@intentsolutionsio/skill-creator 5.0.0 → 5.0.3

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

@@ -41,9 +41,7 @@ def _call_claude(prompt: str, model: str | None, timeout: int = 300) -> str:
         timeout=timeout,
     )
     if result.returncode != 0:
-        raise RuntimeError(
-            f"claude -p exited {result.returncode}\nstderr: {result.stderr}"
-        )
+        raise RuntimeError(f"claude -p exited {result.returncode}\nstderr: {result.stderr}")
     return result.stdout
 
 
@@ -59,14 +57,8 @@ def improve_description(
     iteration: int | None = None,
 ) -> str:
     """Call Claude to improve the description based on eval results."""
-    failed_triggers = [
-        r for r in eval_results["results"]
-        if r["should_trigger"] and not r["pass"]
-    ]
-    false_triggers = [
-        r for r in eval_results["results"]
-        if not r["should_trigger"] and not r["pass"]
-    ]
+    failed_triggers = [r for r in eval_results["results"] if r["should_trigger"] and not r["pass"]]
+    false_triggers = [r for r in eval_results["results"] if not r["should_trigger"] and not r["pass"]]
 
     # Build scores summary
     train_score = f"{eval_results['summary']['passed']}/{eval_results['summary']['total']}"
@@ -104,9 +96,11 @@ Current scores ({scores_summary}):
         prompt += "PREVIOUS ATTEMPTS (do NOT repeat these — try something structurally different):\n\n"
         for h in history:
             train_s = f"{h.get('train_passed', h.get('passed', 0))}/{h.get('train_total', h.get('total', 0))}"
-            test_s = f"{h.get('test_passed', '?')}/{h.get('test_total', '?')}" if h.get('test_passed') is not None else None
+            test_s = (
+                f"{h.get('test_passed', '?')}/{h.get('test_total', '?')}" if h.get("test_passed") is not None else None
+            )
             score_str = f"train={train_s}" + (f", test={test_s}" if test_s else "")
-            prompt += f'<attempt {score_str}>\n'
+            prompt += f"<attempt {score_str}>\n"
             prompt += f'Description: "{h["description"]}"\n'
             if "results" in h:
                 prompt += "Train results:\n"
@@ -114,7 +108,7 @@ Current scores ({scores_summary}):
                     status = "PASS" if r["pass"] else "FAIL"
                     prompt += f'  [{status}] "{r["query"][:80]}" (triggered {r["triggers"]}/{r["runs"]})\n'
             if h.get("note"):
-                prompt += f'Note: {h["note"]}\n'
+                prompt += f"Note: {h['note']}\n"
             prompt += "</attempt>\n\n"
 
     prompt += f"""</scores_summary>
@@ -232,13 +226,16 @@ def main():
     # Output as JSON with both the new description and updated history
     output = {
         "description": new_description,
-        "history": history + [{
-            "description": current_description,
-            "passed": eval_results["summary"]["passed"],
-            "failed": eval_results["summary"]["failed"],
-            "total": eval_results["summary"]["total"],
-            "results": eval_results["results"],
-        }],
+        "history": history
+        + [
+            {
+                "description": current_description,
+                "passed": eval_results["summary"]["passed"],
+                "failed": eval_results["summary"]["failed"],
+                "total": eval_results["summary"]["total"],
+                "results": eval_results["results"],
+            }
+        ],
     }
     print(json.dumps(output, indent=2))
 

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

@@ -88,9 +88,9 @@ def package_skill(skill_path, output_dir=None):
 
     # Create the .skill file (zip format)
     try:
-        with zipfile.ZipFile(skill_filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
+        with zipfile.ZipFile(skill_filename, "w", zipfile.ZIP_DEFLATED) as zipf:
             # Walk through the skill directory, excluding build artifacts
-            for file_path in skill_path.rglob('*'):
+            for file_path in skill_path.rglob("*"):
                 if not file_path.is_file():
                     continue
                 arcname = file_path.relative_to(skill_path.parent)

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

@@ -4,27 +4,27 @@ Quick validation script for skills - minimal version
 """
 
 import sys
-import os
 import re
 import yaml
 from pathlib import Path
 
+
 def validate_skill(skill_path):
     """Basic validation of a skill"""
     skill_path = Path(skill_path)
 
     # Check SKILL.md exists
-    skill_md = skill_path / 'SKILL.md'
+    skill_md = skill_path / "SKILL.md"
     if not skill_md.exists():
         return False, "SKILL.md not found"
 
     # Read and validate frontmatter
     content = skill_md.read_text()
-    if not content.startswith('---'):
+    if not content.startswith("---"):
         return False, "No YAML frontmatter found"
 
     # Extract frontmatter
-    match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL)
+    match = re.match(r"^---\n(.*?)\n---", content, re.DOTALL)
     if not match:
         return False, "Invalid frontmatter format"
 
@@ -39,7 +39,7 @@ def validate_skill(skill_path):
         return False, f"Invalid YAML in frontmatter: {e}"
 
     # Define allowed properties
-    ALLOWED_PROPERTIES = {'name', 'description', 'license', 'allowed-tools', 'metadata', 'compatibility'}
+    ALLOWED_PROPERTIES = {"name", "description", "license", "allowed-tools", "metadata", "compatibility"}
 
     # Check for unexpected properties (excluding nested keys under metadata)
     unexpected_keys = set(frontmatter.keys()) - ALLOWED_PROPERTIES
@@ -50,41 +50,41 @@ def validate_skill(skill_path):
         )
 
     # Check required fields
-    if 'name' not in frontmatter:
+    if "name" not in frontmatter:
         return False, "Missing 'name' in frontmatter"
-    if 'description' not in frontmatter:
+    if "description" not in frontmatter:
         return False, "Missing 'description' in frontmatter"
 
     # Extract name for validation
-    name = frontmatter.get('name', '')
+    name = frontmatter.get("name", "")
     if not isinstance(name, str):
         return False, f"Name must be a string, got {type(name).__name__}"
     name = name.strip()
     if name:
         # Check naming convention (kebab-case: lowercase with hyphens)
-        if not re.match(r'^[a-z0-9-]+$', name):
+        if not re.match(r"^[a-z0-9-]+$", name):
             return False, f"Name '{name}' should be kebab-case (lowercase letters, digits, and hyphens only)"
-        if name.startswith('-') or name.endswith('-') or '--' in name:
+        if name.startswith("-") or name.endswith("-") or "--" in name:
             return False, f"Name '{name}' cannot start/end with hyphen or contain consecutive hyphens"
         # Check name length (max 64 characters per spec)
         if len(name) > 64:
             return False, f"Name is too long ({len(name)} characters). Maximum is 64 characters."
 
     # Extract and validate description
-    description = frontmatter.get('description', '')
+    description = frontmatter.get("description", "")
     if not isinstance(description, str):
         return False, f"Description must be a string, got {type(description).__name__}"
     description = description.strip()
     if description:
         # Check for angle brackets
-        if '<' in description or '>' in description:
+        if "<" in description or ">" in description:
             return False, "Description cannot contain angle brackets (< or >)"
         # Check description length (max 1024 characters per spec)
         if len(description) > 1024:
             return False, f"Description is too long ({len(description)} characters). Maximum is 1024 characters."
 
     # Validate compatibility field if present (optional)
-    compatibility = frontmatter.get('compatibility', '')
+    compatibility = frontmatter.get("compatibility", "")
     if compatibility:
         if not isinstance(compatibility, str):
             return False, f"Compatibility must be a string, got {type(compatibility).__name__}"
@@ -93,11 +93,12 @@ def validate_skill(skill_path):
 
     return True, "Skill is valid!"
 
