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-migration-deep-dive
description: 'Migrate to CodeRabbit from other code review tools or roll out across
a large organization.
Use when switching from another AI review tool, migrating from manual-only reviews,
or planning a phased CodeRabbit adoption strategy.
Trigger with phrases like "migrate to coderabbit", "coderabbit migration",
"switch to coderabbit", "coderabbit from reviewbot", "adopt coderabbit", "replace
code review tool".
'
allowed-tools: Read, Write, Edit, Bash(gh:*), Bash(git:*), Grep
version: 1.11.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- coderabbit
- migration
- adoption
compatibility: Designed for Claude CodeComprehensive guide for migrating to CodeRabbit from other AI code review tools (Codacy, SonarCloud, DeepSource, Sourcery) or from manual-only code review. Covers assessment, phased rollout, configuration transfer, team buy-in, and measuring success.
| From | Complexity | Duration | Key Challenge |
|---|---|---|---|
| Manual-only reviews | Low | 1-2 weeks | Team adoption |
| Codacy / SonarCloud | Medium | 2-3 weeks | Rule translation |
| DeepSource / Sourcery | Medium | 2-3 weeks | Config migration |
| Custom review bots | High | 3-4 weeks | Workflow redesign |
| Multiple tools | High | 4-6 weeks | Consolidation |
set -euo pipefail
ORG="${1:-your-org}"
echo "=== Code Review Tool Assessment ==="
# Check for existing review tools
echo "--- Installed GitHub Apps ---"
gh api "orgs/$ORG/installations" --jq '.installations[] | "\(.app_slug) (ID: \(.id))"' 2>/dev/null
echo ""
echo "--- Review Tool Config Files ---"
for REPO in $(gh repo list "$ORG" --limit 20 --json name --jq '.[].name'); do
# Check for common review tool configs
for CONFIG in ".codacy.yml" "sonar-project.properties" ".deepsource.toml" ".sourcery.yaml" ".coderabbit.yaml"; do
EXISTS=$(gh api "repos/$ORG/$REPO/contents/$CONFIG" --jq '.name' 2>/dev/null || echo "")
if [ -n "$EXISTS" ]; then
echo " $REPO: $CONFIG"
fi
done
done
# Common rule translations:
# Codacy / SonarCloud "code smells" → CodeRabbit path_instructions
# Before (Codacy):
# rules:
# - id: "javascript/complexity"
# - id: "javascript/error-handling"
#
# After (CodeRabbit):
reviews:
path_instructions:
- path: "src/**/*.ts"
instructions: |
Check for:
- Functions with cyclomatic complexity > 10 (suggest refactoring)
- Missing error handling in async operations
- Empty catch blocks
- Unused variables and imports
# DeepSource "analyzer" → CodeRabbit path_instructions
# Before (DeepSource):
# analyzers:
# - name: javascript
# enabled: true
# meta:
# plugins: [react]
#
# After (CodeRabbit):
- path: "src/components/**"
instructions: |
React-specific checks:
- No conditional hooks
- Proper cleanup in useEffect
- Memoization for expensive computations
- Accessibility (aria labels, keyboard navigation)
# Sourcery "refactoring" → CodeRabbit path_instructions
# Before (Sourcery):
# refactor:
# skip: [dont-import-test-modules]
#
# After (CodeRabbit):
- path: "**/*.py"
instructions: |
Python best practices:
- Suggest list comprehensions over manual loops where appropriate
- Flag mutable default arguments
- Check for proper context manager usage
# Run CodeRabbit alongside existing tool for comparison
# .coderabbit.yaml - Start with non-blocking mode
reviews:
profile: "chill" # Fewer comments during evaluation
request_changes_workflow: false # Don't block merges
high_level_summary: true # Show walkthrough for evaluation
auto_review:
enabled: true
drafts: false
base_branches: [main, develop]
path_filters:
- "!**/*.lock"
- "!**/*.snap"
- "!dist/**"
- "!vendor/**"
chat:
auto_reply: true
# During parallel run, track:
1. Comment quality: Are CodeRabbit comments actionable?
2. Coverage: Does it catch what the old tool catches?
3. Speed: Is review posted before human reviewers start?
4. Noise: Are there many false positives?
5. Team reaction: Do developers find it helpful?
# After successful parallel run, make CodeRabbit primary
# .coderabbit.yaml - Enable full features
reviews:
profile: "assertive" # Balanced feedback
request_changes_workflow: true # Now blocking
high_level_summary: true
sequence_diagrams: true
auto_review:
enabled: true
drafts: false
base_branches: [main, develop]
path_instructions:
# Transfer your best rules from the old tool
- path: "src/api/**"
instructions: |
Review for: input validation, proper HTTP status codes,
auth middleware usage, error response format.
