readwise-skills

readwise-skills is a repository of AI agent “skills” for working with a user’s Readwise/Reader data. It includes skills that teach an agent how to use the Readwise CLI and Readwise MCP tools, plus higher-level workflows like triaging saved articles, feed catch-up, quizzes, book reviews, reading recaps, and generating a “now reading” page/persona for personalization.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml ai-agents readwise mcp cli productivity personalization summarization knowledge-management
⚙ Agent Friendliness
37
/ 100
Can an agent use this?
🔒 Security
42
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
45
Documentation
55
Error Messages
0
Auth Simplicity
45
Rate Limits
10

🔒 Security

TLS Enforcement
70
Auth Strength
40
Scope Granularity
25
Dep. Hygiene
40
Secret Handling
35

The README references a remote MCP server endpoint over HTTPS, which suggests TLS-in-transit is used. However, the repo-level README does not describe authentication details, secret handling practices, scope granularity, or any security controls for the skills themselves. Because the skills operate on personal reading data, secure credential storage and minimal logging are important but not evidenced in the provided documentation.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
30
Error Recovery
20
AF Security Reliability

Best When

You already use Readwise (and either the Readwise MCP server or the Readwise CLI) and want an agent to perform reading-management workflows end-to-end.

Avoid When

You cannot authenticate to Readwise or do not have access to the MCP/CLI, or you need guarantees around documented error handling, retry/idempotency, and operational reliability.

Use Cases

  • Automate triage of a reading/inbox queue (decide what to focus on and why)
  • Summarize and extract highlights/gems from Reader feed batches
  • Generate quizzes and graded practice from recently read content
  • Draft long-form book reviews using a user’s highlight history
  • Produce conversational reading recaps and recommendations based on reading behavior
  • Create a personalized reading persona and use it to tailor other agent outputs
  • Visualize reading highlights as an idea-connection graph
  • Generate and publish a “What I’m Reading” webpage from a library

Not For

  • Directly hosting or replacing a Readwise backend (it is client/agent tooling, not a full data platform)
  • Use without the Readwise MCP server or Readwise CLI (the skills depend on those integrations)
  • Compliance-grade data handling without verifying Readwise’s own security/privacy controls
  • Mission-critical automation where idempotency/retry semantics are required and documented

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Uses Readwise MCP server or Readwise CLI credentials (exact mechanism not specified in README) Likely API key/token via Readwise MCP/CLI (not documented here)
OAuth: No Scopes: No

The README indicates skills rely on the Readwise MCP server or Readwise CLI, but it does not document the specific authentication flow, scopes, or token handling within this repo.

Pricing

Free tier: No
Requires CC: No

Pricing for readwise-skills itself is not described here; any cost would likely be tied to your Readwise plan and your LLM usage.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Skills depend on either the Readwise MCP server (remote) or the Readwise CLI; if neither is configured, the skills cannot function.
  • README does not document tool I/O contracts, error codes, retry/idempotency behavior, or pagination patterns for the agent workflows—agents may need defensive handling.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for readwise-skills.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6447
Packages Evaluated
19956
Need Evaluation
586
Need Re-evaluation
Community Powered