Serially land a batch of green PRs through the forge's own merge API — migration-aware ordering, update-branch for stale PRs, wait for the post-merge workflows between merges, then run /worktree-cleanup. Invoke as `/merge-train` (discover all green PRs) or `/merge-train <PR#> [<PR#>…]` (explicit batch). Operator-invoked only; complements /pr-iterate, which never merges.
87%
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
Detected 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 documented, operator-invoked merge workflow with no malicious signs, but its single-retry rule for failed post-merge runs after a tag push could let a real base-branch failure be re-run past its red verdict, which is a risky weakening of a protection without malicious intent.
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 runs `gh pr list` in auto-discovery mode (step 1), which returns outsider-authored PR titles and branch names into the agent's context without the agent selecting a specific item, and those titles are reshown in the plan (step 3) and written into trace reasons (step 4).
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.