New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Weiping Wiki

by appleweiping in appleweiping/WEIPING_WIKI

Maintain and upgrade WEIPINGWIKI / Weiping Wiki as a durable knowledge system, whole-computer project map, and self-maintaining agent workflow.

MITAuto-check passedKnowledge Management

Install Weiping Wiki

skills CLI
$ npx skills add appleweiping/WEIPING_WIKI --skill weiping-wiki -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install appleweiping/WEIPING_WIKI weiping-wiki --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/vipin-wiki .claude/skills/weiping-wiki && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
weiping-wiki
GitHub stars
119
Token cost
~2.5k tokens
SKILL.md length
978 words
Files
8 (incl. references)
Skills in repo
51
Repo updated
First seen
Licence
MIT

At a glance

Maintain and upgrade WEIPINGWIKI / Weiping Wiki as a durable knowledge system, whole-computer project map, and self-maintaining agent workflow.

  • Works in 7 steps: Work from the repo root containing… → Run git status --short --branch;… → Read AGENTS.md, .wiki-schema.md, and… → …
  • Ingesting into the wiki
  • SKILL.md covers Mission, First Moves, Mode Router and Whole-Computer Depth, plus 4 more sections
  • Calls python and git

What it does

Weiping Wiki is an agent skill from appleweiping/WEIPING_WIKI. Maintain and upgrade WEIPINGWIKI / Weiping Wiki as a durable knowledge system, whole-computer project map, and self-maintaining agent workflow. Use for answering from or ingesting into the wiki, refreshing stale pages, weekly maintenance, C:/D:/G: project routing, public/private safety, index/log/catalog updates, automation validation, and skill self-upgrades. Also use for deep, low-coupling routes among D:/devtools, D:/devtools-public, D:/AGENTRESOURCE / D:/agent-resources, D:/AGENTICSCIENCE / UUPF…

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `agents/openai.yaml`, `references/maintenance-model.md` and `references/obsidian-compatibility.md`).

It sits in Knowledge Management. The repository describes itself as: knowledge base managed with an LLM workflow. The licence is MIT.

When your agent uses it

  • Ingesting into the wiki
  • Refreshing stale pages
  • Weekly maintenance
  • C:/D:/G: project routing

Example prompts

  • “/weiping-wiki”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Work from the repo root containing AGENTS.md, .wiki-schema.md, and purpose.md.
  2. Run git status --short --branch; preserve unrelated dirty work.
  3. Read AGENTS.md, .wiki-schema.md, and purpose.md before substantial maintenance, ingest, skill, script, automation, or operating-rule edits.
  4. For whole-computer/project routing, read wiki/concepts/whole-computer-project-map.md first, then wiki/concepts/d-drive-project-map.md…
  5. For interpretation or prioritization, read reader-context.md.
  6. Search active agentmemory when past state can affect the task.
  7. For deep maintenance of the agentic project constellation, inspect entry evidence for WEIPING_WIKI, D:/devtools, D:/devtools-public…

What it can do on your machine

Read from SKILL.md and the folder at commit 76fdc42. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Weiping Wiki loads about 2.5k tokens when it runs, and up to ~8.4k if it reads all its reference files. Until then it costs about 185 tokens; SKILL.md has 978 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~185
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from appleweiping/WEIPING_WIKI at commit 76fdc42, republished under its MIT licence (© appleweiping). 978 words, ~2,527 tokens.

Download SKILL.mdSave it as .claude/skills/weiping-wiki/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
weiping-wiki
description
Maintain and upgrade `WEIPING_WIKI` / `Weiping Wiki` as a durable knowledge system, whole-computer project map, and self-maintaining agent workflow. Use for answering from or ingesting into the wiki, refreshing stale pages, weekly maintenance, C:/D:/G: project routing, public/private safety, index/log/catalog updates, automation validation, and skill self-upgrades. Also use for deep, low-coupling routes among `D:/devtools`, `D:/devtools-public`, `D:/AGENT_RESOURCE` / `D:/agent-resources`, `D:/AGENTIC_SCIENCE` / UUPF, `D:/Research/WEIPING_LAB`, and `D:/Research/WEIPING_COUNCIL`. Historical aliases are `vipin wiki`, `vipinknowledge`, and `vipin-wiki`. Pair with `workstation-maintenance` for physical drive organization.

