dongshuyan/compass-skills / skills/run-history-skill-upgrader
run-history-skill-upgrader
VerifiedUse real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed platform behavior, or validated workflow feedback. Do not use to create a brand-new skill or to execute the business workflow itself.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.6 KB |
| agents/openai.yaml | config | 306 B |
| evals/evals.json | config | 5.4 KB |
| references/evidence-and-scope.md | markdown | 2.6 KB |
| references/examples.md | markdown | 2.3 KB |
| references/upgrade-decision-protocol.md | markdown | 2.9 KB |
| references/validation-and-regression.md | markdown | 2.7 KB |
| scripts/test_validate_upgrade_artifacts.py | script | 5.7 KB |
| scripts/validate_upgrade_artifacts.py | script | 13.6 KB |
scripts/test_validate_upgrade_artifacts.py
View on GitHub#!/usr/bin/env python3
"""Regression tests for the upgrader's portable package validator."""
from __future__ import annotations
import json
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path
VALIDATOR = Path(__file__).with_name("validate_upgrade_artifacts.py")
def write_skill(root: Path) -> Path:
skill_dir = root / "sample-upgrader"
skill_dir.mkdir()
(skill_dir / "SKILL.md").write_text(
"""---
name: sample-upgrader
description: >- # folded description
Plan evidence-based improvements to an existing skill
and apply them only after review.
license: Apache-2.0
compatibility: Requires Python 3.10 or newer
metadata: # package metadata
category: maintenance
allowed-tools: Read Bash
---
# Sample Upgrader
Start in `plan_only`, require `explicit approval`, and operate on an
`existing skill` only.
""",
encoding="utf-8",
)
scripts_dir = skill_dir / "scripts"
scripts_dir.mkdir()
(scripts_dir / "check.py").write_text("VALUE = 1\n", encoding="utf-8")
evals_dir = skill_dir / "evals"
evals_dir.mkdir()
(evals_dir / "evals.json").write_text(
json.dumps(
{
"evals": [
{
"id": 1,
"prompt": "Upgrade this existing skill from a failed run.",
"expected_output": "A reviewable plan before edits.",
"expectations": ["Stops for explicit approval."],
}
]
}
),
encoding="utf-8",
)
return skill_dir
class ValidateUpgradeArtifactsTests(unittest.TestCase):
def test_accepts_multiline_yaml_and_supported_optional_fields(self) -> None:
with tempfile.TemporaryDirectory() as temp_dir:
skill_dir = write_skill(Path(temp_dir))
result = subprocess.run(
[
sys.executable,
"-B",
str(VALIDATOR),
"--skill",
str(skill_dir),
"--json",
],
check=False,
capture_output=True,
text=True,
)
payload = json.loads(result.stdout)
self.assertEqual(result.returncode, 0, payload)
self.assertEqual(
payload["validation_scope"],
"package_structure_and_deterministic_artifact_checks",
)
self.assertFalse(payload["behavior_evaluated"])
self.assertEqual(payload["errors"], [])
self.assertEqual(payload["warnings"], [])
self.assertFalse((skill_dir / "scripts" / "__pycache__").exists())
def test_accepts_quoted_name_with_trailing_comment(self) -> None:
with tempfile.TemporaryDirectory() as temp_dir:
skill_dir = write_skill(Path(temp_dir))
skill_md = skill_dir / "SKILL.md"
skill_md.write_text(
skill_md.read_text(encoding="utf-8").replace(
"name: sample-upgrader",
'name: "sample-upgrader" # package name',
),
encoding="utf-8",
)
result = subprocess.run(
[
sys.executable,
"-B",
str(VALIDATOR),
"--skill",
str(skill_dir),
"--json",
],
check=False,
capture_output=True,
text=True,
)
payload = json.loads(result.stdout)
self.assertEqual(result.returncode, 0, payload)
self.assertEqual(payload["errors"], [])
def test_rejects_malformed_nested_metadata(self) -> None:
for malformed_value in ("[maintenance", "team: east"):
with self.subTest(malformed_value=malformed_value):
with tempfile.TemporaryDirectory() as temp_dir:
skill_dir = write_skill(Path(temp_dir))
skill_md = skill_dir / "SKILL.md"
skill_md.write_text(
skill_md.read_text(encoding="utf-8").replace(
" category: maintenance",
f" category: {malformed_value}",
),
encoding="utf-8",
)
result = subprocess.run(
[
sys.executable,
"-B",
str(VALIDATOR),
"--skill",
str(skill_dir),
"--json",
],
check=False,
capture_output=True,
text=True,
)
payload = json.loads(result.stdout)
self.assertEqual(result.returncode, 1, payload)
self.assertTrue(
any("unsupported nested frontmatter value syntax" in item for item in payload["errors"]),
payload,
)
def test_success_message_does_not_claim_behavior_validation(self) -> None:
with tempfile.TemporaryDirectory() as temp_dir:
skill_dir = write_skill(Path(temp_dir))
result = subprocess.run(
[sys.executable, "-B", str(VALIDATOR), "--skill", str(skill_dir)],
check=False,
capture_output=True,
text=True,
)
self.assertEqual(result.returncode, 0, result.stdout)
self.assertIn("structural package validation passed", result.stdout)
self.assertIn("does not evaluate skill behavior", result.stdout)
if __name__ == "__main__":
unittest.main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |