Agent skill

Weiping Council

by appleweiping in appleweiping/WEIPING_COUNCIL

A skill your agent uses for reproducing, maintaining, monitoring, releasing, or upgrading the WEIPINGCOUNCIL project.

MITAuto-check: notesAgent Workflows

Install Weiping Council

skills CLI
$ npx skills add appleweiping/WEIPING_COUNCIL --skill weiping-council -a claude-code

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

GitHub CLI
$ gh skill install appleweiping/WEIPING_COUNCIL weiping-council --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_COUNCIL.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/weiping-council .claude/skills/weiping-council && 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-council
GitHub stars
133
Token cost
~1.9k tokens
SKILL.md length
852 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses for reproducing, maintaining, monitoring, releasing, or upgrading the WEIPINGCOUNCIL project.

  • Works in 8 steps: Plan → Design → Develop → …
  • Upgrading the WEIPINGCOUNCIL project
  • SKILL.md covers Mission, Lifecycle Workflow, Neighbor Project Boundaries and Review Gate
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Weiping Council is an agent skill from appleweiping/WEIPING_COUNCIL. Use this skill for reproducing, maintaining, monitoring, releasing, or upgrading the WEIPINGCOUNCIL project. It enforces the full lifecycle path from planning through design, development, testing, release, maintenance, monitoring, and continuous upgrade against real open-source quality bars.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. The repository describes itself as: Multi-LLM deliberation system with 6 protocols: council, debate, red-team, consensus, specialist, tournament. The licence is MIT.

When your agent uses it

  • Upgrading the WEIPINGCOUNCIL project

Example prompts

  • “/weiping-council”

Workflow steps

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

  1. Plan
  2. Design
  3. Develop
  4. Test
  5. Release
  6. Maintain
  7. Monitor
  8. Upgrade Iteration

What it can do on your machine

Read from SKILL.md and the folder at commit 4dfbe00. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    Links to these hosts (documentation or services it may open):

    • registry.npmjs.org

    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 Council loads about 1.9k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 852 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:27
    rtifact formats are acceptable; private `.env` files, local DBs, caches, generated reports, and active services are not.
  • NoteMentions a .env fileSKILL.md:31
    - `backend/runtime.py` for env and `.env` loading, provider readiness, CORS origins, and trace primitives.
  • NoteMentions a .env fileSKILL.md:41
    arent directories for another project's `.env`.

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_COUNCIL at commit 4dfbe00, republished under its MIT licence (© appleweiping). 852 words, ~1,857 tokens.

Download SKILL.mdSave it as .claude/skills/weiping-council/SKILL.md (or your agent's skills folder).
name
weiping-council
description
Use this skill for reproducing, maintaining, monitoring, releasing, or upgrading the WEIPING_COUNCIL project. It enforces the full lifecycle path from planning through design, development, testing, release, maintenance, monitoring, and continuous upgrade against real open-source quality bars.

WEIPING_COUNCIL Project Skill

Use this skill whenever work touches WEIPING_COUNCIL behavior, configuration, docs, release process, tests, UI, CLI, provider routing, memory integration, or project quality. Legacy references to vipin-council or Vipin Council are compatibility aliases unless the surrounding text is historical release context.

Mission

Weiping Council is an honest multi-model deliberation runtime. It must be useful when fully configured and truthful when degraded. It must never fake model success, hide provider assumptions, leak credentials, expose private endpoints in public health surfaces, or depend on retired local coordination paths.

Lifecycle Workflow

  1. Plan

    • Read AGENTS.md, README.md, CLAUDE.md, pyproject.toml, backend/config.py, backend/runtime.py, and the latest file under docs/releases/.
    • Define a version-level change. Do not spend a release on small isolated fixes.
    • Write or update a plan under docs/superpowers/plans/ before broad changes.
  2. Design

    • Keep provider identity separate from council member identity.
    • Prefer OpenAI-compatible provider support by default, with Anthropic format as an explicit per-role option.
    • Health and runtime evidence may expose readiness, source labels, missing field names, attempts, latency, and error classes. They must not expose API keys, raw provider URLs, local private endpoints, prompts from private memory, or raw exception messages containing secrets.
    • Treat agentmemory as optional but observable. If recall is unavailable for a run, the run is degraded.
    • CORS must be explicit and local-first by default, never wildcard by default.
    • Keep cross-project links low-coupling: route maps, optional context variables, validation commands, and artifact formats are acceptable; private .env files, local DBs, caches, generated reports, and active services are not.
  3. Develop

    • Backend source of truth:
      • backend/runtime.py for env and .env loading, provider readiness, CORS origins, and trace primitives.
      • backend/providers/router.py for provider calls and per-run traces.
      • backend/council/orchestrator.py for routing, context injection, protocol execution, refinement, metrics, warnings, and degraded state.
      • backend/session_store.py for atomic session persistence and corruption-tolerant reads.
      • backend/main.py for FastAPI contracts.
    • CLI source of truth: vc.py.
    • UI source of truth: frontend/src/components/ChatPane.jsx and frontend/src/components/ResultView.jsx.
    • Use .env.example for safe examples only. Never place real-looking sk-... values in source or docs.
  4. Test

