macca-method 2.1.1 → 2.1.2

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

@@ -0,0 +1,328 @@
+#!/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
+
+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 = []
+
+    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(
+            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/.agents/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/.agents/skills/spec-audit/SKILL.md

@@ -35,6 +35,7 @@ Run as `@Fachri` (Tech Lead). Use the shared persona profile in `../_shared/refe
 You are **@Fachri - Tech Lead** and **Spec Reviewer**. Your job is to ensure that all source-of-truth documents speak the same language - no conflicts, no gaps, no ambiguity.
 
 Two audit modes:
+
 - **Project Mode** - audit `project-context/` documents
 - **Framework Mode** - audit the MACCA framework itself (README, skill docs, workflows)
 
@@ -59,18 +60,23 @@ To change it: update `codeReviewPreferences.fixMode` in `.agents/developer-confi
 Determine the mode from user context:
 
 ### Project Mode
+
 Audit `project-context/` documents. Use it when:
+
 - The user is checking spec alignment before coding
 - They just finished spec documents and want a pre-check
 - Spec audit is part of the normal workflow
 
 ### Framework Mode
+
 Audit MACCA itself (README, skill docs, workflows). Use it when:
+
 - The user wants to refine MACCA
 - They suspect instruction drift between skills
 - They want to verify alignment across README, `help`, and the workflows
 
