@xaviele/ag-kit 1.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +20 -0
- package/bin/cli.js +63 -0
- package/package.json +27 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/charts.csv +26 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/colors.csv +97 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/icons.csv +101 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/landing.csv +31 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/products.csv +97 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/prompts.csv +24 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/react-performance.csv +45 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/flutter.csv +53 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/html-tailwind.csv +56 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/jetpack-compose.csv +53 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/nextjs.csv +53 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/nuxt-ui.csv +51 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/nuxtjs.csv +59 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/react-native.csv +52 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/react.csv +54 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/shadcn.csv +61 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/svelte.csv +54 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/swiftui.csv +51 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/stacks/vue.csv +50 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/styles.csv +59 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/typography.csv +58 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/ui-reasoning.csv +101 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/ux-guidelines.csv +100 -0
- package/template/.agent/.shared/ui-ux-pro-max/data/web-interface.csv +31 -0
- package/template/.agent/.shared/ui-ux-pro-max/scripts/__pycache__/core.cpython-313.pyc +0 -0
- package/template/.agent/.shared/ui-ux-pro-max/scripts/__pycache__/design_system.cpython-313.pyc +0 -0
- package/template/.agent/.shared/ui-ux-pro-max/scripts/core.py +258 -0
- package/template/.agent/.shared/ui-ux-pro-max/scripts/design_system.py +1067 -0
- package/template/.agent/.shared/ui-ux-pro-max/scripts/search.py +106 -0
- package/template/.agent/ARCHITECTURE.md +281 -0
- package/template/.agent/agents/backend-specialist.md +263 -0
- package/template/.agent/agents/code-archaeologist.md +106 -0
- package/template/.agent/agents/database-architect.md +226 -0
- package/template/.agent/agents/debugger.md +225 -0
- package/template/.agent/agents/devops-engineer.md +242 -0
- package/template/.agent/agents/documentation-writer.md +104 -0
- package/template/.agent/agents/explorer-agent.md +73 -0
- package/template/.agent/agents/frontend-specialist.md +593 -0
- package/template/.agent/agents/game-developer.md +162 -0
- package/template/.agent/agents/mobile-developer.md +377 -0
- package/template/.agent/agents/orchestrator.md +416 -0
- package/template/.agent/agents/penetration-tester.md +188 -0
- package/template/.agent/agents/performance-optimizer.md +187 -0
- package/template/.agent/agents/product-manager.md +112 -0
- package/template/.agent/agents/product-owner.md +95 -0
- package/template/.agent/agents/project-planner.md +406 -0
- package/template/.agent/agents/qa-automation-engineer.md +103 -0
- package/template/.agent/agents/security-auditor.md +170 -0
- package/template/.agent/agents/seo-specialist.md +111 -0
- package/template/.agent/agents/test-engineer.md +158 -0
- package/template/.agent/mcp_config.json +24 -0
- package/template/.agent/rules/GEMINI.md +273 -0
- package/template/.agent/scripts/auto_preview.py +148 -0
- package/template/.agent/scripts/checklist.py +217 -0
- package/template/.agent/scripts/session_manager.py +120 -0
- package/template/.agent/scripts/verify_all.py +327 -0
- package/template/.agent/skills/adr/SKILL.md +282 -0
- package/template/.agent/skills/alirezarezvani-code-to-prd/SKILL.md +499 -0
- package/template/.agent/skills/api-patterns/SKILL.md +81 -0
- package/template/.agent/skills/api-patterns/api-style.md +42 -0
- package/template/.agent/skills/api-patterns/auth.md +24 -0
- package/template/.agent/skills/api-patterns/documentation.md +26 -0
- package/template/.agent/skills/api-patterns/graphql.md +41 -0
- package/template/.agent/skills/api-patterns/rate-limiting.md +31 -0
- package/template/.agent/skills/api-patterns/response.md +37 -0
- package/template/.agent/skills/api-patterns/rest.md +40 -0
- package/template/.agent/skills/api-patterns/scripts/api_validator.py +211 -0
- package/template/.agent/skills/api-patterns/security-testing.md +122 -0
- package/template/.agent/skills/api-patterns/trpc.md +41 -0
- package/template/.agent/skills/api-patterns/versioning.md +22 -0
- package/template/.agent/skills/app-builder/SKILL.md +75 -0
- package/template/.agent/skills/app-builder/agent-coordination.md +71 -0
- package/template/.agent/skills/app-builder/feature-building.md +53 -0
- package/template/.agent/skills/app-builder/project-detection.md +34 -0
- package/template/.agent/skills/app-builder/scaffolding.md +118 -0
- package/template/.agent/skills/app-builder/tech-stack.md +41 -0
- package/template/.agent/skills/app-builder/templates/SKILL.md +39 -0
- package/template/.agent/skills/app-builder/templates/astro-static/TEMPLATE.md +76 -0
- package/template/.agent/skills/app-builder/templates/chrome-extension/TEMPLATE.md +92 -0
- package/template/.agent/skills/app-builder/templates/cli-tool/TEMPLATE.md +88 -0
- package/template/.agent/skills/app-builder/templates/electron-desktop/TEMPLATE.md +88 -0
- package/template/.agent/skills/app-builder/templates/express-api/TEMPLATE.md +83 -0
- package/template/.agent/skills/app-builder/templates/flutter-app/TEMPLATE.md +90 -0
- package/template/.agent/skills/app-builder/templates/monorepo-turborepo/TEMPLATE.md +90 -0
