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。
A model-agnostic agent-skills platform.
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。
来源文件:README.md
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.
Version semantics: the release badge is this marketplace's display version. npm packages, including the
ccpiCLI 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.
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, skyvern, code-cleanup, web-analytics, token-optimizer, executive-assistant-skills, skill-creator, cursor-pack, crypto-portfolio-tracker. See all at tonsofskills.com.
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."
| Count | Cohort | Reproduce with |
|---|---|---|
| 442 | catalog plugins (catalog-entry cohort) | node scripts/generate-readme-toc.mjs over marketplace.extended.json |
| 3,067 | marketplace-visible skills (distinct) | node -e "import('./scripts/corpus-resolver.mjs').then(m=>console.log(m.resolveCorpus('marketplace-visible').length))" |
| 347 | agent definitions in plugins | git ls-files 'plugins/**' | grep '/agents/.*\.md' |
| 19 | plugin categories | ls -d plugins/*/ |
Across 396 published packages in the claude-code-plugins namespace. Updated daily by GitHub Actions.
| Window | All packages | Established (>30d) |
|---|---|---|
| Last 24 hours | 962 | 962 |
| Last 7 days | 2,920 | 2,916 |
| Last 30 days | 12,868 | 12,779 |
"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:
Last refreshed 2026-08-19T03:03:05.709Z.
Five real questions, five doors — each resolves to a live, generated surface, never a hand-maintained list:
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).
| Category | Plugins | |
|---|---|---|
| 🤖 | AI & Machine Learning | 36 |
| 🎭 | AI Agents & Agency | 10 |
| 🔌 | API Development | 26 |
| 💼 | Business Tools | 6 |
| 👥 | Community | 21 |
| ₿ | Crypto & Web3 | 27 |
| 💾 | Database | 26 |
| 🎨 | Design | 2 |
| 🔧 | DevOps & Infrastructure | 36 |
| 📚 | Examples & Templates | 5 |
| 🧩 | MCP Servers | 16 |
| 📦 | Packages | 5 |
| ⚡ | Performance | 25 |
| ✅ | Productivity | 30 |
| 🎁 | SaaS Skill Packs | 106 |
| 🔐 | Security | 27 |
| ✨ | Skill Enhancers | 9 |
| 🧪 | Testing | 28 |
| 📁 | Analytics | 1 |
Four artifact classes live in this repository, distinguished on sight and never blurred — provenance is a truth requirement here, not a UX nicety:
| Class | What it is | How the reader can tell |
|---|---|---|
| Canonical skill | First-party, harness-free, the source of truth | No .source.json in its plugin directory |
| Generated adapter | A thin, machine-produced harness projection | Lives under a generated path with a "generated — do not edit" header |
| First-party package | An Intent Solutions distribution (npm, cowork zip) | @intentsolutionsio scope, IS-authored license |
| Upstream mirror | Somebody else's work, hosted mirror-by-default | .source.json present — upstream author, license, and pinned commit recorded |
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.
Start with the contribution guide, then the intake and review standards every submission passes through:
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.
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.
name: coderabbit-upgrade-migration
description: 'Update CodeRabbit configuration for new features, migrate between plans,
and adopt new capabilities.
Use when CodeRabbit releases new features, upgrading from Free to Pro plan,
or updating .coderabbit.yaml schema for new options.
Trigger with phrases like "upgrade coderabbit", "coderabbit new features",
"update coderabbit config", "coderabbit plan upgrade", "coderabbit changelog".
'
allowed-tools: Read, Write, Edit, Bash(gh:*), Bash(git:*)
version: 1.11.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- coderabbit
- migration
- upgrade
compatibility: Designed for Claude CodeCodeRabbit is a managed SaaS service -- there is no SDK to upgrade. Configuration changes happen by updating .coderabbit.yaml in your repository. This skill covers adopting new CodeRabbit features, upgrading between plans, migrating configuration formats, and staying current with CodeRabbit capabilities.
.coderabbit.yaml in repository root| From | To | What Changes |
|---|---|---|
| Free | Pro | Private repos, more concurrent reviews, all features |
| Pro | Enterprise | SSO, dedicated support, SLA, custom limits |
| Old config format | New format | Updated YAML schema fields |
| Basic config | Advanced config | Path instructions, learnings, finishing touches |