WEIPING_WIKI

Mission

Keep WEIPING_WIKI useful without a bespoke prompt. The system should answer from maintained knowledge, preserve reusable results, route future agents into the right local projects, and continuously improve its own workflow. Treat vipin wiki, vipinknowledge, and vipin-wiki as historical aliases.

First Moves

  1. Work from the repo root containing AGENTS.md, .wiki-schema.md, and purpose.md.
  2. Run git status --short --branch; preserve unrelated dirty work.
  3. Read AGENTS.md, .wiki-schema.md, and purpose.md before substantial maintenance, ingest, skill, script, automation, or operating-rule edits.
  4. For whole-computer/project routing, read wiki/concepts/whole-computer-project-map.md first, then wiki/concepts/d-drive-project-map.md, wiki/topics/local-active-project-roots.md, and wiki/topics/local-project-roots.md as needed.
  5. For interpretation or prioritization, read reader-context.md.
  6. Search active agentmemory when past state can affect the task.
  7. For deep maintenance of the agentic project constellation, inspect entry evidence for WEIPING_WIKI, D:/devtools, D:/devtools-public, D:/AGENT_RESOURCE / D:/agent-resources, D:/AGENTIC_SCIENCE, WEIPING_LAB, and WEIPING_COUNCIL before editing maps or automations.

Mode Router

  • Query: answer from wiki/index.md, wiki/catalog.json, python scripts/wiki.py search, and the smallest relevant maintained pages. Crystallize reusable answers.
  • Ingest: treat raw/ as immutable; create/update source notes, then propagate durable facts into concepts, entities, topics, analyses, index, log, and catalog.
  • Maintain: compare current pages to live evidence, stronger sources, and current rules. Update existing pages before creating duplicates. Propose deletions only after explicit user approval.
  • Whole-computer map: shallow-scan all drives, classify roots by importance, deep-read only important roots, and keep low-value/system/cache/download roots as brief bucket summaries.
  • Physical file organization: delegate manifests, full-plan, exact-batch, or D-root organization non-moving preflights, type-grouped age-gated move plans, approval packets, approved batch moves, D-root move-with-junction organization, and rollbacks to D:\agent-resources\skills\vipin\workstation-maintenance; this skill records only public-safe routing updates after dry-run evidence or actual changes. Broad user approval can cover all currently passing low-risk batches.
  • Obsidian compatibility: maintain .obsidian/, .base, .canvas, command-palette, template, dashboard, workspace, slide, backlink/search/outline/preview/tag/property/task/word-count, and wiki.py obsidian ... support so the repo works as a real local-first vault without depending on Obsidian's proprietary core.
  • Skill upgrade: when this skill feels prompt-dependent, misses a repeatable step, or fails validation, update the skill and references in the same scoped maintenance pass.
  • Automation run: use python scripts/wiki.py maintain --scope whole-computer --json as the canonical report, then make curated wiki/skill/doc updates only when evidence changed.
  • Agentic constellation maintenance: maintain tight routing links among WEIPING_WIKI, devtools, agent-resources, AGENTIC_SCIENCE/UUPF, WEIPING_LAB, and WEIPING_COUNCIL while forbidding high coupling. Public pages may describe roles, aliases, entry docs, handoff artifacts, optional environment variables, and validation commands; they must not make one repository require another repository's private state, runtime cache, secrets, local DBs, or generated reports to function.
  • LLM Wiki v2 toolset: wiki.py crystallize (durable page from an outcome), wiki.py lifecycle (advisory confidence/retention/supersession audit), wiki.py graph <stats|neighbors|path|export> (wiki-link traversal), wiki.py scrub (pre-ingest secret/private-path scan), health --fix (non-destructive self-heal), and search --graph / --semantic. All additive and public-safe. See [[llm-wiki]] and [[2026-06-19-weiping-wiki-upgrade-audit]].

