SkillAtlasSkill 详情

anth-upgrade-migration

A model-agnostic agent-skills platform.

审核状态:已审核Quality 72Security 70

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年9月2日

Tons of Skills

A model-agnostic agent-skills platform. The canonical layer is harness-free by construction; Claude Code is currently the verified-native harness. Other harnesses remain engineering candidates until their native-path integration is verified; source research alone is never presented as public support.

Release CLI Plugins Skills GitHub Stars skills.sh Sponsor: Kobiton Buy me a monster

ko-fi

Version semantics: the release badge is this marketplace's display version. npm packages, including the ccpi CLI and publishable plugins, retain their own package versions; they are intentionally not expected to equal the display version. The version-surface checker governs the display surfaces without rewriting package semver.

Install

Inside Claude Code, one command installs the whole marketplace:

/plugin marketplace add jeremylongshore/claude-code-plugins

Or use the CLI:

pnpm add -g @intentsolutionsio/ccpi
ccpi install devops-automation-pack

Browse the marketplace · Explore plugins · Download bundles

Killer Skill of the Week — no-ai-slop by Peter Yang

Strip AI slop from any draft — named-pattern edits that keep the writer's real voice

no-ai-slop does two jobs and refuses to fake a third. In Edit mode it makes the minimum effective edit — cutting throat-clearing, weak verbs, and abstract nouns while deliberately preserving the writer's cadence, bluntness, humor, and honest admissions, so a rough draft still sounds like the same person afterward. In Detect mode it names each AI-slop pattern it finds, quotes the offending line, and gives the fix in a few words — and pointedly does NOT score the draft or guess whether an AI wrote it. That restraint is the whole point: AI detectors guess; named patterns are evidence the reader can check. MIT-licensed, single focused skill, actively maintained by Peter Yang.

"AI detectors guess. Named patterns are evidence the user can check." — Peter Yang

Grade: A | Week of July 22, 2026 (W30) | View on GitHub

Previous picks: tonone, mnemos, databricks-pack, kobiton-automate, code-cleanup, web-analytics, token-optimizer, executive-assistant-skills, skill-creator, cursor-pack, crypto-portfolio-tracker. See all at tonsofskills.com.

Scale, labeled

Every number below names the cohort it counts and the command that reproduces it — an unlabeled count is how a corpus ends up with five contradictory answers to "how many skills."

CountCohortReproduce with
440catalog plugins (catalog-entry cohort)node scripts/generate-readme-toc.mjs over marketplace.extended.json
2,984marketplace-visible skills (distinct)node -e "import('./scripts/corpus-resolver.mjs').then(m=>console.log(m.resolveCorpus('marketplace-visible').length))"
347agent definitions in pluginsgit ls-files 'plugins/**' | grep '/agents/.*\.md'
19plugin categoriesls -d plugins/*/

📦 Live npm Downloads

Across 396 published packages in the claude-code-plugins namespace. Updated daily by GitHub Actions.

WindowAll packagesEstablished (>30d)
Last 24 hours962962
Last 7 days2,9202,916
Last 30 days12,86812,779

"Established" excludes packages first published within the last 30 days, so a bulk-publish event doesn't dominate the headline.

Top 10 by last 30 days:

#PackageLast 30d
1@intentsolutionsio/openrouter-pack556
2@intentsolutionsio/groq-pack496
3@intentsolutionsio/databricks-pack274
4@intentsolutionsio/clickhouse-pack273
5@intentsolutionsio/wallet-security-auditor263
6@intentsolutionsio/notion-pack258
7@intentsolutionsio/elevenlabs-pack244
8@intentsolutionsio/freshie-inventory-manager214
9@intentsolutionsio/supabase-pack210
10@intentsolutionsio/agency-os204

Last refreshed 2026-08-19T03:03:05.709Z.

Ways in

Five real questions, five doors — each resolves to a live, generated surface, never a hand-maintained list:

Browse by category

The 19 categories below link into the live marketplace. Plugin counts are the catalog-entry cohort — regenerated from marketplace.extended.json by this generator; the catalog itself lives on tonsofskills.com, never in this file (§ 6A of the platform blueprint).

