Decompose a PRD issue into tracer-bullet tickets — demoable vertical slices sized to one fresh context window, with blocking edges and HITL/AFK labels, published as GitHub sub-issues. Use after /to-prd when a build spans more than one session; skip it (use /implement directly) when the whole change fits one context window.
93%
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
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 workflow reads a PRD GitHub issue body (step 1, "issue body or conversation spec"), and the skill itself flags that body as untrusted, so outsider-authored text reaches the agent without a specific item being selected; the conversation-spec alternative makes it ambiguous, so I score up under the recall-first rule.
agranado2k/ai-report-platform
caeb0da
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.