diff --git a/skill-creator/scripts/generate_report.py b/skill-creator/scripts/generate_report.py new file mode 100644 index 0000000..c8c7630 --- /dev/null +++ b/skill-creator/scripts/generate_report.py @@ -0,0 +1,326 @@ +#!/usr/bin/env python3 +"""Generate an HTML report from run_loop.py output. + +Takes the JSON output from run_loop.py and generates a visual HTML report +showing each description attempt with check/x for each test case. +Distinguishes between train and test queries. +""" + +import argparse +import html +import json +import sys +from pathlib import Path + + +def generate_html(data: dict, auto_refresh: bool = False, skill_name: str = "") -> str: + """Generate HTML report from loop output data. If auto_refresh is True, adds a meta refresh tag.""" + history = data.get("history", []) + holdout = data.get("holdout", 0) + title_prefix = html.escape(skill_name + " – ") if skill_name else "" + + # Get all unique queries from train and test sets, with should_trigger info + train_queries: list[dict] = [] + test_queries: list[dict] = [] + if history: + for r in history[0].get("train_results", history[0].get("results", [])): + train_queries.append({"query": r["query"], "should_trigger": r.get("should_trigger", True)}) + if history[0].get("test_results"): + for r in history[0].get("test_results", []): + test_queries.append({"query": r["query"], "should_trigger": r.get("should_trigger", True)}) + + refresh_tag = ' \n' if auto_refresh else "" + + html_parts = [""" + + + +""" + refresh_tag + """ """ + title_prefix + """Skill Description Optimization + + + + + + +

""" + title_prefix + """Skill Description Optimization

+
+ Optimizing your skill's description. This page updates automatically as Claude tests different versions of your skill's description. Each row is an iteration — a new description attempt. The columns show test queries: green checkmarks mean the skill triggered correctly (or correctly didn't trigger), red crosses mean it got it wrong. The "Train" score shows performance on queries used to improve the description; the "Test" score shows performance on held-out queries the optimizer hasn't seen. When it's done, Claude will apply the best-performing description to your skill. +
+"""] + + # Summary section + best_test_score = data.get('best_test_score') + best_train_score = data.get('best_train_score') + html_parts.append(f""" +
+

Original: {html.escape(data.get('original_description', 'N/A'))}

+

Best: {html.escape(data.get('best_description', 'N/A'))}

+

Best Score: {data.get('best_score', 'N/A')} {'(test)' if best_test_score else '(train)'}

+

Iterations: {data.get('iterations_run', 0)} | Train: {data.get('train_size', '?')} | Test: {data.get('test_size', '?')}

+
+""") + + # Legend + html_parts.append(""" +
+ Query columns: + Should trigger + Should NOT trigger + Train + Test +
+""") + + # Table header + html_parts.append(""" +
+ + + + + + + +""") + + # Add column headers for train queries + for qinfo in train_queries: + polarity = "positive-col" if qinfo["should_trigger"] else "negative-col" + html_parts.append(f' \n') + + # Add column headers for test queries (different color) + for qinfo in test_queries: + polarity = "positive-col" if qinfo["should_trigger"] else "negative-col" + html_parts.append(f' \n') + + html_parts.append(""" + + +""") + + # Find best iteration for highlighting + if test_queries: + best_iter = max(history, key=lambda h: h.get("test_passed") or 0).get("iteration") + else: + best_iter = max(history, key=lambda h: h.get("train_passed", h.get("passed", 0))).get("iteration") + + # Add rows for each iteration + for h in history: + iteration = h.get("iteration", "?") + train_passed = h.get("train_passed", h.get("passed", 0)) + train_total = h.get("train_total", h.get("total", 0)) + test_passed = h.get("test_passed") + test_total = h.get("test_total") + description = h.get("description", "") + train_results = h.get("train_results", h.get("results", [])) + test_results = h.get("test_results", []) + + # Create lookups for results by query + train_by_query = {r["query"]: r for r in train_results} + test_by_query = {r["query"]: r for r in test_results} if test_results else {} + + # Compute aggregate correct/total runs across all retries + def aggregate_runs(results: list[dict]) -> tuple[int, int]: + correct = 0 + total = 0 + for r in results: + runs = r.get("runs", 0) + triggers = r.get("triggers", 0) + total += runs + if r.get("should_trigger", True): + correct += triggers + else: + correct += runs - triggers + return correct, total + + train_correct, train_runs = aggregate_runs(train_results) + test_correct, test_runs = aggregate_runs(test_results) + + # Determine score classes + def score_class(correct: int, total: int) -> str: + if total > 0: + ratio = correct / total + if ratio >= 0.8: + return "score-good" + elif ratio >= 0.5: + return "score-ok" + return "score-bad" + + train_class = score_class(train_correct, train_runs) + test_class = score_class(test_correct, test_runs) + + row_class = "best-row" if iteration == best_iter else "" + + html_parts.append(f""" + + + + +""") + + # Add result for each train query + for qinfo in train_queries: + r = train_by_query.get(qinfo["query"], {}) + did_pass = r.get("pass", False) + triggers = r.get("triggers", 0) + runs = r.get("runs", 0) + + icon = "✓" if did_pass else "✗" + css_class = "pass" if did_pass else "fail" + + html_parts.append(f' \n') + + # Add result for each test query (with different background) + for qinfo in test_queries: + r = test_by_query.get(qinfo["query"], {}) + did_pass = r.get("pass", False) + triggers = r.get("triggers", 0) + runs = r.get("runs", 0) + + icon = "✓" if did_pass else "✗" + css_class = "pass" if did_pass else "fail" + + html_parts.append(f' \n') + + html_parts.append(" \n") + + html_parts.append(""" +
IterTrainTestDescription{html.escape(qinfo["query"])}{html.escape(qinfo["query"])}
{iteration}{train_correct}/{train_runs}{test_correct}/{test_runs}{html.escape(description)}{icon}{triggers}/{runs}{icon}{triggers}/{runs}
+
+""") + + html_parts.append(""" + + +""") + + return "".join(html_parts) + + +def main(): + parser = argparse.ArgumentParser(description="Generate HTML report from run_loop output") + parser.add_argument("input", help="Path to JSON output from run_loop.py (or - for stdin)") + parser.add_argument("-o", "--output", default=None, help="Output HTML file (default: stdout)") + parser.add_argument("--skill-name", default="", help="Skill name to include in the report title") + args = parser.parse_args() + + if args.input == "-": + data = json.load(sys.stdin) + else: + data = json.loads(Path(args.input).read_text()) + + html_output = generate_html(data, skill_name=args.skill_name) + + if args.output: + Path(args.output).write_text(html_output) + print(f"Report written to {args.output}", file=sys.stderr) + else: + print(html_output) + + +if __name__ == "__main__": + main() \ No newline at end of file