Shadows Project Architect

v1.1.0

Structured project planning — requirements analysis, architecture design, task breakdown, dependency mapping, milestone definition. Use when starting a new p...

0· 303·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name, description, and SKILL.md all describe structured project planning and the instructions implement that workflow. The skill requests no binaries, env vars, or config paths, which is proportionate for a purely advisory planning tool. Minor metadata inconsistency: SKILL.md includes an 'openclaw.homepage' URL while the registry metadata lists 'Homepage: none' — this is likely benign bookkeeping but worth noting.
Instruction Scope
SKILL.md confines the agent to asking questions, producing structured text (requirements, architecture, ADRs, task lists, critical path, milestones) and explicitly states it will not execute commands, read files, or make network calls. There are no instructions that reference system files, credentials, or external endpoints beyond an informational homepage URL in metadata.
Install Mechanism
No install spec and no code files — the skill is instruction-only. That is the lowest-risk install mechanism and matches the declared pure-advisory purpose.
Credentials
The skill requires no environment variables, credentials, or config paths. This is proportional to a planning/architect role; there are no unexplained secret requests or unrelated credential needs.
Persistence & Privilege
Flags show always:false and default autonomous invocation allowed (normal). The skill does not request permanent presence, nor does it instruct modifying agent/system configs. No elevated persistence or cross-skill config access is indicated.
Assessment
This skill is an instruction-only project-planning template and appears internally consistent and low-risk. Before installing: (1) confirm you won't paste any secrets or proprietary credentials into prompts (the skill may ask detailed project/context questions); (2) because it's purely advisory, review generated plans for accuracy and security implications before acting on them; (3) watch for future updates that add install scripts, network calls, or env-var requirements — those would materially change the risk profile.

Like a lobster shell, security has layers — review code before you run it.

latestvk977w8mxk8kd17jvtn47dd4dqd82fd3k

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

🏗️ Clawdis
OSmacOS · Linux · Windows

Comments