Trim SKILL.md description to fit 1024-char limit

The round-6 rewrite expanded the description past the validator ceiling (description must not exceed 1024 characters). Tightened the framing without losing the marketing punch, the convergence semantics correction, the trigger phrases, or the permission caveat.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: yeelam-gordon

skills/copilot-pr-autopilot/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: copilot-pr-autopilot
-description: 'Copilot just left 14 review comments on your PR — half are nits. You face hours of fix → reply → resolve → re-request review → repeat, and each re-request lands MORE comments. Up to 10 more rounds before Copilot finally shuts up. You are exhausted. Stop. This skill runs the whole loop for you: auto-triggers Copilot Code Review via GraphQL (no @copilot mention needed), triages every open thread (Copilot, humans, advanced-security) with a fix / decline / escalate rubric, dispatches parallel fix sub-agents that obey the repo build/test/lint conventions, commits one round per iteration, replies+resolves citing the pushed SHA, then re-triggers Copilot until HEAD is reviewed with zero threads awaiting the agent''s reply (any remaining open threads are explicit hand-offs to the human merge owner — escalated declines, design tradeoffs). You merge a clean PR; the bot ran the marathon. Use when Copilot left comments on your PR and you want them gone without babysitting. Trigger phrases: "address copilot comments", "run a copilot review loop", "fix this PR", "iterate on copilot feedback", "get this PR to green". Repo-agnostic, gh CLI + PowerShell. Full multi-round autopilot needs repo Triage/Write permission; external PR authors get single-iteration mode plus manual re-trigger (UI 🔄 or substantive-commit push).'
+description: 'Copilot left 14 review comments on your PR — half are nits. Hours of fix → reply → resolve → re-request, and each round lands MORE comments. This skill runs the whole loop: auto-triggers Copilot Code Review via GraphQL (no @copilot mention), triages every open thread (Copilot, humans, advanced-security) with a fix / decline / escalate rubric, dispatches parallel fix sub-agents that obey the repo build/test/lint conventions, commits per iteration, replies+resolves citing the pushed SHA, then re-triggers until HEAD is reviewed with zero threads awaiting the agent''s reply (remaining open threads are explicit hand-offs to the human merge owner — escalated declines, design tradeoffs). You merge a clean PR; the bot ran the marathon. Trigger phrases: "address copilot comments", "run a copilot review loop", "fix this PR", "iterate on copilot feedback", "get this PR to green". Repo-agnostic, gh CLI + PowerShell. Full autopilot needs repo Triage/Write; external PR authors get single-iteration mode plus manual re-trigger (UI 🔄 or substantive-commit push).'
 ---
 
 # Copilot PR Autopilot