@fakhrulraharjo/opencode-skill-creator 0.3.0

package/dist/skill/references/schemas.md

@@ -0,0 +1,430 @@
+# JSON Schemas
+
+This document defines the JSON schemas used by skill-creator.
+
+---
+
+## evals.json
+
+Defines the evals for a skill. Located at `evals/evals.json` within the skill directory.
+
+```json
+{
+  "skill_name": "example-skill",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "User's example prompt",
+      "expected_output": "Description of expected result",
+      "files": ["evals/files/sample1.pdf"],
+      "expectations": [
+        "The output includes X",
+        "The skill used script Y"
+      ]
+    }
+  ]
+}
+```
+
+**Fields:**
+- `skill_name`: Name matching the skill's frontmatter
+- `evals[].id`: Unique integer identifier
+- `evals[].prompt`: The task to execute
+- `evals[].expected_output`: Human-readable description of success
+- `evals[].files`: Optional list of input file paths (relative to skill root)
+- `evals[].expectations`: List of verifiable statements
+
+---
+
+## history.json
+
+Tracks version progression in Improve mode. Located at workspace root.
+
+```json
+{
+  "started_at": "2026-01-15T10:30:00Z",
+  "skill_name": "pdf",
+  "current_best": "v2",
+  "iterations": [
+    {
+      "version": "v0",
+      "parent": null,
+      "expectation_pass_rate": 0.65,
+      "grading_result": "baseline",
+      "is_current_best": false
+    },
+    {
+      "version": "v1",
+      "parent": "v0",
+      "expectation_pass_rate": 0.75,
+      "grading_result": "won",
+      "is_current_best": false
+    },
+    {
+      "version": "v2",
+      "parent": "v1",
+      "expectation_pass_rate": 0.85,
+      "grading_result": "won",
+      "is_current_best": true
+    }
+  ]
+}
+```
+
+**Fields:**
+- `started_at`: ISO timestamp of when improvement started
+- `skill_name`: Name of the skill being improved
+- `current_best`: Version identifier of the best performer
+- `iterations[].version`: Version identifier (v0, v1, ...)
+- `iterations[].parent`: Parent version this was derived from
+- `iterations[].expectation_pass_rate`: Pass rate from grading
+- `iterations[].grading_result`: "baseline", "won", "lost", or "tie"
+- `iterations[].is_current_best`: Whether this is the current best version
+
+---
+
+## grading.json
+
+Output from the grader agent. Located at `<run-dir>/grading.json`.
+
+```json
+{
+  "expectations": [
+    {
+      "text": "The output includes the name 'John Smith'",
+      "passed": true,
+      "evidence": "Found in transcript Step 3: 'Extracted names: John Smith, Sarah Johnson'"
+    },
+    {
+      "text": "The spreadsheet has a SUM formula in cell B10",
+      "passed": false,
+      "evidence": "No spreadsheet was created. The output was a text file."
+    }
+  ],
+  "summary": {
+    "passed": 2,
+    "failed": 1,
+    "total": 3,
+    "pass_rate": 0.67
+  },
+  "execution_metrics": {
+    "tool_calls": {
+      "Read": 5,
+      "Write": 2,
+      "Bash": 8
+    },
+    "total_tool_calls": 15,
+    "total_steps": 6,
+    "errors_encountered": 0,
+    "output_chars": 12450,
+    "transcript_chars": 3200
+  },
+  "timing": {
+    "executor_duration_seconds": 165.0,
+    "grader_duration_seconds": 26.0,
+    "total_duration_seconds": 191.0
+  },
+  "claims": [
+    {
+      "claim": "The form has 12 fillable fields",
+      "type": "factual",
+      "verified": true,
+      "evidence": "Counted 12 fields in field_info.json"
+    }
+  ],
+  "user_notes_summary": {
+    "uncertainties": ["Used 2023 data, may be stale"],
+    "needs_review": [],
+    "workarounds": ["Fell back to text overlay for non-fillable fields"]
+  },
+  "eval_feedback": {
+    "suggestions": [
+      {
+        "assertion": "The output includes the name 'John Smith'",
+        "reason": "A hallucinated document that mentions the name would also pass"
+      }
+    ],
+    "overall": "Assertions check presence but not correctness."
