.agents/skills/doc-exec-log-append/SKILL.md
以 append-only 方式向执行台账追加记录,默认不回读历史正文,降低上下文污染。关键词:执行记录、台账追加、append-only、batch、不回读上下文。
npx skillsauth add w5851/Julia_RelaxTime doc-exec-log-appendInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
将“执行事实”以标准模板追加到执行台账末尾,且默认不读取台账历史内容,减少上下文污染并保持记录可追溯。
本 Skill 只处理“执行记录追加”,不负责开发任务定义、范围变更、DoD 设计。
默认协作行为:当 agent 在推进开发计划并产生可记录执行事实时,应自动触发本 Skill 追加台账;若目标台账不存在,先创建再追加。
当用户意图是以下之一时使用:
关键词:
doc-archive)。例外(仅以下情况允许读取台账):
最小输入字段:
log_file: 目标执行台账路径(通常在 docs/dev/active/)batch_id: 如 Batch N2goal: 本批次目标code_changes: 代码变更摘要validation_commands: 验证命令列表artifacts: 产物路径列表(如 outputs/results/...)result: 执行结果mainline: 主线映射(N1/N2/N3/N4)可选字段:
timestampnoteslog_file;task_file 自动推导同目录“执行台账”;docs/dev/active 最新“开发任务单”并推导。直接复制并填充:
{{cmd_1}}{{cmd_2}}{{artifact_1}}{{artifact_2}}本仓库已落地脚本:scripts/dev/append_exec_log.jl,用于统一执行追加:
--log-file 时,自动根据 --task-file 或 active 最新任务单推导台账路径;不存在则自动创建。这将“no read-back”从约定升级为可执行约束,降低人工偏差。
julia --project=. scripts/dev/append_exec_log.jl \
--log-file docs/dev/active/2026-02-26_多重派发重构与PNJL迁移下线执行台账.md \
--batch "Batch N2" \
--goal "移除旧入口并完成冒烟校验" \
--code-change "删除 src/pnjl 兼容路径调用点" \
--cmd "julia --project=. scripts/dev/run_prune_wave_gate.jl --base HEAD --head HEAD" \
--cmd "UNIT_PROFILE=smoke julia --project=. tests/unit/runtests.jl" \
--artifact "outputs/results/pnjl_prune_wave_snapshot_20260226_101500.txt" \
--result "通过" \
--mainline "N2"
development
Academic and technical writing style guidance focused on clarity, rigor, and human-like narrative flow. Use when drafting papers, polishing manuscripts, rewriting AI-like prose, or improving argument coherence and citation-aware structure.
tools
Prefer semantic symbol tools for precise navigation and refactoring. Use vscode_listCodeUsages and vscode_renameSymbol instead of grep-style text search when changing code symbols.
testing
Structured technical/theoretical research workflow for method selection, model comparison, and implementation-oriented conclusions with validation plans. Use when decisions must map literature evidence to concrete engineering or computational next steps.
testing
OpenAlex-focused scholarly retrieval skill for work/author/institution queries, citation trend snapshots, and topic-level evidence discovery. Use when you need structured literature discovery and bibliometric signals from OpenAlex.