AgriciDaniel/claude-blog / skills/blog-notebooklm
blog-notebooklm
VerifiedQuery a user's Gemini Notebook (formerly NotebookLM) for source-grounded answers through a logged-in browser session on their Google account. Uses the account's usage limits and writes browser state. Runs only on an explicit request: /blog notebooklm, "ask my Gemini Notebook", "ask my NotebookLM notebook", or "query my notebook library". Also used by blog-write when the user named a notebook for research. Not for generic research or note-taking.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.3 KB |
| references/commands.md | markdown | 8.1 KB |
| references/troubleshooting.md | markdown | 6.6 KB |
| scripts/__init__.py | script | 605 B |
| scripts/ask_question.py | script | 11.1 KB |
| scripts/auth_manager.py | script | 14.0 KB |
| scripts/browser_session.py | script | 8.7 KB |
| scripts/browser_utils.py | script | 5.7 KB |
| scripts/cleanup_manager.py | script | 11.2 KB |
| scripts/config.py | script | 6.4 KB |
| scripts/notebook_manager.py | script | 15.9 KB |
| scripts/requirements.lock | other | 8.2 KB |
| scripts/requirements.txt | manifest | 609 B |
| scripts/run.py | script | 3.9 KB |
| scripts/runtime_paths.py | script | 2.6 KB |
| scripts/setup_environment.py | script | 12.1 KB |
scripts/runtime_paths.py
View on GitHub"""Read-only runtime path policy, shipped identically with each integration.
CLAUDE_BLOG_RUNTIME_DIR is an explicit trusted absolute operator/host path.
No override means the original skill-local .venv/data layout. Resolution never
creates directories, expands shell expressions or migrates existing state.
"""
import os
from pathlib import Path
import re
from typing import NamedTuple
class RuntimePaths(NamedTuple):
root: Path
venv: Path
data: Path
def validate_absolute_override(raw: str, path_type=Path):
"""Validate native Path semantics, including Windows drive/UNC anchors."""
if not raw or raw != raw.strip() or "\x00" in raw:
raise ValueError("CLAUDE_BLOG_RUNTIME_DIR must be a nonempty absolute path")
if "$" in raw or re.search(r"%[^%]+%", raw) or raw.startswith("~"):
raise ValueError("CLAUDE_BLOG_RUNTIME_DIR must be resolved, without shell or host placeholders")
path = path_type(raw)
if not path.is_absolute() or ".." in path.parts:
raise ValueError("CLAUDE_BLOG_RUNTIME_DIR must be absolute, without parent traversal")
return path
def confined_directory(root: Path, *parts: str) -> Path:
"""Refuse linked managed directories and paths outside the selected root."""
root = root.resolve()
path = root
for part in parts:
path = path / part
if path.is_symlink():
raise ValueError("runtime directory must not be a symlink")
try:
path.resolve().relative_to(root)
except ValueError as exc:
raise ValueError("runtime directory escapes its selected root") from exc
if path.exists() and not path.is_dir():
raise ValueError("runtime directory must be a directory")
return path
def resolve_runtime_paths(skill_dir: Path, integration: str) -> RuntimePaths:
"""Return consistent venv/data roots without any filesystem mutation."""
if integration not in ("blog-audio", "blog-google", "blog-notebooklm"):
raise ValueError("unknown runtime integration")
skill_dir = Path(skill_dir)
if not skill_dir.is_absolute():
raise ValueError("trusted installed skill path must be absolute")
raw = os.environ.get("CLAUDE_BLOG_RUNTIME_DIR")
if raw is None:
root = skill_dir.resolve()
else:
selected = validate_absolute_override(raw).resolve()
if selected.exists() and not selected.is_dir():
raise ValueError("CLAUDE_BLOG_RUNTIME_DIR must be a directory")
root = confined_directory(selected, integration)
return RuntimePaths(root, confined_directory(root, ".venv"), confined_directory(root, "data"))
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |