Address Copilot round 7: regenerate README.skills.md + fix oscillation anchor

- docs/README.skills.md: regenerated via 'npm run build' so the copilot-pr-autopilot row uses the trimmed description (zero-threads-awaiting-reply wording, not the old zero-open-Copilot-threads claim). The earlier rebuild ran against the pre-trim description and left the row out of sync with SKILL.md.

- references/09-convergence.md:60: the link target '04-triage.md#oscillation-handling' did not resolve — 04-triage.md has no heading by that slug. Repointed to the actual section header anchor '#conflicting-comments--break-oscillation-early', which is the canonical oscillation handling location in that doc.

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

Author: yeelam-gordon

docs/README.skills.md

@@ -98,7 +98,7 @@ See [CONTRIBUTING.md](../CONTRIBUTING.md#adding-skills) for guidelines on how to
 | [convert-plaintext-to-md](../skills/convert-plaintext-to-md/SKILL.md)<br />`gh skills install github/awesome-copilot convert-plaintext-to-md` | Convert a text-based document to markdown following instructions from prompt, or if a documented option is passed, follow the instructions for that option. | None |
 | [copilot-cli-quickstart](../skills/copilot-cli-quickstart/SKILL.md)<br />`gh skills install github/awesome-copilot copilot-cli-quickstart` | Use this skill when someone wants to learn GitHub Copilot CLI from scratch. Offers interactive step-by-step tutorials with separate Developer and Non-Developer tracks, plus on-demand Q&A. Just say "start tutorial" or ask a question! Note: This skill targets GitHub Copilot CLI specifically and uses CLI-specific tools (ask_user, sql, fetch_copilot_cli_documentation). | None |
 | [copilot-instructions-blueprint-generator](../skills/copilot-instructions-blueprint-generator/SKILL.md)<br />`gh skills install github/awesome-copilot copilot-instructions-blueprint-generator` | Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files that guide GitHub Copilot to produce code consistent with project standards, architecture patterns, and exact technology versions by analyzing existing codebase patterns and avoiding assumptions. | None |
-| [copilot-pr-autopilot](../skills/copilot-pr-autopilot/SKILL.md)<br />`gh skills install github/awesome-copilot copilot-pr-autopilot` | 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 open Copilot threads. 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. | `references/02-wait.md`<br />`references/03-list-threads.md`<br />`references/04-triage.md`<br />`references/05-fix.md`<br />`references/06-build-test.md`<br />`references/08-reply-resolve.md`<br />`references/09-convergence.md`<br />`references/api-quirks.md`<br />`references/orchestration.md`<br />`scripts/01-request-review.ps1`<br />`scripts/02-check-review-status.ps1`<br />`scripts/03-list-open-threads.ps1`<br />`scripts/08-reply-and-resolve.ps1`<br />`scripts/10-cleanup-outdated.ps1`<br />`scripts/_lib.ps1`<br />`templates` |
+| [copilot-pr-autopilot](../skills/copilot-pr-autopilot/SKILL.md)<br />`gh skills install github/awesome-copilot copilot-pr-autopilot` | 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 — escalated declines, design tradeoffs). You merge a clean PR; the bot runs it. Trigger phrases: "address copilot comments", "run a copilot review loop", "fix this PR", "iterate on copilot feedback". 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). | `references/02-wait.md`<br />`references/03-list-threads.md`<br />`references/04-triage.md`<br />`references/05-fix.md`<br />`references/06-build-test.md`<br />`references/08-reply-resolve.md`<br />`references/09-convergence.md`<br />`references/api-quirks.md`<br />`references/orchestration.md`<br />`scripts/01-request-review.ps1`<br />`scripts/02-check-review-status.ps1`<br />`scripts/03-list-open-threads.ps1`<br />`scripts/08-reply-and-resolve.ps1`<br />`scripts/10-cleanup-outdated.ps1`<br />`scripts/_lib.ps1`<br />`templates` |
 | [copilot-sdk](../skills/copilot-sdk/SKILL.md)<br />`gh skills install github/awesome-copilot copilot-sdk` | Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent. | None |
 | [copilot-spaces](../skills/copilot-spaces/SKILL.md)<br />`gh skills install github/awesome-copilot copilot-spaces` | Use Copilot Spaces to provide project-specific context to conversations. Use this skill when users mention a "Copilot space", want to load context from a shared knowledge base, discover available spaces, or ask questions grounded in curated project documentation, code, and instructions. | None |
 | [copilot-usage-metrics](../skills/copilot-usage-metrics/SKILL.md)<br />`gh skills install github/awesome-copilot copilot-usage-metrics` | Retrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI and REST API. | `get-enterprise-metrics.sh`<br />`get-enterprise-user-metrics.sh`<br />`get-org-metrics.sh`<br />`get-org-user-metrics.sh` |

skills/copilot-pr-autopilot/references/09-convergence.md

@@ -57,7 +57,7 @@ only when Copilot has nothing new to say AND every open thread has a
 reply from the agent. There is no "max rounds" cap built into the
 scripts — the parent agent SHOULD apply a sane cap (e.g., 10 rounds)
 and escalate to the user if the loop is oscillating (same finding
-re-raised across rounds — see [04-triage.md#oscillation-handling]).
+re-raised across rounds — see [04-triage.md](04-triage.md#conflicting-comments--break-oscillation-early)).
 
 `-SingleIteration` mode is the **one** exception: by definition, it
 runs one round only (the trigger path is unavailable), and the