portfolio-case-study-forge

v1.0.0

Turn rough project notes into polished portfolio case studies with metrics, visuals checklist, and interviewer talking points.

0· 183·0 current·0 all-time
byvx:17605205782@52yuanchangxing
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, SKILL.md workflow, resource template, and included helper script all align: they exist to structure project notes into case studies. The single dependency (python3) is reasonable for the bundled script and the functionality described.
Instruction Scope
SKILL.md confines the agent to asking for inputs, producing drafts/checklists/talking points, and using the local script/resource. It explicitly forbids fabricating metrics and recommends preview mode; there are no instructions to read unrelated system files, access secrets, or call external endpoints.
Install Mechanism
No install spec is provided (instruction-only with a local script), so nothing is downloaded or written to disk by an installer. The included script is small, plain-text, and auditable.
Credentials
No environment variables, credentials, or config paths are required. The skill does not request unrelated secrets or external API keys.
Persistence & Privilege
always:false (default) and no indications the skill modifies other skills or system-wide settings. The helper script writes a local JSON template file by default (args allow specifying output), which is normal and limited in scope.
Assessment
This skill appears coherent and low-risk: the helper script is small and local, there are no required credentials or remote installs, and the SKILL.md explicitly warns against fabricating metrics. Before installing or running: (1) inspect scripts/case_study_scaffold.py yourself (it's short and harmless); (2) run the helper with --help and use a non-privileged directory to test (it writes a JSON scaffold by default); (3) avoid pasting sensitive credentials or private data into prompts; and (4) if you later ask the agent to save, rename, or publish files, confirm those actions explicitly (the skill prefers preview/draft mode).

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

latestvk97a85x4dpqb2ncappsawn5he182vy9a

License

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

Runtime requirements

🧰 Clawdis
Binspython3

Comments