3steps To Wisdom
v2.1.0A communication method enforcing three steps in every reply: think through goals and options, execute with command and result, then reflect on outcomes and l...
⭐ 0· 95·0 current·0 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 (three-step communication) match the SKILL.md: it only prescribes a Thinking → Execution → Reflection structure and references storing outputs in a memory palace. No unrelated binaries, credentials, or installs are requested.
Instruction Scope
The Execution step asks for 'command + result' and 'show the execution result' which can be interpreted as running commands or reporting results. That is coherent with a workflow that documents actions, but it is ambiguous: the agent may need to actually execute commands (if permitted) or should clearly indicate when results are hypothetical. Also the skill instructs automatically persisting outputs into a 'memory palace'—this is consistent with keeping records, but it implies use of the agent's memory/persistence mechanisms (not declared).
Install Mechanism
Instruction-only skill with no install spec and no code files. Lowest-risk install surface; nothing is written to disk or downloaded.
Credentials
No environment variables, credentials, or config paths are requested. The memory-persistence guidance is conceptual and not tied to any undeclared secret or external service.
Persistence & Privilege
The skill is not marked always:true and is user-invocable. However it instructs outputs be 'automatically' saved to memory categories; if installed, ensure you understand how the agent's memory feature is used and where those entries are stored, since the skill implicitly expects write-access to the agent's memory.
Assessment
This skill simply enforces a three-part reply format (thinking, execution, reflection) and is internally consistent. Before installing, decide if you want: 1) every agent reply to be verbose and structured that way; 2) the agent to execute commands when presenting 'command + result' (confirm your agent's shell/execution permissions); and 3) the outputs to be persisted in the agent's memory—check what memory is stored, how long it is kept, and whether it may include sensitive data. If you don't want automatic persistence or command execution, either disable those agent capabilities or ask for a clarification behavior (e.g., show hypothetical commands/results rather than actually running them).Like a lobster shell, security has layers — review code before you run it.
latestvk975mkqq25py7dnrpb5atdge4n83wxnv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.