Configure development tasks, git hooks, CI/CD, or release automation. Use when creating or fixing a repository development workflow.
80%
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/oma-dev-workflow/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 release-coordination resource's `release:check` task runs `gh pr list`, which returns PR titles that outsiders can author, and `release:changelog` reads commit subjects from git history, so the agent ingests outsider-authored GitHub text when it runs these tasks; this is included under the recall-first override even though the label filter and merge gating limit who can get text into those lists.
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 CI workflow executes the GitHub Action `jdx/mise-action@v2`, an inbound remote repository whose content runs in the pipeline; it is owned by an individual maintainer (jdx) rather than a first-party organization, so it is common/reputable unofficial and rated medium, while the googleapis Release Please action and actions/checkout are official and excluded.
first-fluke/oh-my-agent
2bd468c
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.