Type-Based Autonomy
v1.0.0Type-based autonomous task queue system. Categorizes tasks by type (research, writing, analysis, maintenance) and lets autonomy work only on value-add tasks...
⭐ 0· 649·2 current·2 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (type-based autonomous queue) align with what the skill asks the agent to do: read tasks/QUEUE.md, filter by @type, pick work, log progress, and checkpoint context. No unexpected binaries, env vars, or external services are requested.
Instruction Scope
SKILL.md gives detailed runtime steps for reading/writing workspace files (tasks/QUEUE.md, memory/*, GOALS.md, .learnings/) and for checkpointing session context. This is coherent with autonomy but notable because the instructions explicitly tell the agent to persist decisions, context, and file states to disk (memory/episodic/[today].md, memory/[today].md). That can include preferences, decisions, and file references — potentially sensitive information. The skill does not instruct network exfiltration or require unrelated files, but it gives broad discretion to write and update project memory files.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute. This minimizes installation risk; nothing is downloaded or written by an installer.
Credentials
No environment variables, credentials, or config paths are required. All file paths referenced are project-local and consistent with the skill's function. No unrelated secrets are requested.
Persistence & Privilege
The skill is not always-enabled and uses normal autonomous invocation. It instructs the agent to create and update persistent memory/checkpoint files in the workspace, which is a legitimate autonomy need but increases the impact of any agent compromise because it persists conversational/contextual data. The skill does not modify other skills or system-wide settings.
Assessment
This skill is internally consistent and doesn't ask for credentials or external installs, but it explicitly instructs the agent to write checkpoints and logs with session context (decisions, preferences, file states) into workspace files (memory/…, .learnings/, GOALS.md). Before installing, verify where those memory files will reside and how they're protected (encryption, access controls, backups, retention policy). Consider: 1) running the skill in a sandboxed project to inspect what gets written, 2) adding rules to redact or exclude sensitive fields from automatic checkpoints, and 3) confirming the platform 'write' capability is intended and limited to the project workspace. Also confirm you accept the stated goal bias (tasks should support the agent's GOALS.md 'MONEY' objective) and that skipping security/backup tasks by autonomy is acceptable for your environment.Like a lobster shell, security has layers — review code before you run it.
latestvk976bm8346hprasf1s9mtzayrd818pve
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🏷️ Clawdis