 Before continuing, show the target:
+
 ```
 Mode: [Project / Framework]
 Auditing: [short list of main documents being checked]
@@ -85,6 +91,7 @@ Default valid prefixes (Project Mode): `FEAT-*`, `BR-*`, `NFR-*`, `AC-*`, `US-*`
 ### Project Mode
 
 Read everything available in `project-context/`:
+
 - `PRD.md` - features, business rules, acceptance criteria, non-goals
 - `architecture.md` - tech stack, folder structure, patterns
 - `schema.md` - tables, columns, types, relationships
@@ -99,7 +106,7 @@ Read everything that exists. Note ID patterns if they are used.
 
 ### Framework Mode
 
-Resolve the active skill installation root. First read `_shared/references/skill-catalog.md`, `invocation-policy.md`, `output-ownership.md`, `scope-rules.md`, and the MACCA README only when this is the MACCA source repository.
+Resolve the active skill installation root. First read `../_shared/references/skill-catalog.md`, `../_shared/references/invocation-policy.md`, `../_shared/references/output-ownership.md`, `../_shared/references/scope-rules.md`, and the MACCA README only when this is the MACCA source repository.
 
 Compare compact contracts first. Read full `SKILL.md`, local references/assets, or installer code only for skills/relationships flagged by that comparison or explicitly named by the user. Do not load the entire collection by default. Do not treat an application's README as MACCA documentation.
 
@@ -110,48 +117,57 @@ Compare compact contracts first. Read full `SKILL.md`, local references/assets,
 ### Project Mode
 
 **SA-01: PRD ↔ architecture**
+
 - Does the architecture support the PRD NFRs (performance, security, accessibility)?
 - Do the PRD constraints fit the chosen tech stack?
 - Do PRD success metrics map to architecture observability signals where technical instrumentation is required?
 - Does product rollout align with deployment, rollback, and recovery constraints?
 
 **SA-02: PRD ↔ schema**
+
 - Does every persisted PRD entity have a datastore-native representation (table, collection, aggregate, node, stream, or equivalent)?
 - Do validation, relationship, consistency, and retention rules reflect PRD business rules?
 
 **SA-03: PRD ↔ api**
+
 - Does every integration-facing PRD feature have supporting operations (endpoint, query/mutation, procedure, event, or equivalent)?
 - Does `api.md` contain operations for PRD non-goals?
 
 **SA-04: PRD ↔ Task.md**
+
 - Is every PRD feature mapped to >=1 task?
 - Does Task.md include tasks for features not in the PRD (scope creep)? If the feature is recorded in `## Approved Scope Delta`, mark it as `pending formal spec sync`, not a direct conflict.
 - Do PRD IDs (`FEAT-*`, `BR-*`) appear in Task.md traceability?
 - Do rollout, analytics, degraded behavior, and applicable NFR work have tasks or explicit N/A decisions?
 
 **SA-05: schema ↔ api**
+
 - Does every persisted input/output field in `api.md` map to the data contract where appropriate?
 - Do response types match schema types?
 - If schema/api traceability is used, does it reference real PRD IDs?
 - Do API retry/idempotency assumptions align with schema concurrency and consistency rules?
 
 **SA-06: architecture ↔ rules**
+
 - Are architectural patterns (e.g. repository pattern) required in `rules.md`?
 - Do any rules conflict with the chosen architecture?
 - Do logging, migration, feature-flag, generated-code, and secret rules exist only when their architecture/schema mechanisms apply?
 
 **SA-07: architecture ↔ schema**
+
 - Does schema notation fit the architecture's database choice?
 - Is schema style consistent with the architecture's ORM choice?
 - Do tenancy, scale, migration, backup, and recovery assumptions align?
 
 **SA-08: StyleGuide ↔ PRD**
+
 - Does the CSS framework in StyleGuide match any PRD mention?
 - Are all PRD pages/features covered by StyleGuide components?
 - Do accessibility targets and supported locales match the PRD?
 - Do operational UI states cover PRD failure/degraded behavior where UI is involved?
 
 **SA-09: Task.md ↔ all specs**
+
 - Do task references point to real spec sections?
 - Do task acceptance criteria match PRD acceptance criteria?
 - If task traceability IDs are used, do they reference real PRD/schema/api/rules IDs?
@@ -162,38 +178,47 @@ Compare compact contracts first. Read full `SKILL.md`, local references/assets,
 ### Framework Mode
 
 **SA-F01: README ↔ skill descriptions**
+
 - Are skill names, personas, and functions the same in README and `SKILL.md`?
 - Do README summaries differ from the actual skill descriptions?
 
 **SA-F02: README ↔ workflow order**
+
 - Does the README workflow match skill prerequisites?
 - Does the README suggest an order that conflicts with skill instructions?
 
 **SA-F03: help ↔ README**
+
 - Does `help` recommend the same next-step workflow as README?
 - Does `help` contain an alternative path that changes the core workflow order without reason?
 
 **SA-F04: Skill prerequisite consistency**
+
 - Are `brainstorm-*`, `developer`, `spec-init`, `spec-compliance`, and `code-review` aligned on prerequisites?
 - Does one skill allow a step that another skill marks invalid?
 
 **SA-F05: Output file naming consistency**
+
 - Are output names (`PRD.md`, `Task.md`, etc.) the same across all skills?
 - Are output locations (`project-context/`, `.agents/`, elsewhere) named consistently?
 
 **SA-F06: Cross-skill handoff**
+
 - Does the "next step" from skill A match the entry point of skill B?
 - Are there dead ends, loops, or mismatched handoffs?
 
 **SA-F07: Persona consistency**
+
 - Are personas, roles, and assigned skills consistent across README, `meet`, and skill frontmatter?
 - Does any skill name the wrong owner?
 
 **SA-F08: Enforcement & order consistency**
+
 - Are "spec-compliance before code-review," "update Task.md," and "confirm before bug-log" stated consistently everywhere?
 - Does any instruction weaken a mandatory gate elsewhere?
 
 **SA-F09: Terminology consistency**
+
 - Are terms such as `spec`, `project-context/`, `phase`, `task`, `Batch Generate`, and `Project Audit` used with the same meaning everywhere?
 - Is any concept defined differently in 2+ places?
 
@@ -261,11 +286,13 @@ Fix Manifest (only when corrections were requested):
 ```
 
 If there are no issues:
+
 ```
 ✅ All documents in this audit mode are consistent - no conflicts, inconsistencies, or ambiguities were found.
 ```
 
 **Apply fixes:**
+
 - Audit-only invocation: report only, regardless of `fixMode`; do not offer a mutation gate unless the user requests corrections.
 - Correction requested + `fix-then-report`: apply actionable corrections, validate all affected document pairs, then report.
 - Correction requested + `report-first`: show the summary and shared gate. On approval, resume directly under the Approval Resume Protocol.