- package/template/.agent/skills/app-builder/templates/nextjs-fullstack/TEMPLATE.md +122 -0
- package/template/.agent/skills/app-builder/templates/nextjs-saas/TEMPLATE.md +122 -0
- package/template/.agent/skills/app-builder/templates/nextjs-static/TEMPLATE.md +169 -0
- package/template/.agent/skills/app-builder/templates/nuxt-app/TEMPLATE.md +134 -0
- package/template/.agent/skills/app-builder/templates/python-fastapi/TEMPLATE.md +83 -0
- package/template/.agent/skills/app-builder/templates/react-native-app/TEMPLATE.md +119 -0
- package/template/.agent/skills/architecture/SKILL.md +55 -0
- package/template/.agent/skills/architecture/context-discovery.md +43 -0
- package/template/.agent/skills/architecture/examples.md +94 -0
- package/template/.agent/skills/architecture/pattern-selection.md +68 -0
- package/template/.agent/skills/architecture/patterns-reference.md +50 -0
- package/template/.agent/skills/architecture/trade-off-analysis.md +77 -0
- package/template/.agent/skills/bash-linux/SKILL.md +199 -0
- package/template/.agent/skills/behavioral-modes/SKILL.md +242 -0
- package/template/.agent/skills/brainstorming/SKILL.md +163 -0
- package/template/.agent/skills/brainstorming/dynamic-questioning.md +350 -0
- package/template/.agent/skills/claudekit-ai-multimodal/SKILL.md +353 -0
- package/template/.agent/skills/clean-code/SKILL.md +201 -0
- package/template/.agent/skills/code-review-checklist/SKILL.md +109 -0
- package/template/.agent/skills/database-design/SKILL.md +52 -0
- package/template/.agent/skills/database-design/database-selection.md +43 -0
- package/template/.agent/skills/database-design/indexing.md +39 -0
- package/template/.agent/skills/database-design/migrations.md +48 -0
- package/template/.agent/skills/database-design/optimization.md +36 -0
- package/template/.agent/skills/database-design/orm-selection.md +30 -0
- package/template/.agent/skills/database-design/schema-design.md +56 -0
- package/template/.agent/skills/database-design/scripts/schema_validator.py +172 -0
- package/template/.agent/skills/deployment-procedures/SKILL.md +241 -0
- package/template/.agent/skills/doc.md +177 -0
- package/template/.agent/skills/document/SKILL.md +250 -0
- package/template/.agent/skills/documentation-templates/SKILL.md +194 -0
- package/template/.agent/skills/frontend-design/SKILL.md +452 -0
- package/template/.agent/skills/frontend-design/animation-guide.md +331 -0
- package/template/.agent/skills/frontend-design/color-system.md +311 -0
- package/template/.agent/skills/frontend-design/decision-trees.md +418 -0
- package/template/.agent/skills/frontend-design/motion-graphics.md +306 -0
- package/template/.agent/skills/frontend-design/scripts/accessibility_checker.py +183 -0
- package/template/.agent/skills/frontend-design/scripts/ux_audit.py +722 -0
- package/template/.agent/skills/frontend-design/typography-system.md +345 -0
- package/template/.agent/skills/frontend-design/ux-psychology.md +1116 -0
- package/template/.agent/skills/frontend-design/visual-effects.md +383 -0
- package/template/.agent/skills/game-development/2d-games/SKILL.md +119 -0
- package/template/.agent/skills/game-development/3d-games/SKILL.md +135 -0
- package/template/.agent/skills/game-development/SKILL.md +167 -0
- package/template/.agent/skills/game-development/game-art/SKILL.md +185 -0
- package/template/.agent/skills/game-development/game-audio/SKILL.md +190 -0
- package/template/.agent/skills/game-development/game-design/SKILL.md +129 -0
- package/template/.agent/skills/game-development/mobile-games/SKILL.md +108 -0
- package/template/.agent/skills/game-development/multiplayer/SKILL.md +132 -0
- package/template/.agent/skills/game-development/pc-games/SKILL.md +144 -0
- package/template/.agent/skills/game-development/vr-ar/SKILL.md +123 -0
- package/template/.agent/skills/game-development/web-games/SKILL.md +150 -0
- package/template/.agent/skills/geo-fundamentals/SKILL.md +156 -0
- package/template/.agent/skills/geo-fundamentals/scripts/geo_checker.py +289 -0
- package/template/.agent/skills/i18n-localization/SKILL.md +154 -0
- package/template/.agent/skills/i18n-localization/scripts/i18n_checker.py +241 -0
- package/template/.agent/skills/intelligent-routing/SKILL.md +335 -0
- package/template/.agent/skills/lint-and-validate/SKILL.md +45 -0
- package/template/.agent/skills/lint-and-validate/scripts/lint_runner.py +184 -0
- package/template/.agent/skills/lint-and-validate/scripts/type_coverage.py +173 -0
- package/template/.agent/skills/mcp-builder/SKILL.md +176 -0
- package/template/.agent/skills/mindrally-meta-prompt/SKILL.md +129 -0
- package/template/.agent/skills/mobile-design/SKILL.md +394 -0
- package/template/.agent/skills/mobile-design/decision-trees.md +516 -0
- package/template/.agent/skills/mobile-design/mobile-backend.md +491 -0
- package/template/.agent/skills/mobile-design/mobile-color-system.md +420 -0
- package/template/.agent/skills/mobile-design/mobile-debugging.md +122 -0
- package/template/.agent/skills/mobile-design/mobile-design-thinking.md +357 -0
- package/template/.agent/skills/mobile-design/mobile-navigation.md +458 -0
- package/template/.agent/skills/mobile-design/mobile-performance.md +767 -0
- package/template/.agent/skills/mobile-design/mobile-testing.md +356 -0
- package/template/.agent/skills/mobile-design/mobile-typography.md +433 -0
- package/template/.agent/skills/mobile-design/platform-android.md +666 -0
- package/template/.agent/skills/mobile-design/platform-ios.md +561 -0
- package/template/.agent/skills/mobile-design/scripts/mobile_audit.py +670 -0
- package/template/.agent/skills/mobile-design/touch-psychology.md +537 -0
- package/template/.agent/skills/nextjs-react-expert/1-async-eliminating-waterfalls.md +351 -0
- package/template/.agent/skills/nextjs-react-expert/2-bundle-bundle-size-optimization.md +240 -0
- package/template/.agent/skills/nextjs-react-expert/3-server-server-side-performance.md +490 -0
- package/template/.agent/skills/nextjs-react-expert/4-client-client-side-data-fetching.md +264 -0
