Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and recoverable pipeline design.
72%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./skills/antigravity-agentflow/SKILL.mdThe skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The guide directs the agent-user to modify the host's crontab and copy files into the Claude Code config, which changes machine state, though it is tempered by repeated authorization and "preserve existing files" caveats.
The 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 required pipeline has workers read task descriptions and comments on the Kanban board (Asana, GitHub Projects, Linear), and an outsider who can comment on or create items in a monitored board can get text into the agent's context without the agent selecting a specific item.
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 skill instructs an inbound setup fetch of the individual-owned, unpinned GitHub repository UrRhb/agentflow (via `git clone` and `/plugin marketplace add`) and relies on its skills, prompts, and plugin material, which is unofficial community content without strong first-party provenance, so it is a medium-tier dependency.
boisenoise/skills-collections
6475104
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.