+  }
+}
+```
+
+**Fields:**
+- `expectations[]`: Graded expectations with evidence
+- `summary`: Aggregate pass/fail counts
+- `execution_metrics`: Tool usage and output size (from executor's metrics.json)
+- `timing`: Wall clock timing (from timing.json)
+- `claims`: Extracted and verified claims from the output
+- `user_notes_summary`: Issues flagged by the executor
+- `eval_feedback`: (optional) Improvement suggestions for the evals, only present when the grader identifies issues worth raising
+
+---
+
+## metrics.json
+
+Output from the executor agent. Located at `<run-dir>/outputs/metrics.json`.
+
+```json
+{
+  "tool_calls": {
+    "Read": 5,
+    "Write": 2,
+    "Bash": 8,
+    "Edit": 1,
+    "Glob": 2,
+    "Grep": 0
+  },
+  "total_tool_calls": 18,
+  "total_steps": 6,
+  "files_created": ["filled_form.pdf", "field_values.json"],
+  "errors_encountered": 0,
+  "output_chars": 12450,
+  "transcript_chars": 3200
+}
+```
+
+**Fields:**
+- `tool_calls`: Count per tool type
+- `total_tool_calls`: Sum of all tool calls
+- `total_steps`: Number of major execution steps
+- `files_created`: List of output files created
+- `errors_encountered`: Number of errors during execution
+- `output_chars`: Total character count of output files
+- `transcript_chars`: Character count of transcript
+
+---
+
+## timing.json
+
+Wall clock timing for a run. Located at `<run-dir>/timing.json`.
+
+**How to capture:** When a subagent task completes, the task notification includes `total_tokens` and `duration_ms`. Save these immediately — they are not persisted anywhere else and cannot be recovered after the fact.
+
+```json
+{
+  "total_tokens": 84852,
+  "duration_ms": 23332,
+  "total_duration_seconds": 23.3,
+  "executor_start": "2026-01-15T10:30:00Z",
+  "executor_end": "2026-01-15T10:32:45Z",
+  "executor_duration_seconds": 165.0,
+  "grader_start": "2026-01-15T10:32:46Z",
+  "grader_end": "2026-01-15T10:33:12Z",
+  "grader_duration_seconds": 26.0
+}
+```
+
+---
+
+## benchmark.json
+
+Output from Benchmark mode. Located at `benchmarks/<timestamp>/benchmark.json`.
+
+```json
+{
+  "metadata": {
+    "skill_name": "pdf",
+    "skill_path": "/path/to/pdf",
+    "executor_model": "<provider/model-id>",
+    "analyzer_model": "<provider/model-id>",
+    "timestamp": "2026-01-15T10:30:00Z",
+    "evals_run": [1, 2, 3],
+    "runs_per_configuration": 3
+  },
+
+  "runs": [
+    {
+      "eval_id": 1,
+      "eval_name": "Ocean",
+      "configuration": "with_skill",
+      "run_number": 1,
+      "result": {
+        "pass_rate": 0.85,
+        "passed": 6,
+        "failed": 1,
+        "total": 7,
+        "time_seconds": 42.5,
+        "tokens": 3800,
+        "tool_calls": 18,
+        "errors": 0
+      },
+      "expectations": [
+        {"text": "...", "passed": true, "evidence": "..."}
+      ],
+      "notes": [
+        "Used 2023 data, may be stale",
+        "Fell back to text overlay for non-fillable fields"
+      ]
+    }
+  ],
+
+  "run_summary": {
+    "with_skill": {
+      "pass_rate": {"mean": 0.85, "stddev": 0.05, "min": 0.80, "max": 0.90},
+      "time_seconds": {"mean": 45.0, "stddev": 12.0, "min": 32.0, "max": 58.0},
+      "tokens": {"mean": 3800, "stddev": 400, "min": 3200, "max": 4100}
+    },
+    "without_skill": {
+      "pass_rate": {"mean": 0.35, "stddev": 0.08, "min": 0.28, "max": 0.45},
+      "time_seconds": {"mean": 32.0, "stddev": 8.0, "min": 24.0, "max": 42.0},
+      "tokens": {"mean": 2100, "stddev": 300, "min": 1800, "max": 2500}
+    },
+    "delta": {
+      "pass_rate": "+0.50",
+      "time_seconds": "+13.0",
+      "tokens": "+1700"
+    }
+  },
+
+  "notes": [
+    "Assertion 'Output is a PDF file' passes 100% in both configurations - may not differentiate skill value",
+    "Eval 3 shows high variance (50% ± 40%) - may be flaky or model-dependent",
+    "Without-skill runs consistently fail on table extraction expectations",
+    "Skill adds 13s average execution time but improves pass rate by 50%"
+  ]
+}
+```
+
+**Fields:**
+- `metadata`: Information about the benchmark run
+  - `skill_name`: Name of the skill
+  - `timestamp`: When the benchmark was run
+  - `evals_run`: List of eval names or IDs
+  - `runs_per_configuration`: Number of runs per config (e.g. 3)
+- `runs[]`: Individual run results
+  - `eval_id`: Numeric eval identifier
+  - `eval_name`: Human-readable eval name (used as section header in the viewer)
+  - `configuration`: Must be `"with_skill"` or `"without_skill"` (the viewer uses this exact string for grouping and color coding)
+  - `run_number`: Integer run number (1, 2, 3...)
