outputs with the user before revising the skill" in your TodoList to make sure it happens.

Good luck!