ClawHub

Sticky Message Antipattern Detector

v1.0.0

Scan a draft, pitch, or copy for the named failure modes that kill stickiness — buried leads, decision paralysis, common-sense sedation, semantic stretch, st...

⭐ 0· 33·0 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
Capability signals
CryptoCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name, description, and SKILL.md all describe a copy/pitch diagnostic. The skill declares no binaries, no environment variables, and no installs — all appropriate for a text-audit detector. The required tools (Read, Write, optional Grep) are reasonable for locating and annotating passages in user-supplied drafts.
ℹ
Instruction Scope
SKILL.md confines work to user-provided drafts and audience profiles and specifies producing a flagged-passage report (diagnosis, not rewrite). It requires a readable draft and audience context. Minor caveat: the execution environment lists file read/write tools; while the skill's instructions do not ask for system files or secrets, an agent with broad filesystem permissions could read other files if misused. The skill itself does not instruct that behavior.
✓
Install Mechanism
No install spec and no code files are present (instruction-only). This is the lowest-risk install posture — nothing is downloaded or written by the skill itself.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. All declared inputs are sensible (document + audience profile) and proportional to the stated task.
✓
Persistence & Privilege
always:false and disable-model-invocation:false (normal). The skill does not request persistent system presence, modify other skills, or require elevated privileges. Autonomous invocation is allowed by default but is not combined with other concerning capabilities.
Assessment
This skill appears coherent and limited to auditing user-provided prose. Before installing, consider: (1) Only provide the draft text and audience info needed for diagnosis — avoid pasting passwords, private secrets, or sensitive PII. (2) Prefer pasting the draft rather than giving the agent broad filesystem access; if the agent must read files, restrict its working directory or explicitly confirm which file. (3) Check the GitHub homepage/source if provenance matters (the registry points to a public repo). (4) Remember the skill diagnoses problems but does not rewrite — request the rewrite separately if desired.

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

anti-patternvk97cjww88bc2rhhp4n5phvwzn984w73qauditvk97cjww88bc2rhhp4n5phvwzn984w73qbookforgevk97cjww88bc2rhhp4n5phvwzn984w73qcommunicationvk97cjww88bc2rhhp4n5phvwzn984w73qcopywritingvk97cjww88bc2rhhp4n5phvwzn984w73qdiagnosticvk97cjww88bc2rhhp4n5phvwzn984w73qeditingvk97cjww88bc2rhhp4n5phvwzn984w73qlatestvk97cjww88bc2rhhp4n5phvwzn984w73qmarketingvk97cjww88bc2rhhp4n5phvwzn984w73qmessagingvk97cjww88bc2rhhp4n5phvwzn984w73qpersuasionvk97cjww88bc2rhhp4n5phvwzn984w73qwritingvk97cjww88bc2rhhp4n5phvwzn984w73q

License

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

Runtime requirements

📚 Clawdis

Comments