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.

1.44x

Quality

84%

Does it follow best practices?

Impact

94%

1.44x

Average score across 3 eval scenarios

Securityby

Critical

Do not install without reviewing

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured skill body built on copy-paste executable commands and real bundle scripts. Its main weakness is workflow clarity: posting and follow/unfollow are outward-facing operations that proceed without explicit validation or confirmation checkpoints, which the rubric caps at 3.

Suggestions

Add an explicit 'Confirm before posting/following' checkpoint (or a dry-run/preview step) for outward-facing operations, and document a validate→fix→retry loop so destructive actions can clear the workflow_clarity cap.

Trim or condense the 'Key Concepts' definitions to only AT-Protocol-specific nuances Claude would not already know, improving token efficiency.

Add a brief pre-flight validation note (e.g., check that BLUESKY_HANDLE/BLUESKY_PASSWORD are set and the target handle resolves) before destructive calls.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with copy-paste bash examples and argument tables earning their place, though the 'Key Concepts' section defines a few terms (Handle, DID, URI, CID) that partially explain what Claude already knows or could infer.	4 / 5
Actionability	Fully executable guidance throughout — every script is shown with concrete `uv run` commands, flag examples, and argument tables that cover the common cases copy-paste ready.	5 / 5
Workflow Clarity	Per-script usage is clear and the pagination pattern is sequenced, but outward-facing/destructive operations (posting, following) lack explicit validation checkpoints or confirm-before-act feedback loops, which caps this dimension.	3 / 5
Progressive Disclosure	Well-organized into per-script sections with clear, one-level-deep references to real bundle files (all `scripts/*.py` referenced exist); the SKILL.md serves as overview/index with implementation kept in the scripts, with only minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names a clear niche, enumerates concrete capabilities, and provides an explicit 'Use when...' trigger clause with natural phrasing. Minor room to add a few more conversational synonyms, but it is already comprehensive and low-conflict.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'posting text/images/links, replying to posts, reading their timeline, searching posts, viewing profiles, following/unfollowing users, checking notifications, or viewing reply threads' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Read from and post to Bluesky social network using the AT Protocol') and 'when' ('Use this skill when the user wants to interact with Bluesky including...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage (post, reply, timeline, search, profile, follow/unfollow, notifications, reply threads), but a few common synonyms a user might say (feed, mentions, likes/reposts) are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche ('Bluesky social network using the AT Protocol') with distinct, service-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fpl9000/ai-skills
Path: bluesky/SKILL.md
Commit: 46b1ac6

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

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.