ClawHub

Message Clinic Runner

v1.0.0

Run the full Made-to-Stick Idea Clinic on a draft message — diagnose it against SUCCESs, rewrite the weak dimensions, and ship a before/after pair with a one...

⭐ 0· 34·0 current·0 all-time
byHung Quoc To@quochungto
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 describe an end-to-end message rewrite workflow; the skill is instruction-only, requests no credentials or installs, and delegates SUCCESs-specific fixes to the listed foundation skills — this is proportional and expected for an orchestrator.
✓
Instruction Scope
Runtime instructions stick to the stated task: read a single user-supplied draft, require audience/goal/tone constraints, run the stickiness audit, invoke specific foundation skills only for flagged dimensions, and produce message-clinic-output.md. It does read/write the working directory (creates the output file and may reference stickiness-scorecard.md) which is appropriate for the workflow.
✓
Install Mechanism
No install spec and no code files — the skill is instruction-only. Nothing is downloaded or written to disk by an installer; lowest-risk install posture.
✓
Credentials
The skill declares no required environment variables, binaries, or credentials. It does rely on other in-agent foundation skills (listed in depends-on); those skills may have their own requirements, but nothing here asks for unrelated secrets or system access.
✓
Persistence & Privilege
always:false and user-invocable: true. The skill writes a single output file in the working directory but does not request permanent presence, nor does it modify other skills' configs. Autonomous invocation is allowed by platform default but is not combined with other high-privilege requests here.
Scan Findings in Context
[no_regex_findings] expected: The repo is instruction-only so the regex-based scanner had no code to analyze; this absence of findings is expected and not evidence of additional safety.
Assessment
This skill is an orchestrator that reads one user-supplied draft and writes message-clinic-output.md with a before/after plus audit trail; it does not request credentials or install software. Before enabling: (1) review the referenced foundation skills (stickiness-audit, core-message-extractor, etc.) because those downstream skills may have additional permissions or external calls, (2) avoid pasting secrets or sensitive PII into drafts you ask it to rewrite, (3) note that the agent will write output files to its working directory and may reference an existing stickiness scorecard, and (4) test with non-sensitive drafts to confirm the behavior and that brand/legal constraints are honored. If you need stronger guarantees (no file writes, no delegation), consider invoking lower-level foundation skills directly or restricting the agent's filesystem/network permissions.

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

before-aftervk977s663c4m64d866kdn1h633984x0srbookforgevk977s663c4m64d866kdn1h633984x0srclinicvk977s663c4m64d866kdn1h633984x0srcommunicationvk977s663c4m64d866kdn1h633984x0srcommunications-reviewvk977s663c4m64d866kdn1h633984x0srcopywritingvk977s663c4m64d866kdn1h633984x0srlatestvk977s663c4m64d866kdn1h633984x0srmessagingvk977s663c4m64d866kdn1h633984x0srorchestratorvk977s663c4m64d866kdn1h633984x0srrewritingvk977s663c4m64d866kdn1h633984x0srstickyvk977s663c4m64d866kdn1h633984x0srworkflowvk977s663c4m64d866kdn1h633984x0sr

License

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

Runtime requirements

📚 Clawdis

Comments