Whole-Computer Depth

Use importance tiers before opening files:

TierQualifiesDepth
Tier 0WEIPING_WIKI, operating docs, skill roots, agentmemory, D:/devtools, D:/agent-resourcesDetailed routing, commands, safety gates, update rules, log/catalog/index changes
Tier 1Active research/product/app/game/health/company reposDedicated page or detailed section with purpose, root, status, entry docs, safety boundary
Tier 2Portfolio, coursework, study archives, old projects, media packagesPublic-safe summary and discovery clues
Tier 3OS folders, caches, downloads, binaries, package stores, temp dirsOne-line bucket summary; do not deep-read unless asked
Private/sensitiveCredentials, private chats/docs, account state, medical/financial recordsPrivate-only minimal metadata or no public record

Read references/whole-computer-depth.md before broad inventory or local organization work. Read the shared workstation-maintenance skill before any physical C:/D:/G: move plan or D-root organization plan.

Show full SKILL.md (404 more words)Show less

Recurring Maintenance

Default cadence is weekly Tuesday afternoon with gpt-5.5 and xhigh reasoning when the automation schema supports it. Automation may commit and push only after scoped curated changes and validation.

Run:

powershell
python scripts/wiki.py maintain --scope whole-computer --json
python scripts/wiki.py catalog
python scripts/wiki.py lint
python scripts/wiki.py health --json
powershell .\scripts\Test-PrePushSafety.ps1
git diff --check

Read references/weekly-maintenance-runbook.md for automation behavior and references/safety-and-automation.md for commit/push gates.

For deep infrastructure maintenance, also verify the current topology and entry evidence for:

  • D:/Research/WEIPING_WIKI and the compatibility junction D:/Research/vipin's knowledgebase
  • D:/devtools and D:/devtools-public
  • D:/AGENT_RESOURCE and the compatibility junction D:/agent-resources
  • D:/AGENTIC_SCIENCE, especially UUPF under uupf/UniversalUpgradeForge.zip
  • D:/Research/WEIPING_LAB and the compatibility junction D:/Research/vipin-lab
  • D:/Research/WEIPING_COUNCIL and the compatibility junction D:/Research/vipin-council

Read references/obsidian-compatibility.md before Obsidian-style vault, Bases, Canvas, backlink, search, quick-switcher, command-palette, outline, preview, footnote, tag, property, task, daily/unique note, template, slide, word-count, web-clip, or workspace upgrades.

Self-Upgrade Loop

Upgrade this skill when:

  • a user has to explain a workflow that should be automatic
  • a future agent would need to invent a prompt to maintain the wiki
  • a maintenance report shows repeated manual triage
  • validation, safety, or automation rules are stale
  • the whole-computer map gains a new important root or risk boundary
  • an important root needs better cross-project routing without adding runtime coupling

For major upgrades, use UUPF from D:/AGENTIC_SCIENCE/uupf/UniversalUpgradeForge.zip in offline mode first:

powershell
$env:PYTHONIOENCODING = "utf-8"
python -m uupgrade.cli doctor
python -m uupgrade.cli plan "<target-skill-or-doc-path>" --goal "<upgrade-goal>" --iterations 108 --output ".wiki-tmp/uupf-runs/<name>"
python -m uupgrade.cli upgrade "<target-skill-or-doc-path>" --goal "<upgrade-goal>" --iterations 108 --provider offline --output ".wiki-tmp/uupf-runs/<name>"

Treat UUPF reports as audit evidence and planning input. Do not publish raw generated run folders or claim that offline UUPF applied patches. Hand-apply only reviewed, source-grounded changes.

