reset
Skill85 starsChanged 5 months agoMITView on GitHub
按 scope 重置 wiki 到干净 scaffold(wiki / raw / log / checkpoints / all)。适用于开发迭代或 setup 失败后的无痛重启。
- Reads credentials
Files
/reset
按 scope 重置 wiki 到干净 scaffold。设计目的是开发迭代和 setup 失败恢复 — 不是日常操作。
Trigger
手动:/reset --scope wiki / --scope raw / --scope log / --scope checkpoints / --scope all。可用逗号组合多个 scope:--scope wiki,log。
Inputs
--scope(必填):取值wiki— 删除wiki/<entity>/与wiki/outputs/下所有*.md,同时删除wiki/index.md、wiki/log.md和wiki/graph/下的文件。保留.gitkeep和wiki/CLAUDE.md。raw— 删除raw/papers/、raw/discovered/、raw/tmp/、raw/notes/、raw/web/下所有条目(保留.gitkeep)。log— 重置wiki/log.md为空模板。checkpoints— 通过research_wiki.py checkpoint-clear清除批处理状态。all— 以上全部。
Outputs
- 磁盘上清空 / 重置后的文件。
- 控制台摘要:已删除文件数、已重置文件数。
Wiki Interaction
读取
- 所有
wiki/<entity>/*.md(用于枚举删除清单)。 raw/<sub>/*(用于枚举 raw 删除清单)。
写入
- 删除
wiki/<entity>/*.md(保留.gitkeep)。 - 重写
wiki/index.md、wiki/graph/*,可选地重写wiki/log.md。 - 删除
raw/<sub>/*(保留.gitkeep)。
Workflow
前置条件:当前目录包含 wiki/、tools/。WIKI_ROOT=wiki/。
Step 1: 构造删除计划(dry-run)
python3 tools/reset_wiki.py --scope <scope>该命令打印 JSON 计划,列出将要删除或重置的全部文件,不修改任何东西。按 scope 分组展示给用户(wiki entity 目录、raw 子目录、log、checkpoints)。
Step 2: 与用户确认
打印计划摘要并请求显式确认:
About to delete N files and reset M files. Continue? [y/N]用户拒绝则退出。未经明确许可不得执行 — /reset 是破坏性操作,raw/ 的删除不可恢复。
Step 3: 执行
python3 tools/reset_wiki.py --scope <scope> --yes工具打印 JSON 状态报告({deleted_files, reset_files})。
Step 4: 记录日志(除非已重置 log)
若执行的 scope 不包含 log,追加一条日志:
python3 tools/research_wiki.py log wiki/ "reset | scope: <scope>"Step 5: 报告
打印结果并建议下一步:
## Reset complete — scope: <scope>
Deleted: N files
Reset: M files
Next steps:
- /init — 从 raw/ 引导 wiki
- /prefill — 沉淀基础背景知识
- /ingest — 手动添加单个来源Constraints
- 破坏性操作前必须确认:禁止在未展示计划并征得用户同意前调用
--yes。 - 保留:
.gitkeep占位、wiki/CLAUDE.md、.claude/(skill 永不被触碰)。 raw/删除不可逆:PDF 不在 git 中。执行raw或allscope 前必须警告用户。/reset不触碰tools/、mcp-servers/、i18n/、.env或 git 状态。- scope 必填:无默认行为(
/reset不带参数时提示用户选择 scope,而非猜测)。
Error Handling
- 未知 scope:列出有效 scope 并以非零退出码退出。
- wiki 目录缺失:报错并建议运行
/init。 checkpoint-clear失败:记录警告但不影响其他 scope。
Dependencies
工具(通过 Bash)
python3 tools/reset_wiki.py --scope <scope> [--yes] [--project-root .]— 确定性破坏性辅助工具python3 tools/research_wiki.py log wiki/ "<message>"— 追加日志reset_wiki.py在checkpointsscope 下直接删除wiki/.checkpoints/*.json(不走 CLI —checkpoint-clear子命令需指定具体的task_id,而/reset --scope checkpoints的语义是"全部清除")
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 4
- DAIR-AutoResearch/AutoSci★ 1.7k11% same
- PKU-DAIR/AutoSci★ 1.7k11% same
- skyllwt/AutoSci★ 1.7k11% same
- skyllwt/OmegaWiki★ 1.7k11% same
Wrote their own version · 11
- nykooi1/vibe-wise★ 3.5ksame name
- davekilleen/Dex★ 508same name
- oprogramadorreal/optimus-claude★ 75same name
- mlz11/ClaudeNotifier★ 36same name
- kennethleungty/claude-music★ 23same name
- winchxyz/idea-to-build★ 9same name
- Overdrive-Consulting/vc-fundraising-skill★ 4same name
- tjg37/ironclaw★ 1same name
- ozerova152-lab/youtube-producer★ 0same name
- petecurran/sorted★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use exp-pilot-eval, exp-pilot-run and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
DAIR-AutoResearchSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
DAIR-AutoResearchSkillexp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
phanghonghaoSkillposter
HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.
Also in 4 projects that use this
- +1 more from DAIR-AutoResearch
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- askSkill
- checkSkill
- daily-arxivSkill
- discoverSkill
- editSkill
- empirical-designSkill
- empirical-ingestSkill
- exp-designSkill
- exp-evalSkill
- exp-runSkill
- exp-statusSkill
- ideateSkill
- ingestSkill
- initSkill
- noveltySkill
- paper-compileSkill
- paper-draftSkill
- paper-planSkill
- prefillSkill
- rebuttalSkill
- refineSkill
- researchSkill
- reviewSkill
- setupSkill
- stata-planSkill
- surveySkill
- theory-ingestSkill
- variable-mapSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