+  - `result`: Nested object with `pass_rate`, `passed`, `total`, `time_seconds`, `tokens`, `errors`
+- `run_summary`: Statistical aggregates per configuration
+  - `with_skill` / `without_skill`: Each contains `pass_rate`, `time_seconds`, `tokens` objects with `mean` and `stddev` fields
+  - `delta`: Difference strings like `"+0.50"`, `"+13.0"`, `"+1700"`
+- `notes`: Freeform observations from the analyzer
+
+**Important:** The viewer reads these field names exactly. Using `config` instead of `configuration`, or putting `pass_rate` at the top level of a run instead of nested under `result`, will cause the viewer to show empty/zero values. Always reference this schema when generating benchmark.json manually.
+
+---
+
+## comparison.json
+
+Output from blind comparator. Located at `<grading-dir>/comparison-N.json`.
+
+```json
+{
+  "winner": "A",
+  "reasoning": "Output A provides a complete solution with proper formatting and all required fields. Output B is missing the date field and has formatting inconsistencies.",
+  "rubric": {
+    "A": {
+      "content": {
+        "correctness": 5,
+        "completeness": 5,
+        "accuracy": 4
+      },
+      "structure": {
+        "organization": 4,
+        "formatting": 5,
+        "usability": 4
+      },
+      "content_score": 4.7,
+      "structure_score": 4.3,
+      "overall_score": 9.0
+    },
+    "B": {
+      "content": {
+        "correctness": 3,
+        "completeness": 2,
+        "accuracy": 3
+      },
+      "structure": {
+        "organization": 3,
+        "formatting": 2,
+        "usability": 3
+      },
+      "content_score": 2.7,
+      "structure_score": 2.7,
+      "overall_score": 5.4
+    }
+  },
+  "output_quality": {
+    "A": {
+      "score": 9,
+      "strengths": ["Complete solution", "Well-formatted", "All fields present"],
+      "weaknesses": ["Minor style inconsistency in header"]
+    },
+    "B": {
+      "score": 5,
+      "strengths": ["Readable output", "Correct basic structure"],
+      "weaknesses": ["Missing date field", "Formatting inconsistencies", "Partial data extraction"]
+    }
+  },
+  "expectation_results": {
+    "A": {
+      "passed": 4,
+      "total": 5,
+      "pass_rate": 0.80,
+      "details": [
+        {"text": "Output includes name", "passed": true}
+      ]
+    },
+    "B": {
+      "passed": 3,
+      "total": 5,
+      "pass_rate": 0.60,
+      "details": [
+        {"text": "Output includes name", "passed": true}
+      ]
+    }
+  }
+}
+```
+
+---
+
+## analysis.json
+
+Output from post-hoc analyzer. Located at `<grading-dir>/analysis.json`.