- package/template/.agent/skills/nextjs-react-expert/5-rerender-re-render-optimization.md +581 -0
- package/template/.agent/skills/nextjs-react-expert/6-rendering-rendering-performance.md +432 -0
- package/template/.agent/skills/nextjs-react-expert/7-js-javascript-performance.md +684 -0
- package/template/.agent/skills/nextjs-react-expert/8-advanced-advanced-patterns.md +150 -0
- package/template/.agent/skills/nextjs-react-expert/9-cache-components.md +103 -0
- package/template/.agent/skills/nextjs-react-expert/SKILL.md +293 -0
- package/template/.agent/skills/nextjs-react-expert/scripts/convert_rules.py +222 -0
- package/template/.agent/skills/nextjs-react-expert/scripts/react_performance_checker.py +252 -0
- package/template/.agent/skills/nodejs-best-practices/SKILL.md +333 -0
- package/template/.agent/skills/parallel-agents/SKILL.md +175 -0
- package/template/.agent/skills/performance-profiling/SKILL.md +143 -0
- package/template/.agent/skills/performance-profiling/scripts/lighthouse_audit.py +76 -0
- package/template/.agent/skills/plan-writing/SKILL.md +152 -0
- package/template/.agent/skills/pm-skills-create-prd/SKILL.md +88 -0
- package/template/.agent/skills/powershell-windows/SKILL.md +167 -0
- package/template/.agent/skills/prompt-engineering/SKILL.md +566 -0
- package/template/.agent/skills/python-patterns/SKILL.md +441 -0
- package/template/.agent/skills/red-team-tactics/SKILL.md +199 -0
- package/template/.agent/skills/rust-pro/SKILL.md +176 -0
- package/template/.agent/skills/seo-fundamentals/SKILL.md +129 -0
- package/template/.agent/skills/seo-fundamentals/scripts/seo_checker.py +219 -0
- package/template/.agent/skills/server-management/SKILL.md +161 -0
- package/template/.agent/skills/skills/adr/SKILL.md +282 -0
- package/template/.agent/skills/skills/alirezarezvani-code-to-prd/SKILL.md +499 -0
- package/template/.agent/skills/skills/claudekit-ai-multimodal/SKILL.md +353 -0
- package/template/.agent/skills/skills/document/SKILL.md +250 -0
- package/template/.agent/skills/skills/mindrally-meta-prompt/SKILL.md +129 -0
- package/template/.agent/skills/skills/pm-skills-create-prd/SKILL.md +88 -0
- package/template/.agent/skills/skills/prompt-engineering/SKILL.md +566 -0
- package/template/.agent/skills/systematic-debugging/SKILL.md +109 -0
- package/template/.agent/skills/tailwind-patterns/SKILL.md +269 -0
- package/template/.agent/skills/tdd-workflow/SKILL.md +149 -0
- package/template/.agent/skills/testing-patterns/SKILL.md +178 -0
- package/template/.agent/skills/testing-patterns/scripts/test_runner.py +219 -0
- package/template/.agent/skills/vulnerability-scanner/SKILL.md +276 -0
- package/template/.agent/skills/vulnerability-scanner/checklists.md +121 -0
- package/template/.agent/skills/vulnerability-scanner/scripts/security_scan.py +458 -0
- package/template/.agent/skills/web-design-guidelines/SKILL.md +57 -0
- package/template/.agent/skills/webapp-testing/SKILL.md +187 -0
- package/template/.agent/skills/webapp-testing/scripts/playwright_runner.py +173 -0
- package/template/.agent/skills/zalo-mini-app/SKILL.md +81 -0
- package/template/.agent/skills/zalo-mini-app/references/api-device.md +121 -0
- package/template/.agent/skills/zalo-mini-app/references/api-overview.md +88 -0
- package/template/.agent/skills/zalo-mini-app/references/api-storage.md +74 -0
- package/template/.agent/skills/zalo-mini-app/references/api-ui.md +124 -0
- package/template/.agent/skills/zalo-mini-app/references/api-user.md +113 -0
- package/template/.agent/skills/zalo-mini-app/references/api-zalo.md +127 -0
- package/template/.agent/skills/zalo-mini-app/references/design-guidelines.md +70 -0
- package/template/.agent/skills/zalo-mini-app/references/getting-started.md +95 -0
- package/template/.agent/skills/zalo-mini-app/references/react-best-practices.md +790 -0
- package/template/.agent/skills/zalo-mini-app/references/web-design-guidelines.md +591 -0
- package/template/.agent/skills/zalo-mini-app/references/zaui-display.md +103 -0
- package/template/.agent/skills/zalo-mini-app/references/zaui-form.md +108 -0
- package/template/.agent/skills/zalo-mini-app/references/zaui-layout.md +94 -0
- package/template/.agent/skills/zalo-mini-app/references/zaui-overlay.md +98 -0
- package/template/.agent/skills/zalo-mini-app/references/zaui-overview.md +82 -0
- package/template/.agent/workflows/brainstorm.md +113 -0
- package/template/.agent/workflows/create.md +59 -0
- package/template/.agent/workflows/debug.md +103 -0
- package/template/.agent/workflows/deploy.md +176 -0
- package/template/.agent/workflows/enhance.md +63 -0
- package/template/.agent/workflows/orchestrate.md +237 -0
- package/template/.agent/workflows/plan.md +89 -0
- package/template/.agent/workflows/preview.md +81 -0
- package/template/.agent/workflows/status.md +86 -0
- package/template/.agent/workflows/test.md +144 -0
- package/template/.agent/workflows/ui-ux-pro-max.md +296 -0
- package/template/.agent/workflows/veo-marketing.md +46 -0
|
@@ -0,0 +1,184 @@
|
|
|
1
|
+
#!/usr/bin/env python3
|
|
2
|
+
"""
|
|
3
|
+
Lint Runner - Unified linting and type checking
|
|
4
|
+
Runs appropriate linters based on project type.
|
|
5
|
+
|
|
6
|
+
Usage:
|
|
7
|
+
python lint_runner.py <project_path>
|
|
8
|
+
|
|
9
|
+
Supports:
|
|
10
|
+
- Node.js: npm run lint, npx tsc --noEmit
|
|
11
|
+
- Python: ruff check, mypy
|
|
12
|
+
"""
|
|
13
|
+
|
|
14
|
+
import subprocess
|
|
15
|
+
import sys
|
|
16
|
+
import json
|
|
17
|
+
import platform
|
|
18
|
+
import shutil
|
|
19
|
+
from pathlib import Path
|
|
20
|
+
from datetime import datetime
|
|
21
|
+
|
|
22
|
+
# Fix Windows console encoding
|
|
23
|
+
try:
|
|
24
|
+
sys.stdout.reconfigure(encoding='utf-8', errors='replace')
|
|
25
|
+
except:
|
|
26
|
+
pass
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
def detect_project_type(project_path: Path) -> dict:
|
|
30
|
+
"""Detect project type and available linters."""