# On any open PR, post this comment:
@coderabbitai configuration
# CodeRabbit replies with the active config as YAML.
# Compare with the latest schema documentation to find:
# 1. Deprecated fields you're still using
# 2. New fields available that you're not using
# 3. Fields with changed default values
# What you gain with Pro:
1. Private repository support (Free = public only)
2. More concurrent reviews (Free = 1, Pro = 5)
3. Learnings (CodeRabbit remembers your feedback preferences)
4. Finishing Touches (auto-generate docstrings, custom recipes)
5. Full path instructions and review customization
6. Priority review processing
# Steps:
1. Go to app.coderabbit.ai > Organization > Subscription
2. Select Pro plan
3. Set seat assignment policy (active committers recommended)
4. Add payment method
5. Seats activate immediately for all configured repos
# .coderabbit.yaml - Modern configuration with latest features
language: "en-US"
early_access: false # Set true to try beta features
reviews:
profile: "assertive"
request_changes_workflow: true
high_level_summary: true
high_level_summary_in_walkthrough: true # Summary inside walkthrough comment
review_status: true
collapse_walkthrough: false
sequence_diagrams: true # Visual control flow diagrams
poem: false
auto_review:
enabled: true
drafts: false
base_branches:
- main
- develop
ignore_title_keywords:
- "WIP"
- "DO NOT MERGE"
- "chore: bump"
path_filters:
- "!**/*.lock"
- "!**/*.snap"
- "!**/generated/**"
- "!dist/**"
- "!vendor/**"
path_instructions:
- path: "src/api/**"
instructions: "Review for input validation, auth middleware, error handling."
- path: "src/db/**"
instructions: "Review for parameterized queries, transactions, N+1 patterns."
- path: "**/*.test.*"
instructions: "Review for edge cases. Skip style comments."
- path: ".github/workflows/**"
instructions: "Pin action versions to SHA. No secrets in logs."
# Finishing Touches (Pro+)
finishing_touches:
docstrings:
enabled: true # @coderabbitai generate-docstrings command
# Tool integrations
tools:
eslint:
enabled: true # Lint with ESLint rules
biome:
enabled: true # Biome linter
shellcheck:
enabled: true # Shell script linting
markdownlint:
enabled: true # Markdown linting
# Tone customization (Pro+)
tone_instructions: |
Be concise and direct. Use bullet points for multiple suggestions.
Include code examples for non-obvious fixes.
Rate severity: Critical > Warning > Suggestion > Nitpick.
chat:
auto_reply: true
# .coderabbit.yaml - Custom finishing touch recipes (Pro+)
finishing_touches:
docstrings:
enabled: true
recipes:
- name: "fix-imports"
description: "Sort and organize imports"
instructions: |
Sort all imports alphabetically. Group: external packages first,
then internal modules, then relative imports. Remove unused imports.
- name: "tighten-types"
description: "Replace any with proper types"
instructions: |
Replace all `any` types with proper TypeScript types.
Use `unknown` for truly unknown values. Add type guards where needed.
- name: "add-error-handling"
description: "Add missing error handling"
instructions: |
Add try/catch blocks to async operations that are missing error handling.
Include meaningful error messages and proper error propagation.
# Use recipes on a PR:
@coderabbitai run fix-imports
@coderabbitai run tighten-types
@coderabbitai generate-docstrings
# Or check the boxes in the Finishing Touches section of the walkthrough comment
# .coderabbit.yaml - Opt into beta features
early_access: true # Enables experimental features as they ship
# Early access features are documented at:
# https://docs.coderabbit.ai/early-access
#
# Recent early access features have included:
# - Finishing touch recipes (now GA)
# - Tool integrations (eslint, biome, shellcheck)
# - Sequence diagrams in walkthroughs
# - Knowledge base / code guidelines auto-detection
set -euo pipefail
echo "=== Post-Upgrade Validation ==="
# 1. Validate YAML syntax
echo "--- YAML Validation ---"
python3 -c "
import yaml
config = yaml.safe_load(open('.coderabbit.yaml'))
print(f'YAML: VALID ({len(str(config))} chars)')
# Check for new features
reviews = config.get('reviews', {})
ft = reviews.get('finishing_touches', {})
tools = reviews.get('tools', {})
tone = config.get('tone_instructions', '')
early = config.get('early_access', False)
print(f'Finishing touches: {\"enabled\" if ft else \"not configured\"}')
print(f'Tool integrations: {len(tools)} tools configured')
print(f'Tone instructions: {\"set\" if tone else \"default\"}')
print(f'Early access: {early}')
" 2>&1
# 2. Verify config is active
echo ""
echo "--- Verify on PR ---"
echo "Post '@coderabbitai configuration' on any open PR to verify"
echo "the new configuration is active."
# When updating configuration:
- [ ] YAML syntax validated before committing
- [ ] Config committed to main branch (CodeRabbit reads from base branch)
- [ ] @coderabbitai configuration verified on a test PR
- [ ] Team notified of any behavior changes
- [ ] Old deprecated fields removed
- [ ] New features tested on a non-critical PR first
| Issue | Cause | Solution |
|---|---|---|
| New field ignored | Not on Pro/Enterprise plan | Upgrade plan for full feature access |
| Config not applied after update | Committed to wrong branch | Merge config changes to the base branch |
| YAML parse error | Invalid syntax | Validate YAML before committing |
| Feature not available | Requires early_access: true | Enable early access in config |
| Finishing touches not working | Not on Pro plan | Upgrade to Pro for finishing touches |
Pin the current configuration in a pilot repository, apply one schema change on a non-critical pull request, validate YAML and the active configuration, then compare review behavior to the prior baseline. If a feature or field is ignored or changes blocking behavior, restore the pinned configuration and defer the upgrade until the plan/schema requirement is verified.
For CI integration after upgrade, see coderabbit-ci-integration.
评论 (0)
暂无评论,成为第一个评论者吧!