bluesky
Read from and post to Bluesky social network using the AT Protocol. Use this skill when the user wants to interact with Bluesky including posting text/images/links, replying to posts, reading their timeline, searching posts, viewing profiles, following/unfollowing users, checking notifications, or viewing reply threads. All scripts use PEP 723 inline metadata for dependencies and run via `uv run`. Requires BLUESKY_HANDLE and BLUESKY_PASSWORD environment variables.
87
82%
Does it follow best practices?
Impact
94%
1.44xAverage score across 3 eval scenarios
Critical
Do not install without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly communicates what the skill does, when to use it, and how it's implemented. It provides comprehensive trigger terms covering the full range of Bluesky interactions, uses proper third-person voice, and includes an explicit 'Use this skill when...' clause with detailed scenarios. The technical implementation details (PEP 723, uv run, environment variables) add useful context without cluttering the core purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: posting text/images/links, replying to posts, reading timeline, searching posts, viewing profiles, following/unfollowing users, checking notifications, viewing reply threads. Also mentions technical implementation details like PEP 723 and `uv run`. | 3 / 3 |
Completeness | Clearly answers both 'what' (read from and post to Bluesky using AT Protocol, with a comprehensive list of capabilities) and 'when' (explicit 'Use this skill when the user wants to interact with Bluesky including...' clause with detailed trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Bluesky', 'post', 'timeline', 'reply', 'follow', 'unfollow', 'notifications', 'profiles', 'images', 'links', 'search posts'. These are all terms a user would naturally use when wanting to interact with Bluesky. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific social network (Bluesky) and a specific protocol (AT Protocol). Very unlikely to conflict with other skills unless there were multiple Bluesky-related skills. The mention of environment variables and implementation details further narrows the niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, highly actionable skill with excellent concrete examples for every script. Its main weaknesses are length (could benefit from splitting detailed per-script docs into separate files) and the lack of validation/verification steps for public-facing operations like posting. Some sections like Key Concepts and the uv installation explanation add tokens without much value for an AI agent.
Suggestions
Add a verification step after posting (e.g., 'After posting, use the returned URI to confirm the post is live via replies.py or profile check') to improve workflow safety for public actions.
Move detailed per-script argument tables and extensive examples into separate reference files, keeping SKILL.md as a concise overview with one example per script and links to details.
Remove the Key Concepts glossary section — Claude already understands DIDs, URIs, and handles — or reduce it to a single line noting the App Password recommendation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of command examples, but includes some unnecessary content: the 'How it works' explanation for reply threading, the Key Concepts glossary (Claude knows AT Protocol concepts), and the Prerequisites section explaining what uv is and how to install it is somewhat verbose for an AI agent audience. | 2 / 3 |
Actionability | Every script has fully executable, copy-paste-ready bash commands with multiple usage variations. Arguments are documented in tables, and common patterns like credential setup, JSON processing with jq, and pagination are all concrete and immediately usable. | 3 / 3 |
Workflow Clarity | Individual script usage is clear, but there are no validation checkpoints or feedback loops. For operations like posting (which is a destructive/public action), there's no guidance on verifying success, checking the post appeared, or handling failures beyond a brief error section. The pagination workflow is well-sequenced though. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a long monolithic document (~200 lines) where detailed argument tables and extensive examples for each script could be split into per-script reference files. The skill would benefit from a concise overview pointing to detailed docs for each script. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- fpl9000/ai-skills
- Commit
3d82fcd
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.