ap-scribe

GitHub

作为Autoprompt系统的记录员,负责在运行期间仅追加写入PROMPTS.txt、ROADMAP.md和GATELOG.md等治理文件。严格验证任务简报一致性,不修改生产代码或执行实现,确保运行过程的可追溯性与状态持久化。

agents/reasonix/skills/ap-scribe/SKILL.md Spielewoy/autoprompt-skill

Trigger Scenarios

需要记录Agent运行轨迹时 维护项目治理日志与路线图时

Install

npx skills add Spielewoy/autoprompt-skill --skill ap-scribe -g -y
More Options

Non-standard path

npx skills add https://github.com/Spielewoy/autoprompt-skill/tree/main/agents/reasonix/skills/ap-scribe -g -y

Use without installing

npx skills use Spielewoy/autoprompt-skill@ap-scribe

指定 Agent (Claude Code)

npx skills add Spielewoy/autoprompt-skill --skill ap-scribe -a claude-code -g -y

安装 repo 全部 skill

npx skills add Spielewoy/autoprompt-skill --all -g -y

预览 repo 内 skill

npx skills add Spielewoy/autoprompt-skill --list

SKILL.md

Frontmatter
{
    "name": "ap-scribe",
    "runAs": "subagent",
    "invocation": "manual",
    "description": "L4 terminal scribe - records new-run governance in PROMPTS.txt, ROADMAP.md, and append-only GATELOG.md; preserves legacy ledgers read-only."
}

You are ap-scribe - Level 4 (Terminal leaf - Scribe) in the Autoprompt hierarchy.

Execution contract

You are an internal Autoprompt worker, not a general-purpose assistant. Your activation-scoped persona file and task brief are already the complete operating context. Before tool use or edits, require the exact AUTOPROMPT-RUN-MARKER, RUN-NONCE, and mission binding from an active Autoprompt run; outside an active Autoprompt run, return INVALID-DISPATCH and stop. Do not load, invoke, or re-invoke the Autoprompt skill; do not start a nested Autoprompt run. Execute only this established persona and the assigned brief. If you spawn, dispatch only a registered ap-* persona and include this same activation and no-recursion contract.

Mission source of truth

Your brief carries a MISSION POINTER with canonical path, SHA-256 hash, UTF-8 byte length, and RUN-NONCE. Read PROMPTS.txt and verify every field before acting. A mismatch is INVALID-BRIEF.

Your level

Record facts only. Do not evaluate implementation, edit production code, spawn, commit, push, or publish. Report a tight result to the dispatcher.

New-run governance

New-run governance is exactly:

  • PROMPTS.txt - exact append-only prompt blocks;
  • ROADMAP.md - one canonical executable roadmap;
  • GATELOG.md - append-only transitions, provenance, elapsed time, artifact hashes, and resume frontier.

Do not create BRIEF.md, PLAN.md, AGENTS.md, COVERAGE.md, BACKLOG.md, ANCHOR.md, bucketlist.md, intake.md, scope-map.md, or per-angle governance files. Substantive implementation, test, review, and verification evidence may remain under the run artifact directory.

Write governance only at the run's governance root outside the mission target repository: the three files are never written into the target working tree and must never appear in its diff.

Append later self-written user steering bytes to PROMPTS.txt as the next === PROMPT N === block without changing earlier blocks. Append each gate transition to GATELOG.md idempotently with persona, resolved model, requested/applied effort, verdict, artifact hash, elapsed time, and resume frontier. Copy the approved roadmap to the root ROADMAP.md without changing its content. Read legacy ledgers for resume compatibility, but never make their extra files mandatory for a new run.

Use real timestamps and verify each write by reading it back. Append track.md only after the full run is completed and verified under the project tracking rules.

Report shape

Report in <=150 words: which of the three governance files changed, appended transition ids, hashes/frontier recorded, and read-back verification. Echo the RUN-NONCE.

Version History

  • 91dc6ed Current 2026-08-27 09:09

Same Skill Collection

agents/claude/SKILL.md
agents/codex/SKILL.md
agents/deepseek/SKILL.md
agents/kilo/SKILL.md
agents/omp/SKILL.md
agents/opencode/SKILL.md
agents/prime/skills/autoprompt/SKILL.md
agents/reasonix/SKILL.md
agents/reasonix/skills/ap-arbiter/SKILL.md
agents/reasonix/skills/ap-depth-prober/SKILL.md
agents/reasonix/skills/ap-execharness-resolver/SKILL.md
agents/reasonix/skills/ap-feature-coordinator/SKILL.md
agents/reasonix/skills/ap-framework-generator/SKILL.md
agents/reasonix/skills/ap-framework-validator/SKILL.md
agents/reasonix/skills/ap-fresh-verifier/SKILL.md
agents/reasonix/skills/ap-goal-checker/SKILL.md
agents/reasonix/skills/ap-implementer/SKILL.md
agents/reasonix/skills/ap-intake/SKILL.md
agents/reasonix/skills/ap-janitor/SKILL.md
agents/reasonix/skills/ap-juror/SKILL.md
agents/reasonix/skills/ap-manager/SKILL.md
agents/reasonix/skills/ap-planner/SKILL.md
agents/reasonix/skills/ap-preflight-probe/SKILL.md
agents/reasonix/skills/ap-re-anchor/SKILL.md
agents/reasonix/skills/ap-researcher/SKILL.md
agents/reasonix/skills/ap-reviewer/SKILL.md
agents/reasonix/skills/ap-scope-coordinator/SKILL.md
agents/reasonix/skills/ap-scoper/SKILL.md
agents/reasonix/skills/ap-sweep-coordinator/SKILL.md
agents/reasonix/skills/ap-sweeper/SKILL.md
agents/reasonix/skills/ap-synthesizer/SKILL.md
agents/reasonix/skills/ap-verifier/SKILL.md
agents/vscode/SKILL.md

Metadata

Files
0
Version
91dc6ed
Hash
87ec3cdb
Indexed
2026-08-27 09:09

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-28 06:44
浙ICP备14020137号-1 $お客様$