    • Tests must be hermetic. Use explicit env={} or an explicit temporary dotenv_path; never let ambient machine credentials decide test results. Runtime loading must never search parent directories for another project's .env.
    • Cover missing credentials, transient and permanent provider failures, redaction, agentmemory unavailable behavior, explicit protocol fidelity, auto routing, atomic session storage, malformed artifacts, unique member IDs, per-session traces, concurrent session isolation, CLI status formatting, and frontend build.
    • Required local gate:
      powershell
      .\.venv\Scripts\python.exe -m pytest -q
      .\.venv\Scripts\python.exe -m ruff check .
      .\.venv\Scripts\python.exe scripts\release_scan.py
      Push-Location frontend
      npm run build
      npm audit --audit-level=low --registry=https://registry.npmjs.org
      Pop-Location
    • The release scan must return no real secrets, operator-specific private paths, or retired active-coordination dependencies.
  5. Release

    • Bump APP_VERSION, pyproject.toml, and frontend/package*.json together.
    • Add release notes under docs/releases/.
    • Update README.md with current configuration, health semantics, verification, monitoring, and troubleshooting.
    • Keep LICENSE and .github/workflows/ci.yml aligned with the local gate.
    • Commit and push the project repo after a passing gate and review score of 10/10.
  6. Maintain

    • Keep docs, .env.example, tests, and UI aligned with actual runtime behavior.
    • Remove compatibility shims when they become misleading.
    • Protect existing user changes and generated local files. Do not stage .venv, node_modules, dist, session data, or egg-info artifacts.
  7. Monitor

    • Level 1: GET /api/health returns backend availability plus redacted provider and agentmemory readiness.
    • Level 2: GET /api/models confirms member identity and configured provider model names.
    • Level 3: a deterministic /api/query smoke prompt validates routing, provider call, trace capture, and persisted session JSON.
    • Degraded is a real state, not a connection failure.
    • If /api/query returns fast_path or standard_path, that is a routing decision and must be reflected honestly in the API response and saved session JSON.
  8. Upgrade Iteration

    • Before major upgrades, compare current behavior with active open-source agent/runtime projects such as CrewAI, LangGraph, Open WebUI, LiteLLM, AutoGen/Microsoft Agent Framework, and OpenAI-compatible UI/proxy projects.
    • Import patterns only when they fit this project: provider abstraction, monitoring clarity, real examples, reproducible install, plugin surfaces, telemetry transparency, or safer local defaults.
    • Prefer original modules that make Weiping Council better at deliberation honesty: per-call evidence, dissent preservation, reviewer scoring, protocol traces, and reproducible quality gates.
Show full SKILL.md (178 more words)Show less

Neighbor Project Boundaries

  • deepseek-cli is a terminal-first DeepSeek client and may be used as an optional provider source, but Weiping Council must work with any OpenAI-compatible provider.
  • WEIPING_LAB is the broader workbench/lab layer. Weiping Council can export inspectable session JSON for it, but should not import lab-specific state into the core runtime.
  • WEIPING_WIKI is the public route map and durable operating context, not a runtime dependency.
  • Council handoff artifacts are data/sessions/<uuid>.json files with id, query, protocol, created_at, stages, final_answer, confidence, dissent, audit_trail, routing, metrics, provider_health, model_call_traces, degraded, and warnings.
  • Shared memory is agentmemory; do not revive retired local mailbox or markdown memory dependencies.

Review Gate

After a complete version-level batch is implemented and locally verified, use independent review agents for strict scoring. Required dimensions:

  • honesty and safety
  • architecture and concurrency
  • provider compatibility and degraded behavior
  • CLI/UI usability
  • documentation and onboarding
  • tests and release reproducibility
  • monitoring and maintenance story
  • relationship to deepseek-cli and WEIPING_LAB

Do not request a score while still actively editing the batch. If any reviewer returns less than 10/10, treat every blocker as mandatory and iterate.

© 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

Just SKILL.md in .codex/skills/weiping-council of appleweiping/WEIPING_COUNCIL.

Open the folder on GitHubat commit 4dfbe00

Compare with similar skills

Weiping Council 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 Council compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Weiping Council this skillappleweiping/WEIPING_COUNCIL133—~1.9kAutomated safety check: NotesMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k10 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k36 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT
Skill CreatorAzure/azqr79689 repos~8.2kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 10 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes
  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 36 repos~1.4k tokens
    Agent WorkflowsAuto-check passed
  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    796 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

Categories

Questions about Weiping Council

What does Weiping Council do?

A skill your agent uses for reproducing, maintaining, monitoring, releasing, or upgrading the WEIPINGCOUNCIL project. Weiping Council is an agent skill from appleweiping/WEIPING_COUNCIL. Use this skill for reproducing, maintaining, monitoring, releasing, or upgrading the WEIPINGCOUNCIL project.

When should I use Weiping Council?

Weiping Council fits situations like: upgrading the WEIPINGCOUNCIL project.

How do I install Weiping Council in Claude Code?

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

How do I install Weiping Council in Codex?

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

Can I use Weiping Council 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_COUNCIL --skill weiping-council -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-council, .gemini/skills/weiping-council, .github/skills/weiping-council and .opencode/skills/weiping-council in your project.

What does Weiping Council need to run?

SKILL.md names no scripts, command-line tools or credentials: Weiping Council is instructions for the agent only.

Does Weiping Council access the network?

SKILL.md names 1 domain. As links in the text: registry.npmjs.org. This is read from the text; nothing was executed.

Is Weiping Council safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Weiping Council use?

Weiping Council 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 Council use?

About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Weiping Council?

Skills that share tags, products or a category with Weiping Council: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Weiping Council?

appleweiping (a GitHub user) maintains it in appleweiping/WEIPING_COUNCIL, which has 133 GitHub stars. The repository was last updated on August 28, 2026.

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