xtrm-tools 0.5.0

package/skills/skill-creator/scripts/run_loop.py

@@ -0,0 +1,332 @@
+#!/usr/bin/env python3
+"""Run the eval + improve loop until all pass or max iterations reached.
+
+Combines run_eval.py and improve_description.py in a loop, tracking history
+and returning the best description found. Supports train/test split to prevent
+overfitting.
+"""
+
+import argparse
+import json
+import random
+import sys
+import tempfile
+import time
+import webbrowser
+from pathlib import Path
+
+import anthropic
+
+from scripts.generate_report import generate_html
+from scripts.improve_description import improve_description
+from scripts.run_eval import find_project_root, run_eval
+from scripts.utils import parse_skill_md
+
+
+def split_eval_set(eval_set: list[dict], holdout: float, seed: int = 42) -> tuple[list[dict], list[dict]]:
+    """Split eval set into train and test sets, stratified by should_trigger."""
+    random.seed(seed)
+
+    # Separate by should_trigger
+    trigger = [e for e in eval_set if e["should_trigger"]]
+    no_trigger = [e for e in eval_set if not e["should_trigger"]]
+
+    # Shuffle each group
+    random.shuffle(trigger)
+    random.shuffle(no_trigger)
+
+    # Calculate split points
+    n_trigger_test = max(1, int(len(trigger) * holdout))
+    n_no_trigger_test = max(1, int(len(no_trigger) * holdout))
+
+    # Split
+    test_set = trigger[:n_trigger_test] + no_trigger[:n_no_trigger_test]
+    train_set = trigger[n_trigger_test:] + no_trigger[n_no_trigger_test:]
+
+    return train_set, test_set
+
+
+def run_loop(
+    eval_set: list[dict],
+    skill_path: Path,
+    description_override: str | None,
+    num_workers: int,
+    timeout: int,
+    max_iterations: int,
+    runs_per_query: int,
+    trigger_threshold: float,
+    holdout: float,
+    model: str,
+    verbose: bool,
+    live_report_path: Path | None = None,
+    log_dir: Path | None = None,
+) -> dict:
+    """Run the eval + improvement loop."""
+    project_root = find_project_root()
+    name, original_description, content = parse_skill_md(skill_path)
+    current_description = description_override or original_description
+
+    # Split into train/test if holdout > 0
+    if holdout > 0:
+        train_set, test_set = split_eval_set(eval_set, holdout)
+        if verbose:
+            print(f"Split: {len(train_set)} train, {len(test_set)} test (holdout={holdout})", file=sys.stderr)
+    else:
+        train_set = eval_set
+        test_set = []
+
+    client = anthropic.Anthropic()
+    history = []
+    exit_reason = "unknown"
+
+    for iteration in range(1, max_iterations + 1):
+        if verbose:
+            print(f"\n{'='*60}", file=sys.stderr)
+            print(f"Iteration {iteration}/{max_iterations}", file=sys.stderr)
+            print(f"Description: {current_description}", file=sys.stderr)
+            print(f"{'='*60}", file=sys.stderr)
+
+        # Evaluate train + test together in one batch for parallelism
+        all_queries = train_set + test_set
+        t0 = time.time()
+        all_results = run_eval(
+            eval_set=all_queries,
+            skill_name=name,
+            description=current_description,
+            num_workers=num_workers,
+            timeout=timeout,
+            project_root=project_root,
+            runs_per_query=runs_per_query,
+            trigger_threshold=trigger_threshold,
+            model=model,
+        )
+        eval_elapsed = time.time() - t0
+
+        # Split results back into train/test by matching queries
+        train_queries_set = {q["query"] for q in train_set}
+        train_result_list = [r for r in all_results["results"] if r["query"] in train_queries_set]
+        test_result_list = [r for r in all_results["results"] if r["query"] not in train_queries_set]
+
+        train_passed = sum(1 for r in train_result_list if r["pass"])
+        train_total = len(train_result_list)
+        train_summary = {"passed": train_passed, "failed": train_total - train_passed, "total": train_total}
+        train_results = {"results": train_result_list, "summary": train_summary}