|
|
31
|
+
result = {
|
|
32
|
+
"type": "unknown",
|
|
33
|
+
"linters": []
|
|
34
|
+
}
|
|
35
|
+
|
|
36
|
+
# Node.js project
|
|
37
|
+
package_json = project_path / "package.json"
|
|
38
|
+
if package_json.exists():
|
|
39
|
+
result["type"] = "node"
|
|
40
|
+
try:
|
|
41
|
+
pkg = json.loads(package_json.read_text(encoding='utf-8'))
|
|
42
|
+
scripts = pkg.get("scripts", {})
|
|
43
|
+
deps = {**pkg.get("dependencies", {}), **pkg.get("devDependencies", {})}
|
|
44
|
+
|
|
45
|
+
# Check for lint script
|
|
46
|
+
if "lint" in scripts:
|
|
47
|
+
result["linters"].append({"name": "npm lint", "cmd": ["npm", "run", "lint"]})
|
|
48
|
+
elif "eslint" in deps:
|
|
49
|
+
result["linters"].append({"name": "eslint", "cmd": ["npx", "eslint", "."]})
|
|
50
|
+
|
|
51
|
+
# Check for TypeScript
|
|
52
|
+
if "typescript" in deps or (project_path / "tsconfig.json").exists():
|
|
53
|
+
result["linters"].append({"name": "tsc", "cmd": ["npx", "tsc", "--noEmit"]})
|
|
54
|
+
|
|
55
|
+
except:
|
|
56
|
+
pass
|
|
57
|
+
|
|
58
|
+
# Python project
|
|
59
|
+
if (project_path / "pyproject.toml").exists() or (project_path / "requirements.txt").exists():
|
|
60
|
+
result["type"] = "python"
|
|
61
|
+
|
|
62
|
+
# Check for ruff
|
|
63
|
+
result["linters"].append({"name": "ruff", "cmd": ["ruff", "check", "."]})
|
|
64
|
+
|
|
65
|
+
# Check for mypy
|
|
66
|
+
if (project_path / "mypy.ini").exists() or (project_path / "pyproject.toml").exists():
|
|
67
|
+
result["linters"].append({"name": "mypy", "cmd": ["mypy", "."]})
|
|
68
|
+
|
|
69
|
+
return result
|
|
70
|
+
|
|
71
|
+
|
|
72
|
+
def run_linter(linter: dict, cwd: Path) -> dict:
|
|
73
|
+
"""Run a single linter and return results."""
|
|
74
|
+
result = {
|
|
75
|
+
"name": linter["name"],
|
|
76
|
+
"passed": False,
|
|
77
|
+
"output": "",
|
|
78
|
+
"error": ""
|
|
79
|
+
}
|
|
80
|
+
|
|
81
|
+
try:
|
|
82
|
+
cmd = linter["cmd"]
|
|
83
|
+
|
|
84
|
+
# Windows compatibility for npm/npx
|
|
85
|
+
if platform.system() == "Windows":
|
|
86
|
+
if cmd[0] in ["npm", "npx"]:
|
|
87
|
+
# Force .cmd extension on Windows
|
|
88
|
+
if not cmd[0].lower().endswith(".cmd"):
|
|
89
|
+
cmd[0] = f"{cmd[0]}.cmd"
|
|
90
|
+
|
|
91
|
+
proc = subprocess.run(
|
|
92
|
+
cmd,
|
|
93
|
+
cwd=str(cwd),
|
|
94
|
+
capture_output=True,
|
|
95
|
+
text=True,
|
|
96
|
+
encoding='utf-8',
|
|
97
|
+
errors='replace',
|
|
98
|
+
timeout=120,
|
|
99
|
+
shell=platform.system() == "Windows" # Shell=True often helps with path resolution on Windows
|
|
100
|
+
)
|
|
101
|
+
|
|
102
|
+
result["output"] = proc.stdout[:2000] if proc.stdout else ""
|
|
103
|
+
result["error"] = proc.stderr[:500] if proc.stderr else ""
|
|
104
|
+
result["passed"] = proc.returncode == 0
|
|
105
|
+
|
|
106
|
+
except FileNotFoundError:
|
|
107
|
+
result["error"] = f"Command not found: {linter['cmd'][0]}"
|
|
108
|
+
except subprocess.TimeoutExpired:
|
|
109
|
+
result["error"] = "Timeout after 120s"
|
|
110
|
+
except Exception as e:
|
|
111
|
+
result["error"] = str(e)
|
|
112
|
+
|
|
113
|
+
return result
|
|
114
|
+
|
|
115
|
+
|
|
116
|
+
def main():
|
|
117
|
+
project_path = Path(sys.argv[1] if len(sys.argv) > 1 else ".").resolve()
|
|
118
|
+
|
|
119
|
+
print(f"\n{'='*60}")
|
|
120
|
+
print(f"[LINT RUNNER] Unified Linting")
|
|
121
|
+
print(f"{'='*60}")
|
|
122
|
+
print(f"Project: {project_path}")
|
|
123
|
+
print(f"Time: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
|
|
124
|
+
|
|
125
|
+
# Detect project type
|
|
126
|
+
project_info = detect_project_type(project_path)
|
|
127
|
+
print(f"Type: {project_info['type']}")
|
|
128
|
+
print(f"Linters: {len(project_info['linters'])}")
|
|
129
|
+
print("-"*60)
|
|
130
|
+
|
|
131
|
+
if not project_info["linters"]:
|
|
132
|
+
print("No linters found for this project type.")
|
|
133
|
+
output = {
|
|
134
|
+
"script": "lint_runner",
|
|
135
|
+
"project": str(project_path),
|
|
136
|
+
"type": project_info["type"],
|
|
137
|
+
"checks": [],
|
|
138
|
+
"passed": True,
|
|
139
|
+
"message": "No linters configured"
|
|
140
|
+
}
|
|
141
|
+
print(json.dumps(output, indent=2))
|
|
142
|
+
sys.exit(0)
|
|
143
|
+
|
|
144
|
+
# Run each linter
|
|
145
|
+
results = []
|
|
146
|
+
all_passed = True
|
|
147
|
+
|
|
148
|
+
for linter in project_info["linters"]:
|
|
149
|
+
print(f"\nRunning: {linter['name']}...")