CategoryPlugins
🤖AI & Machine Learning37
🎭AI Agents & Agency9
🔌API Development26
💼Business Tools6
👥Community20
₿Crypto & Web327
💾Database26
🎨Design2
🔧DevOps & Infrastructure36
📚Examples & Templates5
🧩MCP Servers17
📦Packages5
⚡Performance25
✅Productivity29
🎁SaaS Skill Packs105
🔐Security27
✨Skill Enhancers9
🧪Testing28
📁Analytics1

What the classes mean

Four artifact classes live in this repository, distinguished on sight and never blurred — provenance is a truth requirement here, not a UX nicety:

ClassWhat it isHow the reader can tell
Canonical skillFirst-party, harness-free, the source of truthNo .source.json in its plugin directory
Generated adapterA thin, machine-produced harness projectionLives under a generated path with a "generated — do not edit" header
First-party packageAn Intent Solutions distribution (npm, cowork zip)@intentsolutionsio scope, IS-authored license
Upstream mirrorSomebody else's work, hosted mirror-by-default.source.json present — upstream author, license, and pinned commit recorded

Certification

Not yet certified. The certification program (tiers T0–T4 with retained, hash-matched evidence) is a later epic of the platform blueprint; until its report exists, no artifact on this surface claims a tier. This line is rendered from the absence of certification-report.json — honestly, not cosmetically.

Contribute

Start with the contribution guide, then the intake and review standards every submission passes through:

Governance

Provenance

External plugins are hosted mirror-by-default: the contributor's repository stays the source of truth, every mirrored source is pinned in a content lockfile, and upstream credit — author, license, resolved commit — is recorded in the mirror itself. Improvements flow by upstreaming to the author's repository, never by silently editing the mirror. The full decision record is the external-sync model.

License

MIT for the repository scaffolding and first-party tooling; each plugin carries its own license in its manifest, and mirrored plugins keep their upstream license verbatim.

其他

中风险

  • 来源需自行核对维护者身份。
  • 包含脚本或命令调用,安装前请复核。
  • 可能需要外部 token、网络权限或第三方服务。
  • 未检测到高风险命令。
  • 扫描发现:3 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/anth-upgrade-migration" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/anth-upgrade-migration" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/anth-upgrade-migration" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/anth-upgrade-migration" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/anth-upgrade-migration" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: anth-upgrade-migration
description: 'Upgrade Anthropic SDK versions and migrate between Claude API versions.

  Use when upgrading the Python/TypeScript SDK, migrating from Text Completions

  to Messages API, or adopting new API features like tool use or batches.

  Trigger with phrases like "upgrade anthropic sdk", "anthropic migration",

  "update claude sdk", "migrate to messages api".

  '
allowed-tools: Read, Write, Edit, Bash(npm:*), Bash(pip:*), Bash(git:*)
version: 1.6.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- ai
- anthropic
compatibility: Designed for Claude Code

Anthropic Upgrade & Migration

Overview

Guide for upgrading the Anthropic SDK and migrating between API versions. The SDK follows semver — major versions may have breaking changes.

Check Current Versions

# Python
pip show anthropic | grep Version
# Version: 0.40.0

# TypeScript
npm list @anthropic-ai/sdk
# @anthropic-ai/sdk@0.35.0

# Check latest available
pip index versions anthropic 2>/dev/null | head -1
npm view @anthropic-ai/sdk version

Upgrade Path

Step 1: Create Upgrade Branch

git checkout -b upgrade/anthropic-sdk

Step 2: Upgrade SDK

# Python
pip install --upgrade anthropic
pip show anthropic | grep Version

# TypeScript
npm install @anthropic-ai/sdk@latest

Step 3: Review Breaking Changes

Key breaking changes by version:

Python SDK 0.20+ (anthropic-version: 2023-06-01)

# OLD: Text Completions API (deprecated)
response = client.completions.create(
    model="claude-2",
    prompt="\n\nHuman: Hello\n\nAssistant:",
    max_tokens_to_sample=256
)

# NEW: Messages API
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=256,
    messages=[{"role": "user", "content": "Hello"}]
)

Python SDK 0.30+ (streaming changes)

# OLD: Manual SSE parsing
response = client.messages.create(..., stream=True)
for line in response.iter_lines():
    ...

# NEW: High-level streaming
with client.messages.stream(...) as stream:
    for text in stream.text_stream:
        print(text)

TypeScript SDK 0.20+ (import path change)

// OLD
import Anthropic from 'anthropic';

// NEW
import Anthropic from '@anthropic-ai/sdk';

Step 4: Update API Version Header

# The SDK sends anthropic-version header automatically
# To pin a specific version:
client = anthropic.Anthropic(
    default_headers={"anthropic-version": "2023-06-01"}
)

# For beta features:
client = anthropic.Anthropic(
    default_headers={"anthropic-beta": "token-counting-2024-11-01"}
)

Step 5: Run Tests and Verify

# Run your test suite
python -m pytest tests/ -v
npm test

# Verify a live call
python3 -c "
import anthropic
c = anthropic.Anthropic()
m = c.messages.create(model='claude-haiku-4-20250514', max_tokens=8, messages=[{'role':'user','content':'hi'}])
print(f'OK: {m.model} {m.usage}')
"

Migration: Text Completions to Messages

Text CompletionsMessages API
client.completions.create()client.messages.create()
prompt (string)messages (array)
max_tokens_to_samplemax_tokens
model: "claude-2"model: "claude-sonnet-4-20250514"
\n\nHuman:...\n\nAssistant:[{role: "user"}, {role: "assistant"}]
response.completionresponse.content[0].text

Rollback

# Python — pin to previous version
pip install anthropic==0.39.0

# TypeScript — pin to previous version
npm install @anthropic-ai/sdk@0.34.0

# Git rollback
git checkout main -- package.json package-lock.json
npm install

Prerequisites

  • Record the current SDK version, lockfile digest, API version header, model identifiers, supported runtime versions, and a tested rollback revision.
  • Obtain release notes from the official SDK/API sources and an approved sandbox workspace with synthetic prompts; production credentials must not be used for migration tests.
  • Define compatibility, latency, cost, and response-shape acceptance thresholds and identify the owner who approves promotion.

Instructions

  1. Create a migration branch and lock the current dependency graph. Compare the target SDK and API behavior against official release notes; do not infer compatibility from a package version alone.
  2. Update the SDK and request shapes in a sandbox, preserving explicit model IDs, max_tokens, authentication through the secret manager, and least-privileged workspace access.
  3. Run unit, contract, streaming, tool-use, error, and token-count tests using synthetic fixtures. Compare redacted response-shape and usage receipts with the baseline; never log prompt or response content.
  4. Canary the pinned artifact on an isolated workspace with zero customer traffic. Promote only after owner approval and threshold checks; monitor errors, latency, rate limits, and spend during the rollout.
  5. If any gate fails, stop promotion, restore the prior lockfile/revision, revoke temporary credentials, and preserve the redacted migration receipt.

Output

Produce a migration receipt containing source and target SDK versions, API-version header, lockfile/artifact digests, test and canary results, model IDs, workspace/environment, approval, rollout state, rollback reference, and retention deadline. Exclude API keys, prompt/response text, customer identifiers, and raw exception payloads.

Error Handling

FailureResponse
Dependency or API contract test failsPin the prior version, isolate the failing fixture, and do not promote.
Authentication or permission failureStop the canary, verify the secret-manager reference and workspace scope, and never print the key.
429/5xx, timeout, or latency regressionRespect SDK retry guidance, apply a bounded circuit breaker, and roll back when the canary threshold is exceeded.
Response-shape or tool-use driftQuarantine the result, update the adapter only after an approved contract decision, and rerun the full suite.

Examples

For a synthetic migration fixture, pin anthropic from 0.39.0 to the reviewed target, run 100 sandbox Messages API calls with customer=fixture-017, assert response-shape parity and customer_content_logged=0, then promote to a 1% internal canary. A failed threshold yields promotion=halted; rollback=prior-lockfile.

Resources

Next Steps

For CI integration during upgrades, see anth-ci-integration.

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!