+
+        if test_set:
+            test_passed = sum(1 for r in test_result_list if r["pass"])
+            test_total = len(test_result_list)
+            test_summary = {"passed": test_passed, "failed": test_total - test_passed, "total": test_total}
+            test_results = {"results": test_result_list, "summary": test_summary}
+        else:
+            test_results = None
+            test_summary = None
+
+        history.append({
+            "iteration": iteration,
+            "description": current_description,
+            "train_passed": train_summary["passed"],
+            "train_failed": train_summary["failed"],
+            "train_total": train_summary["total"],
+            "train_results": train_results["results"],
+            "test_passed": test_summary["passed"] if test_summary else None,
+            "test_failed": test_summary["failed"] if test_summary else None,
+            "test_total": test_summary["total"] if test_summary else None,
+            "test_results": test_results["results"] if test_results else None,
+            # For backward compat with report generator
+            "passed": train_summary["passed"],
+            "failed": train_summary["failed"],
+            "total": train_summary["total"],
+            "results": train_results["results"],
+        })
+
+        # Write live report if path provided
+        if live_report_path:
+            partial_output = {
+                "original_description": original_description,
+                "best_description": current_description,
+                "best_score": "in progress",
+                "iterations_run": len(history),
+                "holdout": holdout,
+                "train_size": len(train_set),
+                "test_size": len(test_set),
+                "history": history,
+            }
+            live_report_path.write_text(generate_html(partial_output, auto_refresh=True, skill_name=name))
+
+        if verbose:
+            def print_eval_stats(label, results, elapsed):
+                pos = [r for r in results if r["should_trigger"]]
+                neg = [r for r in results if not r["should_trigger"]]
+                tp = sum(r["triggers"] for r in pos)
+                pos_runs = sum(r["runs"] for r in pos)
+                fn = pos_runs - tp
+                fp = sum(r["triggers"] for r in neg)
+                neg_runs = sum(r["runs"] for r in neg)
+                tn = neg_runs - fp
+                total = tp + tn + fp + fn
+                precision = tp / (tp + fp) if (tp + fp) > 0 else 1.0
+                recall = tp / (tp + fn) if (tp + fn) > 0 else 1.0
+                accuracy = (tp + tn) / total if total > 0 else 0.0
+                print(f"{label}: {tp+tn}/{total} correct, precision={precision:.0%} recall={recall:.0%} accuracy={accuracy:.0%} ({elapsed:.1f}s)", file=sys.stderr)
+                for r in results:
+                    status = "PASS" if r["pass"] else "FAIL"
+                    rate_str = f"{r['triggers']}/{r['runs']}"
+                    print(f"  [{status}] rate={rate_str} expected={r['should_trigger']}: {r['query'][:60]}", file=sys.stderr)
+
+            print_eval_stats("Train", train_results["results"], eval_elapsed)
+            if test_summary:
+                print_eval_stats("Test ", test_results["results"], 0)
+
+        if train_summary["failed"] == 0:
+            exit_reason = f"all_passed (iteration {iteration})"
+            if verbose:
+                print(f"\nAll train queries passed on iteration {iteration}!", file=sys.stderr)
+            break
+
+        if iteration == max_iterations:
+            exit_reason = f"max_iterations ({max_iterations})"
+            if verbose:
+                print(f"\nMax iterations reached ({max_iterations}).", file=sys.stderr)
+            break
+
+        # Improve the description based on train results
+        if verbose:
+            print(f"\nImproving description...", file=sys.stderr)
+
+        t0 = time.time()
+        # Strip test scores from history so improvement model can't see them
