writing-clearly-and-concisely
Verdict safe, but 1 finding (1 low), mainly policy violation. Most recent scan 2026-02-08.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.
- Package
- 8 files, 174 KB
- SKILL.md
- 483 words, 9 sections
- Code
- None. Instructions only.
SKILL.md covers: Writing Clearly and Concisely · Overview · When to Use This Skill · Limited Context Strategy · Elements of Style · Rules · Reference Files · AI Writing Patterns to Avoid · Bottom Line
Findings
LOW Skill does not specify a license Policy Violationstatic
Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.
SKILL.md
What is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 5.9 KB |
SKILL.md | doc | 3.7 KB |
signs-of-ai-writing.md | doc | 93 KB |
elements-of-style/01-introductory.md | doc | 303 B |
elements-of-style/02-elementary-rules-of-usage.md | doc | 12 KB |
elements-of-style/03-elementary-principles-of-composition.md | doc | 33 KB |
elements-of-style/04-a-few-matters-of-form.md | doc | 4.8 KB |
elements-of-style/05-words-and-expressions-commonly-misused.md | doc | 22 KB |
External hosts referenced
en.wikipedia.org arxiv.org aclanthology.org consciouscreativity.com doi.org github.com pubmed.ncbi.nlm.nih.gov www.gutenberg.org citer.toolforge.org cloud.google.com en.wiktionary.org journals.sfu.ca klasresearch.com phabricator.wikimedia.org sociologicalscience.com upload.wikimedia.org wellington.scoop.co.nz www.chronicle.com www.imdb.com www.laetusinpraesens.org www.maly.ru www.nytimes.com www.prnewswire.com www.science.org www.theguardian.com www.washingtonpost.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22 at commit b00cf8491de1. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/softaworks/agent-toolkit
- Raw scan result: writing-clearly-and-concisely-scan.json
- Badge for your README:
- Request a re-scan