ワンクリックで
forgejo-feedback-protocol
Process Forgejo PR feedback with reflection, guardrail-gap classification, and inline thread replies.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Process Forgejo PR feedback with reflection, guardrail-gap classification, and inline thread replies.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | forgejo-feedback-protocol |
| description | Process Forgejo PR feedback with reflection, guardrail-gap classification, and inline thread replies. |
Use this skill for every actionable PR review comment.
opencode-forgejo plugin's forgejo_pr_overview tool.guardrail-gap or one-off using review-taxonomy.Forgejo threads replies by review, path, and diff position. Prefer the opencode-forgejo plugin's forgejo_reply_inline_review tool. If you must fall back to the raw API, post to the existing review comments endpoint with:
{
"body": "<reply>",
"path": "<comment.path>",
"new_position": <comment.position>,
"old_position": 0
}
Begin the body with an @-mention of the original comment author, using @<comment.user.login>, so the reviewer being answered is notified and the thread remains attributable.
Do not use prose line numbers from the comment body as new_position.
Top-level PR comments are allowed only after all actionable inline threads have a per-thread response.
Fine-grained outside-in RED-GREEN-REFACTOR microcycles with specialist agents and single-diagnostic implementation.
UI-first BDD for event-model slices, RGR sequence, observed-failure evidence, drill-down unit tests, and non-behavioral exemptions for eddy.
Write implementation plans as test-addressed red-green-refactor cycles, with UI-first Cucumber REDs for event-model slices, rather than component waterfalls.
eddy Rust workspace conventions, Nix toolchain use, error handling, env parsing, tests, and docs coupling.
Event Modeling pattern advice; use when deciding whether something is an event, command, read model, state change, state view, automation, or translation.
Sandbox, LLM/tool trust boundaries, red-team tests, metrics/docs coupling, and threat-model update triggers.