|
|
150
|
+
result = run_linter(linter, project_path)
|
|
151
|
+
results.append(result)
|
|
152
|
+
|
|
153
|
+
if result["passed"]:
|
|
154
|
+
print(f" [PASS] {linter['name']}")
|
|
155
|
+
else:
|
|
156
|
+
print(f" [FAIL] {linter['name']}")
|
|
157
|
+
if result["error"]:
|
|
158
|
+
print(f" Error: {result['error'][:200]}")
|
|
159
|
+
all_passed = False
|
|
160
|
+
|
|
161
|
+
# Summary
|
|
162
|
+
print("\n" + "="*60)
|
|
163
|
+
print("SUMMARY")
|
|
164
|
+
print("="*60)
|
|
165
|
+
|
|
166
|
+
for r in results:
|
|
167
|
+
icon = "[PASS]" if r["passed"] else "[FAIL]"
|
|
168
|
+
print(f"{icon} {r['name']}")
|
|
169
|
+
|
|
170
|
+
output = {
|
|
171
|
+
"script": "lint_runner",
|
|
172
|
+
"project": str(project_path),
|
|
173
|
+
"type": project_info["type"],
|
|
174
|
+
"checks": results,
|
|
175
|
+
"passed": all_passed
|
|
176
|
+
}
|
|
177
|
+
|
|
178
|
+
print("\n" + json.dumps(output, indent=2))
|
|
179
|
+
|
|
180
|
+
sys.exit(0 if all_passed else 1)
|
|
181
|
+
|
|
182
|
+
|
|
183
|
+
if __name__ == "__main__":
|
|
184
|
+
main()
|
|
@@ -0,0 +1,173 @@
|
|
|
1
|
+
#!/usr/bin/env python3
|
|
2
|
+
"""
|
|
3
|
+
Type Coverage Checker - Measures TypeScript/Python type coverage.
|
|
4
|
+
Identifies untyped functions, any usage, and type safety issues.
|
|
5
|
+
"""
|
|
6
|
+
import sys
|
|
7
|
+
import re
|
|
8
|
+
import subprocess
|
|
9
|
+
from pathlib import Path
|
|
10
|
+
|
|
11
|
+
# Fix Windows console encoding for Unicode output
|
|
12
|
+
try:
|
|
13
|
+
sys.stdout.reconfigure(encoding='utf-8', errors='replace')
|
|
14
|
+
sys.stderr.reconfigure(encoding='utf-8', errors='replace')
|
|
15
|
+
except AttributeError:
|
|
16
|
+
pass # Python < 3.7
|
|
17
|
+
|
|
18
|
+
def check_typescript_coverage(project_path: Path) -> dict:
|
|
19
|
+
"""Check TypeScript type coverage."""
|
|
20
|
+
issues = []
|
|
21
|
+
passed = []
|
|
22
|
+
stats = {'any_count': 0, 'untyped_functions': 0, 'total_functions': 0}
|
|
23
|
+
|
|
24
|
+
ts_files = list(project_path.rglob("*.ts")) + list(project_path.rglob("*.tsx"))
|
|
25
|
+
ts_files = [f for f in ts_files if 'node_modules' not in str(f) and '.d.ts' not in str(f)]
|
|
26
|
+
|
|
27
|
+
if not ts_files:
|
|
28
|
+
return {'type': 'typescript', 'files': 0, 'passed': [], 'issues': ["[!] No TypeScript files found"], 'stats': stats}
|
|
29
|
+
|
|
30
|
+
for file_path in ts_files[:30]: # Limit
|
|
31
|
+
try:
|
|
32
|
+
content = file_path.read_text(encoding='utf-8', errors='ignore')
|
|
33
|
+
|
|
34
|
+
# Count 'any' usage
|
|
35
|
+
any_matches = re.findall(r':\s*any\b', content)
|
|
36
|
+
stats['any_count'] += len(any_matches)
|
|
37
|
+
|
|
38
|
+
# Find functions without return types
|
|
39
|
+
# function name(params) { - no return type
|
|
40
|
+
untyped = re.findall(r'function\s+\w+\s*\([^)]*\)\s*{', content)
|
|
41
|
+
# Arrow functions without types: const fn = (x) => or (x) =>
|
|
42
|
+
untyped += re.findall(r'=\s*\([^:)]*\)\s*=>', content)
|
|
43
|
+
stats['untyped_functions'] += len(untyped)
|
|
44
|
+
|
|
45
|
+
# Count typed functions
|
|
46
|
+
typed = re.findall(r'function\s+\w+\s*\([^)]*\)\s*:\s*\w+', content)
|
|
47
|
+
typed += re.findall(r':\s*\([^)]*\)\s*=>\s*\w+', content)
|
|
48
|
+
stats['total_functions'] += len(typed) + len(untyped)
|
|
49
|
+
|
|
50
|
+
except Exception:
|
|
51
|
+
continue
|
|
52
|
+
|
|
53
|
+
# Analyze results
|
|
54
|
+
if stats['any_count'] == 0:
|
|
55
|
+
passed.append("[OK] No 'any' types found")
|
|
56
|
+
elif stats['any_count'] <= 5:
|
|
57
|
+
issues.append(f"[!] {stats['any_count']} 'any' types found (acceptable)")
|
|
58
|
+
else:
|
|
59
|
+
issues.append(f"[X] {stats['any_count']} 'any' types found (too many)")
|
|
60
|
+
|
|
61
|
+
if stats['total_functions'] > 0:
|
|
62
|
+
typed_ratio = (stats['total_functions'] - stats['untyped_functions']) / stats['total_functions'] * 100
|
|
63
|
+
if typed_ratio >= 80:
|
|
64
|
+
passed.append(f"[OK] Type coverage: {typed_ratio:.0f}%")
|
|
65
|
+
elif typed_ratio >= 50:
|
|
66
|
+
issues.append(f"[!] Type coverage: {typed_ratio:.0f}% (improve)")
|
|
67
|
+
else:
|
|
68
|
+
issues.append(f"[X] Type coverage: {typed_ratio:.0f}% (too low)")
|
|
69
|
+
|
|
70
|
+
passed.append(f"[OK] Analyzed {len(ts_files)} TypeScript files")
|
|
71
|
+
|
|
72
|
+
return {'type': 'typescript', 'files': len(ts_files), 'passed': passed, 'issues': issues, 'stats': stats}
|
|
73
|
+
|
|
74
|
+
def check_python_coverage(project_path: Path) -> dict:
|
|
75
|
+
"""Check Python type hints coverage."""
