本文へ移動
cccskills
無料GitHub で公開

post-merge-voice-gate

Post-merge paper-voice gate: inspect the reader-facing draft for planner-talk and axis-label artifacts, then route fixes to the actual source.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md4.6 KB
  • scripts/run.py8.5 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Post-merge Voice Gate

Triggers & routing

  • Trigger: post-merge voice gate, merge voice gate, transition leakage, planner talk, 合并后口吻门, 过渡句污染.
  • Use when: section-merger has produced output/DRAFT.md and you want to ensure merge-injected text won't drag the draft into generator voice before polishing.

Purpose: catch the highest-impact "automation tells" that appear after merge.

Why this exists:

  • Merge can expose planner-talk in section prose or explicitly enabled transitions.
  • Even a few planner-talk or axis-label sentences can make an otherwise solid draft read like a generator.
  • Fixes should land at the earliest responsible artifact: normally the owning section, or outline/transitions.md only when insertion was enabled.

This skill is a gate:

  • It writes a report (output/POST_MERGE_VOICE_REPORT.md).
  • If FAIL, it also appends to output/QUALITY_GATE.md so the workspace remains debuggable.

Role prompt: Voice Gatekeeper (paper voice, no new facts)

You are the post-merge voice gatekeeper for a survey draft.

Your job is to detect high-signal generator voice in the merged draft:
- planner-talk transitions ("To keep the chapter...", "The remaining uncertainty is...")
- slide/navigation narration ("Next, we move...", "We now turn...")
- axis-label slash lists (A / B / C; planning/memory) used as prose

Rules:
- do not change the draft directly; route fixes to the source file
- do not invent facts or citations
- keep fixes minimal and content-bearing (argument bridges, not navigation)

Output:
- a short PASS/FAIL report with a routing plan

Inputs

  • output/DRAFT.md
  • outline/transitions.md

outline/transitions.md is an optional planning artifact by default. It is treated as a possible reader-facing source only when outline/transitions.insert_h3.ok or outline/transitions.insert_h2.ok exists.

Output

  • output/POST_MERGE_VOICE_REPORT.md (always written)

What this gate checks (high-signal only)

  • Planner-talk transition stems (construction notes that read like comments in the paper body)
  • Slash-list axis markers in reader-facing draft prose (A / B / C)
  • Slide/navigation narration that should be argument bridges

Rewrite triggers (if you see these, FAIL and route)

These stems are high-signal generator voice once injected into the draft body:

  • "To keep ..." / "To keep the chapter..."
  • "The remaining uncertainty is ..."
  • "as the comparison lens" / "as the reference point"
  • slash-list axis labels using / (e.g., "retrieval / index / write policy")

Routing rules (earliest responsible artifact)

  • If transition insertion is enabled and the offending phrase appears in outline/transitions.md:
    • Fix: rerun transition-weaver (or hand-edit outline/transitions.md), then rerun section-merger.
  • Otherwise (phrase only appears in the draft body):
    • Fix: route to writer-selfloop / subsection-polisher / draft-polisher depending on where it occurs.

Mini rewrite examples (do not copy verbatim)

Bad (planner talk, reads like a build note):

  • To keep the chapter's comparison lens explicit, we now turn to ...

Better (argument bridge, content-bearing):

  • Once interface contracts fix what actions are executable, the next bottleneck is how agents choose among those actions under uncertainty and budget constraints.

Bad (axis-label slash list):

  • ... under mechanism/architecture/data trade-offs ...

Better (natural prose):

  • ... under trade-offs between architectural choices and the data/feedback available during interaction ...

Script (optional; deterministic gate)

Quick Start

  • uv run python .codex/skills/post-merge-voice-gate/scripts/run.py --workspace <workspace>

All Options

  • --workspace <dir>: workspace root
  • --unit-id <U###>: unit id (optional; for logs)
  • --inputs <semicolon-separated>: override inputs (rare; default: output/DRAFT.md;outline/transitions.md)
  • --outputs <semicolon-separated>: override outputs (rare; default: output/POST_MERGE_VOICE_REPORT.md)
  • --checkpoint <C#>: checkpoint id (optional; for logs)

Examples

  • Run right after section-merger (recommended):
    • uv run python .codex/skills/post-merge-voice-gate/scripts/run.py --workspace <workspace>

Notes

  • The script is analysis-only; it never edits content.
  • On FAIL it writes output/POST_MERGE_VOICE_REPORT.md and appends a short record to output/QUALITY_GATE.md.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Internal template for creating or refactoring a skill into the repository's reference-first shape. **Trigger**: reference-first template, blueprint skill, create a reusable skill, refactor a script-heavy skill. **Use when**: you need a lean `SKILL.md`, explicit `references/`, machine-readable `assets/`, and a minimal deterministic `run.py`.

日本語の概要は準備中です。原文の説明を表示しています。

WILLOSCAR/research-units-pipeline-skills5132026年10月5日 更新

Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.

日本語の概要は準備中です。原文の説明を表示しています。

WILLOSCAR/research-units-pipeline-skills5132026年10月5日 更新

Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.

日本語の概要は準備中です。原文の説明を表示しています。

WILLOSCAR/research-units-pipeline-skills5132026年10月5日 更新

Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.

日本語の概要は準備中です。原文の説明を表示しています。

WILLOSCAR/research-units-pipeline-skills5132026年10月5日 更新

Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.

日本語の概要は準備中です。原文の説明を表示しています。

WILLOSCAR/research-units-pipeline-skills5132026年10月5日 更新

Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing `output/CONTRACT_REPORT.md`; use for mid-Run coverage snapshots or final delivery completeness, not deep provenance integrity.

日本語の概要は準備中です。原文の説明を表示しています。

WILLOSCAR/research-units-pipeline-skills5132026年10月5日 更新

WILLOSCAR のスキルをすべて見る

このスキルの問題を報告する