+        blinded_history = [
+            {k: v for k, v in h.items() if not k.startswith("test_")}
+            for h in history
+        ]
+        new_description = improve_description(
+            client=client,
+            skill_name=name,
+            skill_content=content,
+            current_description=current_description,
+            eval_results=train_results,
+            history=blinded_history,
+            model=model,
+            log_dir=log_dir,
+            iteration=iteration,
+        )
+        improve_elapsed = time.time() - t0
+
+        if verbose:
+            print(f"Proposed ({improve_elapsed:.1f}s): {new_description}", file=sys.stderr)
+
+        current_description = new_description
+
+    # Find the best iteration by TEST score (or train if no test set)
+    if test_set:
+        best = max(history, key=lambda h: h["test_passed"] or 0)
+        best_score = f"{best['test_passed']}/{best['test_total']}"
+    else:
+        best = max(history, key=lambda h: h["train_passed"])
+        best_score = f"{best['train_passed']}/{best['train_total']}"
+
+    if verbose:
+        print(f"\nExit reason: {exit_reason}", file=sys.stderr)
+        print(f"Best score: {best_score} (iteration {best['iteration']})", file=sys.stderr)
+
+    return {
+        "exit_reason": exit_reason,
+        "original_description": original_description,
+        "best_description": best["description"],
+        "best_score": best_score,
+        "best_train_score": f"{best['train_passed']}/{best['train_total']}",
+        "best_test_score": f"{best['test_passed']}/{best['test_total']}" if test_set else None,
+        "final_description": current_description,
+        "iterations_run": len(history),
+        "holdout": holdout,
+        "train_size": len(train_set),
+        "test_size": len(test_set),
+        "history": history,
+    }
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Run eval + improve loop")
+    parser.add_argument("--eval-set", required=True, help="Path to eval set JSON file")
+    parser.add_argument("--skill-path", required=True, help="Path to skill directory")
+    parser.add_argument("--description", default=None, help="Override starting description")
+    parser.add_argument("--num-workers", type=int, default=10, help="Number of parallel workers")
+    parser.add_argument("--timeout", type=int, default=30, help="Timeout per query in seconds")
+    parser.add_argument("--max-iterations", type=int, default=5, help="Max improvement iterations")
+    parser.add_argument("--runs-per-query", type=int, default=3, help="Number of runs per query")
+    parser.add_argument("--trigger-threshold", type=float, default=0.5, help="Trigger rate threshold")
+    parser.add_argument("--holdout", type=float, default=0.4, help="Fraction of eval set to hold out for testing (0 to disable)")
+    parser.add_argument("--model", required=True, help="Model for improvement")
+    parser.add_argument("--verbose", action="store_true", help="Print progress to stderr")
+    parser.add_argument("--report", default="auto", help="Generate HTML report at this path (default: 'auto' for temp file, 'none' to disable)")
+    parser.add_argument("--results-dir", default=None, help="Save all outputs (results.json, report.html, log.txt) to a timestamped subdirectory here")
+    args = parser.parse_args()
+
+    eval_set = json.loads(Path(args.eval_set).read_text())
+    skill_path = Path(args.skill_path)
+
+    if not (skill_path / "SKILL.md").exists():
+        print(f"Error: No SKILL.md found at {skill_path}", file=sys.stderr)
+        sys.exit(1)
+
+    name, _, _ = parse_skill_md(skill_path)
+
+    # Set up live report path
+    if args.report != "none":
+        if args.report == "auto":
+            timestamp = time.strftime("%Y%m%d_%H%M%S")
+            live_report_path = Path(tempfile.gettempdir()) / f"skill_description_report_{skill_path.name}_{timestamp}.html"
+        else:
+            live_report_path = Path(args.report)
+        # Open the report immediately so the user can watch