|
|
76
|
+
issues = []
|
|
77
|
+
passed = []
|
|
78
|
+
stats = {'untyped_functions': 0, 'typed_functions': 0, 'any_count': 0}
|
|
79
|
+
|
|
80
|
+
py_files = list(project_path.rglob("*.py"))
|
|
81
|
+
py_files = [f for f in py_files if not any(x in str(f) for x in ['venv', '__pycache__', '.git', 'node_modules'])]
|
|
82
|
+
|
|
83
|
+
if not py_files:
|
|
84
|
+
return {'type': 'python', 'files': 0, 'passed': [], 'issues': ["[!] No Python files found"], 'stats': stats}
|
|
85
|
+
|
|
86
|
+
for file_path in py_files[:30]: # Limit
|
|
87
|
+
try:
|
|
88
|
+
content = file_path.read_text(encoding='utf-8', errors='ignore')
|
|
89
|
+
|
|
90
|
+
# Count Any usage
|
|
91
|
+
any_matches = re.findall(r':\s*Any\b', content)
|
|
92
|
+
stats['any_count'] += len(any_matches)
|
|
93
|
+
|
|
94
|
+
# Find functions with type hints
|
|
95
|
+
typed_funcs = re.findall(r'def\s+\w+\s*\([^)]*:[^)]+\)', content)
|
|
96
|
+
typed_funcs += re.findall(r'def\s+\w+\s*\([^)]*\)\s*->', content)
|
|
97
|
+
stats['typed_functions'] += len(typed_funcs)
|
|
98
|
+
|
|
99
|
+
# Find functions without type hints
|
|
100
|
+
all_funcs = re.findall(r'def\s+\w+\s*\(', content)
|
|
101
|
+
stats['untyped_functions'] += len(all_funcs) - len(typed_funcs)
|
|
102
|
+
|
|
103
|
+
except Exception:
|
|
104
|
+
continue
|
|
105
|
+
|
|
106
|
+
total = stats['typed_functions'] + stats['untyped_functions']
|
|
107
|
+
|
|
108
|
+
if total > 0:
|
|
109
|
+
typed_ratio = stats['typed_functions'] / total * 100
|
|
110
|
+
if typed_ratio >= 70:
|
|
111
|
+
passed.append(f"[OK] Type hints coverage: {typed_ratio:.0f}%")
|
|
112
|
+
elif typed_ratio >= 40:
|
|
113
|
+
issues.append(f"[!] Type hints coverage: {typed_ratio:.0f}%")
|
|
114
|
+
else:
|
|
115
|
+
issues.append(f"[X] Type hints coverage: {typed_ratio:.0f}% (add type hints)")
|
|
116
|
+
|
|
117
|
+
if stats['any_count'] == 0:
|
|
118
|
+
passed.append("[OK] No 'Any' types found")
|
|
119
|
+
elif stats['any_count'] <= 3:
|
|
120
|
+
issues.append(f"[!] {stats['any_count']} 'Any' types found")
|
|
121
|
+
else:
|
|
122
|
+
issues.append(f"[X] {stats['any_count']} 'Any' types found")
|
|
123
|
+
|
|
124
|
+
passed.append(f"[OK] Analyzed {len(py_files)} Python files")
|
|
125
|
+
|
|
126
|
+
return {'type': 'python', 'files': len(py_files), 'passed': passed, 'issues': issues, 'stats': stats}
|
|
127
|
+
|
|
128
|
+
def main():
|
|
129
|
+
target = sys.argv[1] if len(sys.argv) > 1 else "."
|
|
130
|
+
project_path = Path(target)
|
|
131
|
+
|
|
132
|
+
print("\n" + "=" * 60)
|
|
133
|
+
print(" TYPE COVERAGE CHECKER")
|
|
134
|
+
print("=" * 60 + "\n")
|
|
135
|
+
|
|
136
|
+
results = []
|
|
137
|
+
|
|
138
|
+
# Check TypeScript
|
|
139
|
+
ts_result = check_typescript_coverage(project_path)
|
|
140
|
+
if ts_result['files'] > 0:
|
|
141
|
+
results.append(ts_result)
|
|
142
|
+
|
|
143
|
+
# Check Python
|
|
144
|
+
py_result = check_python_coverage(project_path)
|
|
145
|
+
if py_result['files'] > 0:
|
|
146
|
+
results.append(py_result)
|
|
147
|
+
|
|
148
|
+
if not results:
|
|
149
|
+
print("[!] No TypeScript or Python files found.")
|
|
150
|
+
sys.exit(0)
|
|
151
|
+
|
|
152
|
+
# Print results
|
|
153
|
+
critical_issues = 0
|
|
154
|
+
for result in results:
|
|
155
|
+
print(f"\n[{result['type'].upper()}]")
|
|
156
|
+
print("-" * 40)
|
|
157
|
+
for item in result['passed']:
|
|
158
|
+
print(f" {item}")
|
|
159
|
+
for item in result['issues']:
|
|
160
|
+
print(f" {item}")
|
|
161
|
+
if item.startswith("[X]"):
|
|
162
|
+
critical_issues += 1
|
|
163
|
+
|
|
164
|
+
print("\n" + "=" * 60)
|
|
165
|
+
if critical_issues == 0:
|
|
166
|
+
print("[OK] TYPE COVERAGE: ACCEPTABLE")
|
|
167
|
+
sys.exit(0)
|
|
168
|
+
else:
|
|
169
|
+
print(f"[X] TYPE COVERAGE: {critical_issues} critical issues")
|
|
170
|
+
sys.exit(1)
|
|
171
|
+
|
|
172
|
+
if __name__ == "__main__":
|
|
173
|
+
main()
|
|
@@ -0,0 +1,176 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: mcp-builder
|
|
3
|
+
description: MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
|
|
4
|
+
allowed-tools: Read, Write, Edit, Glob, Grep
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
# MCP Builder
|
|
8
|
+
|
|
9
|
+
> Principles for building MCP servers.
|
|
10
|
+
|
|
11
|
+
---
|
|
12
|
+
|
|
13
|
+
## 1. MCP Overview
|
|
14
|
+
|
|
15
|
+
### What is MCP?
|
|
16
|
+
|
|
17
|
+
Model Context Protocol - standard for connecting AI systems with external tools and data sources.