Keep SKILL.md compact. Put detailed procedures in references/, scripts in scripts/, and user-facing docs in wiki/. Regenerate/validate agents/openai.yaml when trigger wording changes. Read references/skill-upgrade-loop.md before editing this skill.

Safety Rules

  • Do not edit external projects during whole-computer maintenance; read only entry evidence unless the user explicitly asks for project work.
  • Do not physically move files during whole-computer maintenance unless a workstation-maintenance manifest and user-approved age-gated batch exists. For D-root directory organization, require a drive-root plan, non-moving preflight, and rollback-capable move-with-junction execution.
  • Never expose secrets, tokens, credentials, private chats, account state, sensitive documents, raw private material, logs, DBs, or bulky artifacts in public pages or Git.
  • Do not move, rewrite, or clean research experiment code, datasets, checkpoints, server logs, or result files during general wiki maintenance.
  • Keep reports in ignored .wiki-tmp/vipinknowledge-maintenance/ for historical compatibility; commit curated wiki/skill/script/doc changes only.
  • If validation fails, stop before commit/push and leave a clear report.

Canonical Outputs

  • Updated wiki pages with YAML frontmatter and confidence labels where useful.
  • Updated wiki/index.md, wiki/log.md, and wiki/catalog.json.
  • Scoped commits that exclude unrelated dirty work.
  • Agentmemory save for important decisions, findings, and next steps when available.

© appleweiping, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in .codex/skills/vipin-wiki of appleweiping/WEIPING_WIKI.

  • SKILL.md
  • agents/openai.yaml
  • references/maintenance-model.md
  • references/obsidian-compatibility.md
  • references/safety-and-automation.md
  • references/skill-upgrade-loop.md
  • references/weekly-maintenance-runbook.md
  • references/whole-computer-depth.md

Open the folder on GitHubat commit 76fdc42

Compare with similar skills

Weiping Wiki next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Weiping Wiki compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Weiping Wiki this skillappleweiping/WEIPING_WIKI119—~2.5kAutomated safety check: PassMIT
Logseq Review Workflow Evallogseq/logseq45k—~1kAutomated safety check: PassAGPL-3.0
Baoyu URL To Markdownsdyckjq-lab/llm-wiki-skill2.5k2 repos~3.2kAutomated safety check: PassNone
Obsidian CLIAtmosphere/atmosphere3.8k13 repos~795Automated safety check: PassApache-2.0
Esm Cjs Risk Scanlogseq/logseq45k—~3.3kAutomated safety check: PassAGPL-3.0
Knowledge Searchdataelement/bisheng12k—~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • Logseq Review Workflow Eval

    logseq/logseq

    Compare two revisions of the Logseq logseq-review-workflow skill by running the same review prompt against isolated before and after skill snapshots, collecting both outputs, and producing a…

    45k GitHub stars~1k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Baoyu URL To Markdown

    sdyckjq-lab/llm-wiki-skill

    Fetch any URL and convert to markdown using Chrome CDP. An agent skill from sdyckjq-lab/llm-wiki-skill.

    2.5k GitHub starsUsed in 2 repos~3.2k tokens
    Knowledge ManagementAuto-check passed

  • Obsidian CLI

    Atmosphere/atmosphere

    Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.

    3.8k GitHub starsUsed in 13 repos~795 tokens
    Knowledge ManagementAuto-check passed

  • Esm Cjs Risk Scan

    logseq/logseq

    Scan Logseq ClojureScript Node/Electron targets for npm module loading risks, especially ESM-only packages that may fail when loaded through js/require or shadow-cljs require-based shims.

    45k GitHub stars~3.3k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Knowledge Search

    dataelement/bisheng

    Search the user's knowledge bases and knowledge spaces (企业知识库检索).

    12k GitHub stars~1.1k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Capture Conversation

    outline/outline

    Save the current conversation, a decision, or a set of notes as a document in an Outline collection; use when the user wants to keep what was discussed in their knowledge base.

