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-common-errors
description: 'Diagnose and fix CodeRabbit common errors and configuration issues.
Use when CodeRabbit is not reviewing PRs, posting duplicate comments,
ignoring configuration, or behaving unexpectedly.
Trigger with phrases like "coderabbit error", "fix coderabbit",
"coderabbit not working", "debug coderabbit", "coderabbit broken".
'
allowed-tools: Read, Grep, Bash(gh:*), Bash(git:*)
version: 1.11.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- coderabbit
- debugging
- troubleshooting
compatibility: Designed for Claude CodeQuick-reference troubleshooting guide for the most common CodeRabbit issues. CodeRabbit is a GitHub/GitLab App that reviews PRs automatically -- most problems are configuration issues, permission gaps, or YAML syntax errors rather than API failures.
.coderabbit.yaml in repository root| Symptom | Category | Jump To |
|---|---|---|
| No review posted on PR | Installation/Permissions | Error 1 |
| Review on some PRs but not others | Configuration | Error 2-4 |
| Too many comments / noise | Tuning | Error 5 |
| Config changes not taking effect | YAML Issues | Error 6 |
| Bot not responding to commands | Interaction | Error 7 |
| Review takes too long | Performance | Error 8 |
Symptoms: PR is open, targeting main, but no CodeRabbit review appears after 15+ minutes.
Diagnosis:
set -euo pipefail
# Check if CodeRabbit App is installed on this repo
gh api repos/OWNER/REPO/installation --jq '.app_slug' 2>/dev/null || echo "NOT INSTALLED"
# Check if the PR author has a CodeRabbit seat
# Go to app.coderabbit.ai > Organization > Seats
Causes & Solutions:
Symptoms: Reviews appear on PRs to main but not develop or feature branches.
Cause: base_branches filter in configuration only includes specific branches.
Fix:
# .coderabbit.yaml
reviews:
auto_review:
enabled: true
base_branches:
- main
- develop
- "release/*" # Glob patterns work
- "hotfix/*"
# Remove base_branches entirely to review PRs to ALL branches
Symptoms: Some PRs get reviewed, others are silently skipped.
Diagnosis checklist:
# Check these .coderabbit.yaml settings:
reviews:
auto_review:
drafts: false # Draft PRs are skipped (expected behavior)
ignore_title_keywords: # PRs with these keywords in title are skipped
- "WIP"
- "DO NOT MERGE"
- "chore: bump" # This skips dependency update PRs
# Also check: Is the PR author a bot?
# Bot PRs (dependabot, renovate) may not trigger reviews
# unless bot accounts have CodeRabbit seats
Symptoms: CodeRabbit comments on lock files, generated code, or build output.
Fix:
# .coderabbit.yaml - Add path filters
reviews:
path_filters:
- "!**/*.lock"
- "!**/package-lock.json"
- "!**/pnpm-lock.yaml"
- "!**/*.snap"
- "!**/generated/**"
- "!dist/**"
- "!**/*.min.js"
- "!vendor/**"
- "!**/*.generated.*"
Symptoms: CodeRabbit posts 10-20+ comments per PR, most are nitpicks.
Fix:
# .coderabbit.yaml - Reduce comment volume
reviews:
profile: "chill" # Fewer comments, only significant issues
# Options: chill (fewest) → assertive (balanced) → nitpicky (most)
# Give context to prevent misguided comments
path_instructions:
- path: "src/legacy/**"
instructions: |
This is legacy code. Only flag security issues and bugs.
Do NOT suggest refactoring or style changes.
- path: "scripts/**"
instructions: |
One-off scripts. Do not enforce production standards.
Only flag: security issues, destructive ops without confirmation.
Symptoms: You updated .coderabbit.yaml but reviews behave the same way.
Diagnosis:
# In a PR comment, run:
@coderabbitai configuration
# CodeRabbit will reply with the active configuration as YAML.
# Compare with your .coderabbit.yaml to find discrepancies.
# Common causes:
# 1. YAML syntax error - entire config is ignored silently
# 2. Config not on the base branch - CodeRabbit reads config from the PR's base branch
# 3. Organization-level config overriding repo config
# 4. Wrong field name (e.g., "review_instructions" instead of "path_instructions")
YAML validation:
set -euo pipefail
# Validate YAML syntax
python3 -c "import yaml; yaml.safe_load(open('.coderabbit.yaml'))" && echo "YAML OK" || echo "YAML INVALID"
# Or use an online validator: https://www.yamllint.com/
Symptoms: You post @coderabbitai full review but nothing happens.
Causes & Solutions:
@coderabbitai (one word, lowercase).coderabbit.yaml has chat: auto_reply: true# .coderabbit.yaml - Ensure chat is enabled
chat:
auto_reply: true # Required for @coderabbitai commands to work
Symptoms: PR opened but CodeRabbit review not posted after 15 minutes.
Causes:
| PR Size | Expected Time | Action |
|---|---|---|
| < 200 lines | 2-3 min | Normal, wait |
| 200-500 lines | 3-7 min | Normal, wait |
| 500-1000 lines | 7-12 min | Consider splitting |
| 1000+ lines | 12-15+ min | Split PR or be patient |
If it is been 20+ minutes on a small PR:
1. Check CodeRabbit status: https://status.coderabbit.ai
2. Try: @coderabbitai full review (force re-review)
3. Check GitHub App installation hasn't been suspended
4. Contact support via CodeRabbit Discord or email
After applying a fix, create or update a PR and confirm CodeRabbit behaves as expected:
set -euo pipefail
# Force a re-review on an existing PR
gh pr comment PR_NUMBER --body "@coderabbitai full review"
# Or check the active config
gh pr comment PR_NUMBER --body "@coderabbitai configuration"
.coderabbit.yaml| Issue | Cause | Solution |
|---|---|---|
| All reviews stopped suddenly | GitHub App permissions revoked | Reinstall CodeRabbit GitHub App |
| "This repository is not configured" | Repo removed from App access | Re-add repo in GitHub App settings |
| YAML parse error in logs | Invalid .coderabbit.yaml | Validate YAML syntax before committing |
| Stale reviews on old PRs | PR was created before config change | Run @coderabbitai full review |
When reviews stop, verify the app installation and active configuration on a small test PR, make the smallest configuration correction, then request a re-review to confirm the result. If a check or policy behaves unexpectedly, retain the evidence and use the reviewed rollback rather than disabling unrelated repository protections.
For comprehensive debugging, see coderabbit-debug-bundle.
评论 (0)
暂无评论,成为第一个评论者吧!