|
|
18
|
+
|
|
19
|
+
### Core Concepts
|
|
20
|
+
|
|
21
|
+
| Concept | Purpose |
|
|
22
|
+
|---------|---------|
|
|
23
|
+
| **Tools** | Functions AI can call |
|
|
24
|
+
| **Resources** | Data AI can read |
|
|
25
|
+
| **Prompts** | Pre-defined prompt templates |
|
|
26
|
+
|
|
27
|
+
---
|
|
28
|
+
|
|
29
|
+
## 2. Server Architecture
|
|
30
|
+
|
|
31
|
+
### Project Structure
|
|
32
|
+
|
|
33
|
+
```
|
|
34
|
+
my-mcp-server/
|
|
35
|
+
├── src/
|
|
36
|
+
│ └── index.ts # Main entry
|
|
37
|
+
├── package.json
|
|
38
|
+
└── tsconfig.json
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
### Transport Types
|
|
42
|
+
|
|
43
|
+
| Type | Use |
|
|
44
|
+
|------|-----|
|
|
45
|
+
| **Stdio** | Local, CLI-based |
|
|
46
|
+
| **SSE** | Web-based, streaming |
|
|
47
|
+
| **WebSocket** | Real-time, bidirectional |
|
|
48
|
+
|
|
49
|
+
---
|
|
50
|
+
|
|
51
|
+
## 3. Tool Design Principles
|
|
52
|
+
|
|
53
|
+
### Good Tool Design
|
|
54
|
+
|
|
55
|
+
| Principle | Description |
|
|
56
|
+
|-----------|-------------|
|
|
57
|
+
| Clear name | Action-oriented (get_weather, create_user) |
|
|
58
|
+
| Single purpose | One thing well |
|
|
59
|
+
| Validated input | Schema with types and descriptions |
|
|
60
|
+
| Structured output | Predictable response format |
|
|
61
|
+
|
|
62
|
+
### Input Schema Design
|
|
63
|
+
|
|
64
|
+
| Field | Required? |
|
|
65
|
+
|-------|-----------|
|
|
66
|
+
| Type | Yes - object |
|
|
67
|
+
| Properties | Define each param |
|
|
68
|
+
| Required | List mandatory params |
|
|
69
|
+
| Description | Human-readable |
|
|
70
|
+
|
|
71
|
+
---
|
|
72
|
+
|
|
73
|
+
## 4. Resource Patterns
|
|
74
|
+
|
|
75
|
+
### Resource Types
|
|
76
|
+
|
|
77
|
+
| Type | Use |
|
|
78
|
+
|------|-----|
|
|
79
|
+
| Static | Fixed data (config, docs) |
|
|
80
|
+
| Dynamic | Generated on request |
|
|
81
|
+
| Template | URI with parameters |
|
|
82
|
+
|
|
83
|
+
### URI Patterns
|
|
84
|
+
|
|
85
|
+
| Pattern | Example |
|
|
86
|
+
|---------|---------|
|
|
87
|
+
| Fixed | `docs://readme` |
|
|
88
|
+
| Parameterized | `users://{userId}` |
|
|
89
|
+
| Collection | `files://project/*` |
|
|
90
|
+
|
|
91
|
+
---
|
|
92
|
+
|
|
93
|
+
## 5. Error Handling
|
|
94
|
+
|
|
95
|
+
### Error Types
|
|
96
|
+
|
|
97
|
+
| Situation | Response |
|
|
98
|
+
|-----------|----------|
|
|
99
|
+
| Invalid params | Validation error message |
|
|
100
|
+
| Not found | Clear "not found" |
|
|
101
|
+
| Server error | Generic error, log details |
|
|
102
|
+
|
|
103
|
+
### Best Practices
|
|
104
|
+
|
|
105
|
+
- Return structured errors
|
|
106
|
+
- Don't expose internal details
|
|
107
|
+
- Log for debugging
|
|
108
|
+
- Provide actionable messages
|
|
109
|
+
|
|
110
|
+
---
|
|
111
|
+
|
|
112
|
+
## 6. Multimodal Handling
|
|
113
|
+
|
|
114
|
+
### Supported Types
|
|
115
|
+
|
|
116
|
+
| Type | Encoding |
|
|
117
|
+
|------|----------|
|
|
118
|
+
| Text | Plain text |
|
|
119
|
+
| Images | Base64 + MIME type |
|
|
120
|
+
| Files | Base64 + MIME type |
|
|
121
|
+
|
|
122
|
+
---
|
|
123
|
+
|
|
124
|
+
## 7. Security Principles
|
|
125
|
+
|
|
126
|
+
### Input Validation
|
|
127
|
+
|
|
128
|
+
- Validate all tool inputs
|
|
129
|
+
- Sanitize user-provided data
|
|
130
|
+
- Limit resource access
|
|
131
|
+
|
|
132
|
+
### API Keys
|
|
133
|
+
|
|
134
|
+
- Use environment variables
|
|
135
|
+
- Don't log secrets
|
|
136
|
+
- Validate permissions
|
|
137
|
+
|
|
138
|
+
---
|
|
139
|
+
|
|
140
|
+
## 8. Configuration
|
|
141
|
+
|
|
142
|
+
### Claude Desktop Config
|
|
143
|
+
|
|
144
|
+
| Field | Purpose |
|
|
145
|
+
|-------|---------|
|
|
146
|
+
| command | Executable to run |
|
|
147
|
+
| args | Command arguments |
|
|
148
|
+
| env | Environment variables |
|
|
149
|
+
|
|
150
|
+
---
|
|
151
|
+
|
|
152
|
+
## 9. Testing
|
|
153
|
+
|
|
154
|
+
### Test Categories
|
|
155
|
+
|
|
156
|
+
| Type | Focus |
|
|
157
|
+
|------|-------|
|
|
158
|
+
| Unit | Tool logic |
|
|
159
|
+
| Integration | Full server |
|
|
160
|
+
| Contract | Schema validation |
|
|
161
|
+
|
|
162
|
+
---
|
|
163
|
+
|
|
164
|
+
## 10. Best Practices Checklist
|
|
165
|
+
|
|
166
|
+
- [ ] Clear, action-oriented tool names
|
|
167
|
+
- [ ] Complete input schemas with descriptions
|
|
168
|
+
- [ ] Structured JSON output
|
|
169
|
+
- [ ] Error handling for all cases
|
|
170
|
+
- [ ] Input validation
|
|
171
|
+
- [ ] Environment-based configuration
|
|
172
|
+
- [ ] Logging for debugging
|
|
173
|
+
|
|
174
|
+
---
|
|
175
|
+
|
|
176
|
+
> **Remember:** MCP tools should be simple, focused, and well-documented. The AI relies on descriptions to use them correctly.
|
|
@@ -0,0 +1,129 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: "meta-prompt"
|
|
3
|
+
description: "Meta-prompting framework for critiquing responses, analyzing solution trajectories, and evaluating AI-generated content quality"
|
|
4
|
+
version: 1.0.0
|
|
5
|
+
category: build
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
# Meta-Prompt
|
|
9
|
+
|
|
10
|
+
A collection of meta-prompting techniques for evaluating and analyzing AI responses and solution paths.
