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 identifies the platform (Bluesky), lists comprehensive concrete actions, and includes an explicit 'Use this skill when...' clause with detailed trigger scenarios. It also provides useful implementation details about dependencies and environment variables, and is highly distinctive with minimal conflict risk.
| 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, and viewing reply threads. | 3 / 3 |
Completeness | Clearly answers both 'what' (read from and post to Bluesky using AT Protocol, with specific actions listed) 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 | Includes strong natural keywords users would say: 'Bluesky', 'posting', 'timeline', 'replying', 'following/unfollowing', 'notifications', 'profiles', 'AT Protocol'. These cover a wide range of natural user requests related to Bluesky interaction. | 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. | 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 executable examples for every script. Its main weaknesses are moderate verbosity (some explanatory content Claude doesn't need, like AT Protocol concept definitions) and a monolithic structure that could benefit from splitting detailed per-script documentation into separate files. The lack of validation/verification steps after operations (e.g., confirming a post was created successfully) is a notable gap for workflow clarity.
Suggestions
Remove the Key Concepts section (Claude already knows AT Protocol terminology) and trim the 'How it works' explanation in reply.py to save tokens.
Add verification steps after posting/replying (e.g., 'Check the returned URI to confirm the post was created') and mention checking for null cursors in pagination workflows.
Consider splitting per-script detailed documentation (argument tables, all usage examples) into a separate REFERENCE.md, keeping SKILL.md as a concise overview with one example per script.
| 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 'Setting Credentials' section repeats what's already in Prerequisites. The reply.py section's explanation of root/parent threading is implementation detail Claude doesn't need. | 2 / 3 |
Actionability | Every script has fully executable, copy-paste-ready bash commands with multiple usage variations. Arguments are documented in tables where needed, and the examples cover common use cases comprehensively including image posts, pagination, JSON output, and inline credential passing. | 3 / 3 |
Workflow Clarity | Individual script usage is clear, but there are no validation checkpoints for multi-step workflows. For example, posting with images has no guidance on verifying the post succeeded, pagination workflows don't mention checking for empty cursors, and there's no error recovery guidance beyond the brief error handling section. The 'Identify Yourself' requirement is clear but the overall posting workflow lacks verification steps. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical grouping, but it's a long monolithic document (~200 lines) where the detailed argument tables and common patterns could be split into separate reference files. The skill would benefit from a concise overview pointing to per-script documentation rather than inlining everything. | 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
3f74412
- 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.