Load when creating or editing any Markdown file or documentation HTML, such as README, DEVELOPMENT, architecture docs, reference docs, SKILL.md and AGENTS.md, and when rewriting or reviewing one.
72%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/docs-writing/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The rewrite workflow reads tracker issues and attachments and retained source links, which outsiders could author, but only when the agent selects a specific item to verify a claim or preserve evidence.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The only inbound operational dependency is the README install command `kendex add vanillagreencom/kendex --skill docs-writing`, which fetches installed skill material from a GitHub repository whose owner is the skill's named author and is not shown to be a recognized first-party vendor or an independently authenticated digest, so it is a common/reputable unofficial dependency (medium). The other URLs (SKILL.md metadata, documentation links, and the negative example's stylesheet) are static references or inert examples and fail the dependency gate.
vanillagreencom/kendex
3a2f84c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.