|
|
11
|
+
|
|
12
|
+
## Response Quality Evaluator
|
|
13
|
+
|
|
14
|
+
A framework for critiquing and reflecting on the quality of responses, providing a score and indicating whether the response has fully solved the question or task.
|
|
15
|
+
|
|
16
|
+
### Evaluation Fields
|
|
17
|
+
|
|
18
|
+
**Reflections**: The critique and reflections on the sufficiency, superfluency, and general quality of the response.
|
|
19
|
+
|
|
20
|
+
**Score**: Score from 0-10 on the quality of the candidate response.
|
|
21
|
+
|
|
22
|
+
**Found_solution**: Whether the response has fully solved the question or task.
|
|
23
|
+
|
|
24
|
+
### Evaluation Criteria
|
|
25
|
+
|
|
26
|
+
When evaluating responses, consider the following:
|
|
27
|
+
|
|
28
|
+
1. **Accuracy**: Does the response correctly address the question or task?
|
|
29
|
+
2. **Completeness**: Does it cover all aspects of the question or task?
|
|
30
|
+
3. **Clarity**: Is the response clear and easy to understand?
|
|
31
|
+
4. **Conciseness**: Is the response appropriately concise without sacrificing important details?
|
|
32
|
+
5. **Relevance**: Does the response stay focused on the question or task at hand?
|
|
33
|
+
|
|
34
|
+
Provide thoughtful reflections on these aspects and any other relevant factors. Use the score to indicate the overall quality, and set found_solution to true only if the response fully addresses the question or completes the task.
|
|
35
|
+
|
|
36
|
+
### Example Usage
|
|
37
|
+
|
|
38
|
+
```
|
|
39
|
+
reflections: "The response was clear and concise, addressing the main question effectively. However, it could have provided more context on edge cases."
|
|
40
|
+
score: 8
|
|
41
|
+
found_solution: true
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
## Question-Answering Trajectory Analyzer
|
|
45
|
+
|
|
46
|
+
Guidelines for analyzing solution paths to question-answering tasks.
|
|
47
|
+
|
|
48
|
+
### Trajectory Components
|
|
49
|
+
|
|
50
|
+
**Observations**: Environmental information about the current situation that provides context for decision-making.
|
|
51
|
+
|
|
52
|
+
**Thoughts**: Reasoning about the current situation, analyzing what has been observed and planning next steps.
|
|
53
|
+
|
|
54
|
+
**Actions**: The steps taken to progress toward solving the task.
|
|
55
|
+
|
|
56
|
+
### Action Types
|
|
57
|
+
|
|
58
|
+
**Search[entity]**: Searches for the exact entity and returns relevant information if the entity exists. If not, returns suggestions for similar entities.
|
|
59
|
+
|
|
60
|
+
**Lookup[keyword]**: Returns the next relevant passage that contains the keyword. Used for finding specific information within retrieved content.
|
|
61
|
+
|
|
62
|
+
**Finish[answer]**: Returns the answer and finishes the task. Used when sufficient information has been gathered to provide a definitive response.
|
|
63
|
+
|
|
64
|
+
### Analysis Guidelines
|
|
65
|
+
|
|
66
|
+
When analyzing a trajectory:
|
|
67
|
+
|
|
68
|
+
1. Evaluate whether each observation provides useful information
|
|
69
|
+
2. Assess if thoughts demonstrate logical reasoning
|
|
70
|
+
3. Determine if actions are appropriate given the current state
|
|
71
|
+
4. Score the trajectory correctness from 1-10
|
|
72
|
+
5. Evaluate reasoning validity even in incomplete trajectories
|
|
73
|
+
6. Do not generate additional steps; only analyze what is provided
|
|
74
|
+
|
|
75
|
+
## Prompt Engineering Patterns
|
|
76
|
+
|
|
77
|
+
### Chain of Thought
|
|
78
|
+
|
|
79
|
+
Guide the model through step-by-step reasoning:
|
|
80
|
+
|
|
81
|
+
```
|
|
82
|
+
Let's approach this step by step:
|
|
83
|
+
1. First, identify the key components
|
|
84
|
+
2. Then, analyze each component
|
|
85
|
+
3. Finally, synthesize the findings
|
|
86
|
+
```
|
|
87
|
+
|
|
88
|
+
### Few-Shot Learning
|
|
89
|
+
|
|
90
|
+
Provide examples to establish the pattern:
|
|
91
|
+
|
|
92
|
+
```
|
|
93
|
+
Example 1: [input] -> [output]
|
|
94
|
+
Example 2: [input] -> [output]
|
|
95
|
+
Now apply this pattern to: [new input]
|
|
96
|
+
```
|
|
97
|
+
|
|
98
|
+
### Self-Consistency
|
|
99
|
+
|
|
100
|
+
Generate multiple reasoning paths and select the most consistent answer.
|
|
101
|
+
|
|
102
|
+
### Reflection Prompts
|
|
103
|
+
|
|
104
|
+
Encourage self-critique:
|
|
105
|
+
|
|
106
|
+
```
|
|
107
|
+
Review your response and identify:
|
|
108
|
+
- Any potential errors or oversights
|
|
109
|
+
- Areas that could be explained more clearly
|
|
110
|
+
- Missing information that would strengthen the answer
|
|
111
|
+
```
|
|
112
|
+
|
|
113
|
+
## Quality Metrics
|
|
114
|
+
|
|
115
|
+
### Response Scoring Rubric
|
|
116
|
+
|
|
117
|
+
- **10**: Perfect response, fully addresses all aspects with exceptional clarity
|
|
118
|
+
- **8-9**: Excellent response with minor room for improvement
|
|
119
|
+
- **6-7**: Good response that addresses the main points but lacks depth
|
|
120
|
+
- **4-5**: Adequate response with significant gaps or unclear explanations
|
|
121
|
+
- **2-3**: Poor response that misses key aspects or contains errors
|
|
122
|
+
- **0-1**: Response fails to address the question or is completely incorrect
|
|
123
|
+
|
|
124
|
+
### Trajectory Scoring
|
|
125
|
+
|
|
126
|
+
- **10**: Optimal path with efficient, logical steps
|
|
127
|
+
- **7-9**: Good path with minor inefficiencies
|
|
128
|
+
- **4-6**: Acceptable path but with unnecessary steps or missed opportunities
|
|
129
|
+
- **1-3**: Poor path with fundamental reasoning errors
|