+        live_report_path.write_text("<html><body><h1>Starting optimization loop...</h1><meta http-equiv='refresh' content='5'></body></html>")
+        webbrowser.open(str(live_report_path))
+    else:
+        live_report_path = None
+
+    # Determine output directory (create before run_loop so logs can be written)
+    if args.results_dir:
+        timestamp = time.strftime("%Y-%m-%d_%H%M%S")
+        results_dir = Path(args.results_dir) / timestamp
+        results_dir.mkdir(parents=True, exist_ok=True)
+    else:
+        results_dir = None
+
+    log_dir = results_dir / "logs" if results_dir else None
+
+    output = run_loop(
+        eval_set=eval_set,
+        skill_path=skill_path,
+        description_override=args.description,
+        num_workers=args.num_workers,
+        timeout=args.timeout,
+        max_iterations=args.max_iterations,
+        runs_per_query=args.runs_per_query,
+        trigger_threshold=args.trigger_threshold,
+        holdout=args.holdout,
+        model=args.model,
+        verbose=args.verbose,
+        live_report_path=live_report_path,
+        log_dir=log_dir,
+    )
+
+    # Save JSON output
+    json_output = json.dumps(output, indent=2)
+    print(json_output)
+    if results_dir:
+        (results_dir / "results.json").write_text(json_output)
+
+    # Write final HTML report (without auto-refresh)
+    if live_report_path:
+        live_report_path.write_text(generate_html(output, auto_refresh=False, skill_name=name))
+        print(f"\nReport: {live_report_path}", file=sys.stderr)
+
+    if results_dir and live_report_path:
+        (results_dir / "report.html").write_text(generate_html(output, auto_refresh=False, skill_name=name))
+
+    if results_dir:
+        print(f"Results saved to: {results_dir}", file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()

package/skills/skill-creator/scripts/utils.py

@@ -0,0 +1,47 @@
+"""Shared utilities for skill-creator scripts."""
+
+from pathlib import Path
+
+
+
+def parse_skill_md(skill_path: Path) -> tuple[str, str, str]:
+    """Parse a SKILL.md file, returning (name, description, full_content)."""
+    content = (skill_path / "SKILL.md").read_text()
+    lines = content.split("\n")
+
+    if lines[0].strip() != "---":
+        raise ValueError("SKILL.md missing frontmatter (no opening ---)")
+
+    end_idx = None
+    for i, line in enumerate(lines[1:], start=1):
+        if line.strip() == "---":
+            end_idx = i
+            break
+
+    if end_idx is None:
+        raise ValueError("SKILL.md missing frontmatter (no closing ---)")
+
+    name = ""
+    description = ""
+    frontmatter_lines = lines[1:end_idx]
+    i = 0
+    while i < len(frontmatter_lines):
+        line = frontmatter_lines[i]
+        if line.startswith("name:"):
+            name = line[len("name:"):].strip().strip('"').strip("'")
+        elif line.startswith("description:"):
+            value = line[len("description:"):].strip()
+            # Handle YAML multiline indicators (>, |, >-, |-)
+            if value in (">", "|", ">-", "|-"):
+                continuation_lines: list[str] = []
+                i += 1
+                while i < len(frontmatter_lines) and (frontmatter_lines[i].startswith("  ") or frontmatter_lines[i].startswith("\t")):
+                    continuation_lines.append(frontmatter_lines[i].strip())
+                    i += 1
+                description = " ".join(continuation_lines)
+                continue
+            else:
+                description = value.strip('"').strip("'")
+        i += 1
+
+    return name, description, content

package/skills/sync-docs/SKILL.md

@@ -0,0 +1,132 @@
+---
+name: sync-docs
+description: >-
+  Doc audit and structural sync for xtrm projects. Use whenever the README
+  feels too long, docs are out of sync after a sprint, the CHANGELOG is behind,
+  or the user asks to "sync docs", "doc audit", "split readme", "check docs
+  health", or "detect drift". Reads bd issues and git history, then runs
+  docs-only drift detection on README.md, CHANGELOG.md, and docs/ — creating
+  missing focused files instead of a monolithic README.
+gemini-command: sync-docs
+version: 1.1.0
+---
+
+# sync-docs
+
+Keeps project documentation in sync with code reality.
+
+## Overview
+
+```
+Phase 1: Gather context     — what changed recently?
+Phase 2: Detect docs drift  — which docs/ files are stale?
+Phase 3: Analyze structure  — what belongs outside README?
+Phase 4: Plan + execute     — fix docs and changelog
+Phase 5: Validate           — schema-check all docs/
+```
+
+**Audit vs Execute mode:** If the user asked for an audit/report/check-only task, stop after Phase 3. Only run fixes when the user explicitly asks for changes.
+
+---
+
+## Phase 1: Gather Context
+
+```bash
+# Global install
+python3 "$HOME/.claude/skills/sync-docs/scripts/context_gatherer.py" [--since=30]
+
+# From repository
+python3 "skills/sync-docs/scripts/context_gatherer.py" [--since=30]
+```
+
+Outputs JSON with:
+- recently closed bd issues
+- merged PRs from git history
+- recent commits
+- docs drift report from `sync-docs/scripts/drift_detector.py`
+
+---
+
+## Phase 2: Detect docs/ Drift
+
+```bash
+python3 "skills/sync-docs/scripts/drift_detector.py" scan --since 30
+# optional JSON:
+python3 "skills/sync-docs/scripts/drift_detector.py" scan --since 30 --json
+```
+
+A docs file is stale when frontmatter `source_of_truth_for` (or `tracks`) matches files changed in recent commits.
+
+---
+
+## Phase 3: Analyze Document Structure
+
+```bash
+python3 "skills/sync-docs/scripts/doc_structure_analyzer.py"
+```
+
+Checks:
+1. README bloat/extractable sections
+2. CHANGELOG staleness (date + version gap)
+3. Missing focused docs files
+4. Invalid docs schema (missing frontmatter)
+
+Statuses: `BLOATED`, `EXTRACTABLE`, `MISSING`, `STALE`, `INVALID_SCHEMA`, `OK`.
+
+If this is audit-only, stop here and report.
+
+---
+
+## Phase 4: Execute Fixes
+
+| Situation | Action |
+|---|---|
+| README bloated | Extract large sections to focused docs files |
+| Missing docs file | Generate scaffold via `validate_doc.py --generate` |
+| Stale docs file | Update content + bump `version` + `updated` |
+| Stale CHANGELOG | Add entry with local changelog script |
+| Invalid schema | Fix frontmatter and regenerate INDEX |
+
+### Auto-fix known gaps
+
+```bash
+python3 "skills/sync-docs/scripts/doc_structure_analyzer.py" --fix
+python3 "skills/sync-docs/scripts/doc_structure_analyzer.py" --fix --bd-remember
+```
+
+### Create one docs scaffold
+
+```bash
+python3 "skills/sync-docs/scripts/validate_doc.py" --generate docs/hooks.md \
+  --title "Hooks Reference" --scope "hooks" --category "reference" \
+  --source-for "hooks/**/*.mjs,policies/*.json"
+```
+
+### Validate and regenerate metadata/index
+
+```bash
+python3 "skills/sync-docs/scripts/validate_metadata.py" docs/
+```
+
+### Add changelog entry
+
+```bash
+python3 "skills/sync-docs/scripts/changelog/add_entry.py" \
+  CHANGELOG.md Added "Describe the documentation update"
+```
+
+---
+
+## Phase 5: Final Validation
+
+```bash
+python3 "skills/sync-docs/scripts/validate_doc.py" docs/
+python3 "skills/sync-docs/scripts/drift_detector.py" scan --since 30
+```
+
+---
+
+## docs/ as SSOT
+
+`docs/` is the only source of truth for project documentation in this workflow.
+Use frontmatter (`source_of_truth_for`) to link docs pages to code areas and detect drift.