+
 if __name__ == "__main__":
     if len(sys.argv) != 2:
         print("Usage: python quick_validate.py <skill_directory>")
         sys.exit(1)
-    
+
     valid, message = validate_skill(sys.argv[1])
     print(message)
-    sys.exit(0 if valid else 1)
+    sys.exit(0 if valid else 1)

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

@@ -101,8 +101,10 @@ def run_single_query(
 
         cmd = [
             "claude",
-            "-p", query,
-            "--output-format", "stream-json",
+            "-p",
+            query,
+            "--output-format",
+            "stream-json",
             "--verbose",
             "--include-partial-messages",
         ]
@@ -265,14 +267,16 @@ def run_eval(
             did_pass = trigger_rate >= trigger_threshold
         else:
             did_pass = trigger_rate < trigger_threshold
-        results.append({
-            "query": query,
-            "should_trigger": should_trigger,
-            "trigger_rate": trigger_rate,
-            "triggers": sum(triggers),
-            "runs": len(triggers),
-            "pass": did_pass,
-        })
+        results.append(
+            {
+                "query": query,
+                "should_trigger": should_trigger,
+                "trigger_rate": trigger_rate,
+                "triggers": sum(triggers),
+                "runs": len(triggers),
+                "pass": did_pass,
+            }
+        )
 
     passed = sum(1 for r in results if r["pass"])
     total = len(results)

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

@@ -78,10 +78,10 @@ def run_loop(
 
     for iteration in range(1, max_iterations + 1):
         if verbose:
-            print(f"\n{'='*60}", file=sys.stderr)
+            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)
+            print(f"{'=' * 60}", file=sys.stderr)
 
         # Evaluate train + test together in one batch for parallelism
         all_queries = train_set + test_set
@@ -119,23 +119,25 @@ def run_loop(
             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"],
-        })
+        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:
@@ -152,6 +154,7 @@ def run_loop(
             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"]]
@@ -165,11 +168,17 @@ def run_loop(
                 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)
+                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(
+                        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:
@@ -189,14 +198,11 @@ def run_loop(
 
         # Improve the description based on train results
         if verbose:
-            print(f"\nImproving description...", file=sys.stderr)
+            print("\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
-        ]
+        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,
@@ -252,11 +258,21 @@ def main():
     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(
+        "--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")
+    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())
@@ -272,11 +288,15 @@ def main():
     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"
+            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>")
+        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

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

@@ -3,7 +3,6 @@
 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()
@@ -28,14 +27,16 @@ def parse_skill_md(skill_path: Path) -> tuple[str, str, str]:
     while i < len(frontmatter_lines):
         line = frontmatter_lines[i]
         if line.startswith("name:"):
-            name = line[len("name:"):].strip().strip('"').strip("'")
+            name = line[len("name:") :].strip().strip('"').strip("'")
         elif line.startswith("description:"):
-            value = line[len("description:"):].strip()
+            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")):
+                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)

package/skills/skill-creator/templates/agent-template.md

@@ -76,6 +76,7 @@ You receive these parameters in your prompt:
 ## When Activated
 
 You activate when:
+
 - {{ACTIVATION_CONDITION_1}}
 - {{ACTIVATION_CONDITION_2}}
 - {{ACTIVATION_CONDITION_3}}
@@ -89,11 +90,13 @@ You activate when:
 ## Success Criteria
 
 Good output includes:
+
 - {{QUALITY_MARKER_1}}
 - {{QUALITY_MARKER_2}}
 - {{QUALITY_MARKER_3}}
 
 Poor output is:
+
 - {{ANTI_PATTERN_1}}
 - {{ANTI_PATTERN_2}}
 - {{ANTI_PATTERN_3}}

package/skills/skill-creator/templates/skill-template.md

@@ -68,11 +68,13 @@ model: inherit
 ### {{EXAMPLE_1_TITLE}}
 
 **Input:**
+
 ```
 {{EXAMPLE_1_INPUT}}
 ```
 
 **Output:**
+
 ```
 {{EXAMPLE_1_OUTPUT}}
 ```
@@ -80,11 +82,13 @@ model: inherit
 ### {{EXAMPLE_2_TITLE}}
 
 **Input:**
+
 ```
 {{EXAMPLE_2_INPUT}}
 ```
 
 **Output:**
+
 ```
 {{EXAMPLE_2_OUTPUT}}
 ```