    41k GitHub stars~474 tokensUpdated today
    Knowledge ManagementAuto-check passed

More from appleweiping/WEIPING_WIKI

All 51 skills in this repo

  • Communication Assistant

    appleweiping/WEIPING_WIKI

    Unified lazy-mode communication assistant for Vipin across WhatsApp, WeChat, QQ, Feishu/Lark, and email.

    119 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Content Refinement Agent

    appleweiping/WEIPING_WIKI

    Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from appleweiping/WEIPING_WIKI.

    119 GitHub stars~3k tokensUpdated 1 mo ago
    Auto-check passed

  • Chrome Automation

    appleweiping/WEIPING_WIKI

    Connect to and control Google Chrome browser using agent-browser with CDP (Chrome DevTools Protocol).

    119 GitHub starsUsed in 1 repo~5.3k tokens
    Auto-check: warnings

  • Email Assistant

    appleweiping/WEIPING_WIKI

    Personal Gmail and Google Workspace email assistant for Vipin.

    119 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Wechat Video Channel Publish

    appleweiping/WEIPING_WIKI

    A skill your agent uses when the user wants to log into 微信视频号, validate cookie state, upload videos, set scheduled publish time, fill long description, set a cover image, or save drafts through a…

    119 GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed

  • Feishu Bridge

    appleweiping/WEIPING_WIKI

    Route Feishu/Lark content access for Codex. An agent skill from appleweiping/WEIPING_WIKI.

    119 GitHub stars~906 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Weiping Wiki

What does Weiping Wiki do?

Maintain and upgrade WEIPINGWIKI / Weiping Wiki as a durable knowledge system, whole-computer project map, and self-maintaining agent workflow. Weiping Wiki is an agent skill from appleweiping/WEIPING_WIKI. Maintain and upgrade WEIPINGWIKI / Weiping Wiki as a durable knowledge system, whole-computer project map, and self-maintaining agent workflow.

When should I use Weiping Wiki?

Weiping Wiki fits situations like: ingesting into the wiki; refreshing stale pages; weekly maintenance; C:/D:/G: project routing.

How do I install Weiping Wiki in Claude Code?

Run `npx skills add appleweiping/WEIPING_WIKI --skill weiping-wiki -a claude-code`. Or copy the skill folder (.codex/skills/vipin-wiki in appleweiping/WEIPING_WIKI) into .claude/skills/weiping-wiki in your project. Claude Code loads it when a task matches its description.

How do I install Weiping Wiki in Codex?

Run `npx skills add appleweiping/WEIPING_WIKI --skill weiping-wiki -a codex`. Or copy the skill folder (.codex/skills/vipin-wiki in appleweiping/WEIPING_WIKI) into .agents/skills/weiping-wiki in your project. Codex loads it when a task matches its description.

Can I use Weiping Wiki in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add appleweiping/WEIPING_WIKI --skill weiping-wiki -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/weiping-wiki, .gemini/skills/weiping-wiki, .github/skills/weiping-wiki and .opencode/skills/weiping-wiki in your project.

What does Weiping Wiki need to run?

Going by SKILL.md and its folder, Weiping Wiki needs the command-line tools its instructions call (python and git). Our summary lists: Python 3.

Does Weiping Wiki access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Weiping Wiki safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Weiping Wiki use?

Weiping Wiki is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Weiping Wiki use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.8k tokens, read only when the agent opens those files.

What are the alternatives to Weiping Wiki?

Skills that share tags, products or a category with Weiping Wiki: Logseq Review Workflow Eval (logseq/logseq, 45k stars), Baoyu URL To Markdown (sdyckjq-lab/llm-wiki-skill, 2.5k stars), Obsidian CLI (Atmosphere/atmosphere, 3.8k stars) and Esm Cjs Risk Scan (logseq/logseq, 45k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Weiping Wiki?

appleweiping (a GitHub user) maintains it in appleweiping/WEIPING_WIKI, which has 119 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on August 26, 2026.

Source: appleweiping/WEIPING_WIKI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.