- path: "src/db/**"
instructions: |
Review for: parameterized queries, transaction boundaries,
connection cleanup, index usage. Flag N+1 patterns.
- path: "**/*.test.*"
instructions: |
Review for: assertion completeness, edge cases, async handling.
Do NOT comment on test naming or import order.
# Keep exclusions from old tool
path_filters:
- "!**/*.lock"
- "!**/*.snap"
- "!**/generated/**"
- "!dist/**"
- "!vendor/**"
set -euo pipefail
ORG="${1:-your-org}"
echo "=== Old Tool Decommission Checklist ==="
# 1. Remove old tool config files
echo "--- Config Files to Remove ---"
for REPO in $(gh repo list "$ORG" --limit 50 --json name --jq '.[].name'); do
for CONFIG in ".codacy.yml" "sonar-project.properties" ".deepsource.toml" ".sourcery.yaml"; do
EXISTS=$(gh api "repos/$ORG/$REPO/contents/$CONFIG" --jq '.name' 2>/dev/null || echo "")
if [ -n "$EXISTS" ]; then
echo " rm $REPO/$CONFIG"
fi
done
done
echo ""
echo "--- Steps ---"
echo "1. Remove old tool GitHub App from org settings"
echo "2. Delete old tool config files from repos"
echo "3. Update branch protection rules (replace old check with coderabbitai)"
echo "4. Cancel old tool subscription"
echo "5. Update team documentation and onboarding guides"
set -euo pipefail
ORG="${1:-your-org}"
REPO="${2:-your-repo}"
echo "=== CodeRabbit Adoption Metrics ==="
# Review coverage
TOTAL=0
REVIEWED=0
for PR_NUM in $(gh api "repos/$ORG/$REPO/pulls?state=closed&per_page=30" --jq '.[].number'); do
TOTAL=$((TOTAL + 1))
CR=$(gh api "repos/$ORG/$REPO/pulls/$PR_NUM/reviews" \
--jq '[.[] | select(.user.login=="coderabbitai[bot]")] | length' 2>/dev/null || echo "0")
[ "$CR" -gt 0 ] && REVIEWED=$((REVIEWED + 1))
done
echo "Review coverage: $REVIEWED/$TOTAL PRs ($(( REVIEWED * 100 / (TOTAL > 0 ? TOTAL : 1) ))%)"
echo ""
echo "Target metrics:"
echo " - Coverage > 90%: CodeRabbit reviewing most PRs"
echo " - Time-to-review < 5 min: Fast feedback loop"
echo " - Team satisfaction: Survey developers after 2 weeks"
| Issue | Cause | Solution |
|---|---|---|
| Old tool conflicts with CodeRabbit | Both posting reviews | Run parallel briefly, then disable old tool |
| Rules don't translate 1:1 | Different analysis approaches | Focus on intent, not exact rule matching |
| Team prefers old tool | Familiarity bias | Run parallel for 2 weeks, compare results |
| Branch protection breaks | Old check name removed | Update to coderabbitai check name |
| Higher seat cost than old tool | Per-seat vs per-repo pricing | Scope repos to reduce seat count |
Run CodeRabbit and the existing reviewer in parallel on a small, representative repository for a defined period, measure coverage, useful findings, latency, and developer feedback, then migrate the reviewed rules by intent. Do not retire the prior protection or alter required checks until the measured rollout and rollback path are accepted by repository owners.
For ongoing configuration tuning, see coderabbit-core-workflow-b.
评论 (0)
暂无评论,成为第一个评论者吧!