One closed-loop iteration on an open PR — read CI checks + bot and human review comments, triage against this repo's decision records, apply valid suggestions, reply with reasoning on rejected ones, push fixes as Conventional Commits, and report status. Invoke as `/pr-iterate <PR#>`. Compose with `/loop /pr-iterate <PR#>` for continuous monitoring until green.
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/pr-iterate/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a defensive PR-iteration loop with no malicious intent toward the user, but its disclosed lane step can land a PR via a base-branch command and its ruling defaults can pre-approve human-only outward items, both of which are risky even though governed by operator policy.
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 snapshot step lists PR inline, top-level, and review-body comments via `gh api` and fetches each body for a reader subagent, so outsider-authored GitHub PR comment text enters the workflow without the agent selecting a specific item.
agranado2k/agentic-sdlc
0f5671d
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.