con un clic
pr-readiness
Final PR readiness gate after fix loops, merges, and manual debugging.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Final PR readiness gate after fix loops, merges, and manual debugging.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Investigate GitHub pull request review comments, determine whether each comment is valid, propose fixes, and document the analysis in an active samocode session. Use when the user asks to analyze PR comments, run /prcomments, investigate review feedback, or triage pull request comments.
Run OpenAI Codex CLI as a subagent for second opinions, code reviews, and questions. Use when you want a different AI model's perspective.
Run Anthropic Claude CLI as a subagent for second opinions, code reviews, and questions. Use from a Codex (or other) session when you want Claude's perspective.
Create GitHub PR review comments from review findings. Use after running a code review to post findings as line-bound comments.
Execute implementation tasks with different approaches (single, dual-agent, plan-based).
Create implementation plans with phase management.
| name | pr-readiness |
| description | Final PR readiness gate after fix loops, merges, and manual debugging. |
Review final HEAD after implementation, fix loops, merges, and manual debugging. This is a gate, not a general brainstorming review: pass only when important issues are fixed, explicitly deferred, or rejected with evidence.
_overview.mdHEAD; do not rely on earlier review summaries aloneScope: $ARGUMENTS (or current branch vs origin/main if not specified)
Resolve final scope:
HEADgit diff origin/main...HEAD unless $ARGUMENTS names a PR, branch, or explicit diff rangeLoad review debt:
_review_debt.md in the active session path when known; otherwise use the invocation directoryDecision is undecideddefer row missing a ticket/link or concrete owner/reasonreject row missing evidenceHEAD; reopen the row if the claimed fix is absentInspect final HEAD for high-risk surfaces: Focus on changed files that are shared, public, background, or cross-boundary:
avoncoreRun deterministic checks:
avoncore promotion requires 2+ current Python service consumers; frontend mirrors do not countgather, task creation, loops over user data, and missing durable retry assumptionsWalk feature edge cases when applicable:
Produce gate result: Use this format:
# PR Readiness Gate
Scope: [branch/range/PR]
HEAD: [sha]
## Result
PASS | FAIL
## Blocking Readiness Issues
- [issue, evidence, required action]
## Important Open Issues
- [issue, evidence, required decision/fix]
## Review Debt Ledger
- [rows checked, rows updated, unresolved rows]
## Checks Run
- [deterministic checks and targeted tests/commands]
## Residual Risk
- [known accepted risks with ticket/evidence]
Fail if any of these are true:
_review_debt.md has open important rows without a valid fix/defer/reject decisionHEAD introduces a new important issue in a shared/public module, background job, controller/service/repository boundary, concurrency/fan-out path, queue/DB consistency path, or config/default sourcePass only when all important issues are fixed, explicitly deferred, or rejected with evidence, and final HEAD has been checked after the last merge/fix/debug loop.