ClawHub

Context Product Manager

v0.1.0

Turn rough product, feature, or repo-change requests into a PM-grade plan plus agent-ready execution context. Use whenever the user has a vague idea, wants a...

⭐ 1· 49·0 current·0 all-time
by@openclawzhu-ai
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 and description (turn ideas into PM-grade plans and coding-agent handoffs) align with the contents: the skill provides templates, an intake framework, and rendering rules. It does not request unrelated credentials, binaries, or system paths.
ℹ
Instruction Scope
SKILL.md explicitly instructs the agent to read repo/docs/code and to name the files inspected before producing outputs — this is coherent for a repo-aware PM skill but means the skill will access local workspace files. There are no instructions to contact external endpoints, request secrets, or exfiltrate data. Users should expect local file reads and explicit citations of which files were used.
✓
Install Mechanism
No install spec or code files are present; the skill is instruction-only, which keeps risk low (nothing is written to disk or downloaded during install).
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The behavior described (reading repository files, asking clarifying questions, producing templates) does not require additional secrets or external service access.
✓
Persistence & Privilege
Flags are default (always: false, user-invocable true, model invocation allowed), which is appropriate. The skill does not request permanent presence or attempt to modify other skills or system-wide settings.
Assessment
This skill is instruction-only and coherent with its purpose: it will read local repo/docs/code to produce a canonical context blueprint and target-specific handoffs, and will produce Chinese executive/design briefs and English agent handoffs. Before installing, confirm you are comfortable with the agent reading project files in the workspace (the skill will cite which files it inspected). No network endpoints, installs, or secrets are requested, but review any output before handing it to automated coding agents and ensure the language preferences (Chinese for conversation, English for handoffs) match your expectations.

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

latestvk971vba1c480c2dep6czfp3hy5842b8v

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments