ClawHub

Curse Of Knowledge Detector

v1.0.0

Diagnose a draft for the Curse of Knowledge — the expert blind spot that makes insiders write copy full of unexplained jargon, buried assumptions, strategy-l...

⭐ 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
Capability signals
Crypto
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 match the requested artifacts and behavior: it audits prose for jargon and buried assumptions. It requests only the draft and an audience baseline and does not ask for unrelated services, binaries, or credentials.
✓
Instruction Scope
SKILL.md instructs the agent to read a user-provided draft, ask for or construct a listener baseline, run a rubric-style audit, and produce flagged passages with rewrite guidance. It does not direct the agent to read unrelated system files, access environment variables, or transmit data to external endpoints.
✓
Install Mechanism
No install spec and no code files are present — it is instruction-only. That minimizes disk writes and arbitrary code execution risk.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. Requested permissions (ability to read a pasted file or document) are proportionate to auditing text.
✓
Persistence & Privilege
The skill is not always-enabled and does not request persistent privileges or to modify other skills or system-wide settings. It operates interactively on user-provided drafts.
Scan Findings in Context
[no-regex-findings] expected: The static scanner found nothing because this is an instruction-only skill with no code files; that absence is expected and consistent with the skill's design.
Assessment
This skill is coherent and low-risk: it only needs the text you give it and an audience description to run an audit. Before installing, confirm you are comfortable pasting any sensitive text (it will read whatever draft you provide), and be aware the skill diagnoses problems but does not rewrite end-to-end (you'll need a separate rewriting skill for that). If you care about provenance, you can review the linked GitHub homepage for authorship and license details.

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

auditvk972kmsbtdvtnmxrdk5tmtytxd84wfdfbookforgevk972kmsbtdvtnmxrdk5tmtytxd84wfdfclarityvk972kmsbtdvtnmxrdk5tmtytxd84wfdfcommunicationvk972kmsbtdvtnmxrdk5tmtytxd84wfdfcopywritingvk972kmsbtdvtnmxrdk5tmtytxd84wfdfdiagnosticvk972kmsbtdvtnmxrdk5tmtytxd84wfdfexpert-blind-spotvk972kmsbtdvtnmxrdk5tmtytxd84wfdfjargon-detectionvk972kmsbtdvtnmxrdk5tmtytxd84wfdflatestvk972kmsbtdvtnmxrdk5tmtytxd84wfdfmessagingvk972kmsbtdvtnmxrdk5tmtytxd84wfdfplain-languagevk972kmsbtdvtnmxrdk5tmtytxd84wfdfwritingvk972kmsbtdvtnmxrdk5tmtytxd84wfdf

License

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

Runtime requirements

📚 Clawdis

Comments