+
+```json
+{
+  "comparison_summary": {
+    "winner": "A",
+    "winner_skill": "path/to/winner/skill",
+    "loser_skill": "path/to/loser/skill",
+    "comparator_reasoning": "Brief summary of why comparator chose winner"
+  },
+  "winner_strengths": [
+    "Clear step-by-step instructions for handling multi-page documents",
+    "Included validation script that caught formatting errors"
+  ],
+  "loser_weaknesses": [
+    "Vague instruction 'process the document appropriately' led to inconsistent behavior",
+    "No script for validation, agent had to improvise"
+  ],
+  "instruction_following": {
+    "winner": {
+      "score": 9,
+      "issues": ["Minor: skipped optional logging step"]
+    },
+    "loser": {
+      "score": 6,
+      "issues": [
+        "Did not use the skill's formatting template",
+        "Invented own approach instead of following step 3"
+      ]
+    }
+  },
+  "improvement_suggestions": [
+    {
+      "priority": "high",
+      "category": "instructions",
+      "suggestion": "Replace 'process the document appropriately' with explicit steps",
+      "expected_impact": "Would eliminate ambiguity that caused inconsistent behavior"
+    }
+  ],
+  "transcript_insights": {
+    "winner_execution_pattern": "Read skill -> Followed 5-step process -> Used validation script",
+    "loser_execution_pattern": "Read skill -> Unclear on approach -> Tried 3 different methods"
+  }
+}
+```

package/dist/skill/templates/eval-review.html

@@ -0,0 +1,146 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>Eval Set Review - __SKILL_NAME_PLACEHOLDER__</title>
+  <link rel="preconnect" href="https://fonts.googleapis.com">
+  <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+  <link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
+  <style>
+    * { box-sizing: border-box; margin: 0; padding: 0; }
+    body { font-family: 'Lora', Georgia, serif; background: #faf9f5; padding: 2rem; color: #141413; }
+    h1 { font-family: 'Poppins', sans-serif; margin-bottom: 0.5rem; font-size: 1.5rem; }
+    .description { color: #b0aea5; margin-bottom: 1.5rem; font-style: italic; max-width: 900px; }
+    .controls { margin-bottom: 1rem; display: flex; gap: 0.5rem; }
+    .btn { font-family: 'Poppins', sans-serif; padding: 0.5rem 1rem; border: none; border-radius: 6px; cursor: pointer; font-size: 0.875rem; font-weight: 500; }
+    .btn-add { background: #6a9bcc; color: white; }
+    .btn-add:hover { background: #5889b8; }
+    .btn-export { background: #d97757; color: white; }
+    .btn-export:hover { background: #c4613f; }
+    table { width: 100%; max-width: 1100px; border-collapse: collapse; background: white; border-radius: 6px; overflow: hidden; box-shadow: 0 1px 3px rgba(0,0,0,0.08); }
+    th { font-family: 'Poppins', sans-serif; background: #141413; color: #faf9f5; padding: 0.75rem 1rem; text-align: left; font-size: 0.875rem; }
+    td { padding: 0.75rem 1rem; border-bottom: 1px solid #e8e6dc; vertical-align: top; }
+    tr:nth-child(even) td { background: #faf9f5; }
+    tr:hover td { background: #f3f1ea; }
+    .section-header td { background: #e8e6dc; font-family: 'Poppins', sans-serif; font-weight: 500; font-size: 0.8rem; color: #141413; text-transform: uppercase; letter-spacing: 0.05em; }
+    .query-input { width: 100%; padding: 0.4rem; border: 1px solid #e8e6dc; border-radius: 4px; font-size: 0.875rem; font-family: 'Lora', Georgia, serif; resize: vertical; min-height: 60px; }
+    .query-input:focus { outline: none; border-color: #d97757; box-shadow: 0 0 0 2px rgba(217,119,87,0.15); }
+    .toggle { position: relative; display: inline-block; width: 44px; height: 24px; }
+    .toggle input { opacity: 0; width: 0; height: 0; }
+    .toggle .slider { position: absolute; inset: 0; background: #b0aea5; border-radius: 24px; cursor: pointer; transition: 0.2s; }
+    .toggle .slider::before { content: ""; position: absolute; width: 18px; height: 18px; left: 3px; bottom: 3px; background: white; border-radius: 50%; transition: 0.2s; }
+    .toggle input:checked + .slider { background: #d97757; }
+    .toggle input:checked + .slider::before { transform: translateX(20px); }
+    .btn-delete { background: #c44; color: white; padding: 0.3rem 0.6rem; border: none; border-radius: 4px; cursor: pointer; font-size: 0.75rem; font-family: 'Poppins', sans-serif; }
+    .btn-delete:hover { background: #a33; }
+    .summary { margin-top: 1rem; color: #b0aea5; font-size: 0.875rem; }
+  </style>
+</head>
+<body>
+  <h1>Eval Set Review: <span id="skill-name">__SKILL_NAME_PLACEHOLDER__</span></h1>
+  <p class="description">Current description: <span id="skill-desc">__SKILL_DESCRIPTION_PLACEHOLDER__</span></p>
+
+  <div class="controls">
+    <button class="btn btn-add" onclick="addRow()">+ Add Query</button>
+    <button class="btn btn-export" onclick="exportEvalSet()">Export Eval Set</button>
+  </div>
+
+  <table>
+    <thead>
+      <tr>
+        <th style="width:65%">Query</th>
+        <th style="width:18%">Should Trigger</th>
+        <th style="width:10%">Actions</th>
+      </tr>
+    </thead>
+    <tbody id="eval-body"></tbody>
+  </table>
+
+  <p class="summary" id="summary"></p>
+
+  <script>
+    const EVAL_DATA = __EVAL_DATA_PLACEHOLDER__;
+
+    let evalItems = [...EVAL_DATA];
+
+    function render() {
+      const tbody = document.getElementById('eval-body');
+      tbody.innerHTML = '';
+
+      // Sort: should-trigger first, then should-not-trigger
+      const sorted = evalItems
+        .map((item, origIdx) => ({ ...item, origIdx }))
+        .sort((a, b) => (b.should_trigger ? 1 : 0) - (a.should_trigger ? 1 : 0));
+
+      let lastGroup = null;
+      sorted.forEach(item => {
+        const group = item.should_trigger ? 'trigger' : 'no-trigger';
+        if (group !== lastGroup) {
+          const headerRow = document.createElement('tr');
+          headerRow.className = 'section-header';
+          headerRow.innerHTML = `<td colspan="3">${item.should_trigger ? 'Should Trigger' : 'Should NOT Trigger'}</td>`;
+          tbody.appendChild(headerRow);
+          lastGroup = group;
+        }
+
+        const idx = item.origIdx;
+        const tr = document.createElement('tr');
+        tr.innerHTML = `
+          <td><textarea class="query-input" onchange="updateQuery(${idx}, this.value)">${escapeHtml(item.query)}</textarea></td>
+          <td>
+            <label class="toggle">
+              <input type="checkbox" ${item.should_trigger ? 'checked' : ''} onchange="updateTrigger(${idx}, this.checked)">
+              <span class="slider"></span>
+            </label>
+            <span style="margin-left:8px;font-size:0.8rem;color:#b0aea5">${item.should_trigger ? 'Yes' : 'No'}</span>
+          </td>
+          <td><button class="btn-delete" onclick="deleteRow(${idx})">Delete</button></td>
+        `;
+        tbody.appendChild(tr);
+      });
+      updateSummary();
+    }
+
+    function escapeHtml(text) {
+      const div = document.createElement('div');
+      div.textContent = text;
+      return div.innerHTML;
+    }
+
+    function updateQuery(idx, value) { evalItems[idx].query = value; updateSummary(); }
+    function updateTrigger(idx, value) { evalItems[idx].should_trigger = value; render(); }
+    function deleteRow(idx) { evalItems.splice(idx, 1); render(); }
+
+    function addRow() {
+      evalItems.push({ query: '', should_trigger: true });
+      render();
+      const inputs = document.querySelectorAll('.query-input');
+      inputs[inputs.length - 1].focus();
+    }
+
+    function updateSummary() {
+      const trigger = evalItems.filter(i => i.should_trigger).length;
+      const noTrigger = evalItems.filter(i => !i.should_trigger).length;
+      document.getElementById('summary').textContent =
+        `${evalItems.length} queries total: ${trigger} should trigger, ${noTrigger} should not trigger`;
+    }
+
+    function exportEvalSet() {
+      const valid = evalItems.filter(i => i.query.trim() !== '');
+      const data = valid.map(i => ({ query: i.query.trim(), should_trigger: i.should_trigger }));
+      const blob = new Blob([JSON.stringify(data, null, 2)], { type: 'application/json' });
+      const url = URL.createObjectURL(blob);
+      const a = document.createElement('a');
+      a.href = url;
+      a.download = 'eval_set.json';
+      document.body.appendChild(a);
+      a.click();
+      document.body.removeChild(a);
+      URL.revokeObjectURL(url);
+    }
+
+    render();
+  </script>
+</body>
+</html>