package/skills/sync-docs/evals/evals.json

@@ -0,0 +1,89 @@
+{
+  "skill_name": "sync-docs",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "I just closed a bunch of bd issues this sprint and merged 3 PRs. The README.md is getting long — can you sync the docs and make sure everything's in order? Use sync-docs.",
+      "expected_output": "Runs context_gatherer.py and doc_structure_analyzer.py, reports what was found (closed issues, PRs, any drift), identifies README extraction candidates or MISSING docs/ files, and either fixes them or gives a clear plan with next steps.",
+      "files": [],
+      "assertions": [
+        {
+          "id": "ran-context-gatherer",
+          "description": "Ran context_gatherer.py and reported bd closed issues or merged PRs from the output",
+          "check": "result.md mentions context_gatherer or bd closed issues or merged PRs with specific data"
+        },
+        {
+          "id": "ran-structure-analyzer",
+          "description": "Ran doc_structure_analyzer.py and used its output to identify doc issues",
+          "check": "result.md references MISSING, STALE, EXTRACTABLE, or BLOATED status from the analyzer"
+        },
+        {
+          "id": "concrete-action",
+          "description": "Produced at least one concrete recommendation or action (not just a vague summary)",
+          "check": "result.md names a specific file (e.g. docs/hooks.md) or section with a specific next step"
+        },
+        {
+          "id": "used-skill-scripts",
+          "description": "Used the skill scripts rather than just reading files manually",
+          "check": "result.md shows script execution output, not just manual file reading"
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "prompt": "Run sync-docs --fix on this project and remember what you did with bd.",
+      "expected_output": "Runs doc_structure_analyzer.py --fix --bd-remember, creates scaffold files for any missing docs/ subsystems, persists a bd memory with the summary, then validates the created files with validate_doc.py.",
+      "files": [],
+      "assertions": [
+        {
+          "id": "ran-fix-flag",
+          "description": "Ran doc_structure_analyzer.py with --fix flag",
+          "check": "result.md shows the --fix command was executed"
+        },
+        {
+          "id": "ran-bd-remember",
+          "description": "Ran with --bd-remember or manually ran bd remember with a summary",
+          "check": "result.md shows bd remember was called and reports the memory key"
+        },
+        {
+          "id": "scaffold-created",
+          "description": "At least one scaffold file was created in docs/",
+          "check": "result.md lists a docs/*.md file created, OR reports no gaps found (valid outcome)"
+        },
+        {
+          "id": "validated-schema",
+          "description": "Ran validate_doc.py on created files to confirm schema",
+          "check": "result.md shows validate_doc.py was run and reports pass/fail for created files"
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "prompt": "Do a doc audit. I think the README has sections that should be in docs/ but I'm not sure which ones.",
+      "expected_output": "Runs the full 5-phase sync-docs workflow: gathers context, runs drift detection, runs doc_structure_analyzer.py, and identifies EXTRACTABLE/BLOATED sections with specific suggestions for what goes in which docs/ file before recommending or making changes.",
+      "files": [],
+      "assertions": [
+        {
+          "id": "ran-analyzer",
+          "description": "Ran doc_structure_analyzer.py and referenced its structured output",
+          "check": "result.md cites the analyzer output (EXTRACTABLE, BLOATED, line count, or specific section names from the report)"
+        },
+        {
+          "id": "named-specific-sections",
+          "description": "Named specific README sections with their suggested docs/ destination",
+          "check": "result.md lists at least 2 specific sections (e.g. '## Policy System → docs/policies.md') not just generic advice"
+        },
+        {
+          "id": "actionable-report",
+          "description": "Report is actionable — tells user exactly what to do next, not just observations",
+          "check": "result.md includes a prioritized list or clear next steps, not just 'the README could be shorter'"
+        },
+        {
+          "id": "no-edits-made",
+          "description": "Did not edit or create any files (audit only)",
+          "check": "result.md does not claim to have modified README.md or created docs/ files"
+        }
+      ]
+    }
+  ]
+}