twitter-reader

Fetches Twitter/X post and Article content — text, author, engagement metrics and embedded media — downloading images locally and generating complete Markdown with image references. Use when retrieving a tweet's text or an X Article with images, or pulling post metadata for a Markdown/PKM record. Preferred over Jina alone for X Articles with images.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%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.

An unusually actionable body: real commands, real failure envelopes, and hard-won operational gotchas (refusals that look like success, the 500-item ceiling). The main weaknesses are redundancy — the fetch_article.py usage and Jina-key caveats each appear multiple times — and dated observations embedded in the main flow instead of a separate log section.

Suggestions

State the fetch_article.py invocation once (the Scripts section is redundant with the top usage block and the Migration section) and consolidate the repeated JINA_API_KEY/no-fallback caveat into one place.

Move the dated observations (2026-08-30 fxtwitter note, 2026-09-12 Jina block, twitter-cli 0.8.5 ceiling) into a dedicated 'verified-on' or maintenance-log section so time-sensitive facts don't age the main instructions.

Consider moving the Jina refusal forensics and the twitter-cli 500-ceiling deep-dive into a reference file (e.g. references/troubleshooting.md), keeping SKILL.md as the overview.

Dimension	Reasoning	Score
Conciseness	Mostly dense, high-value operational detail, but the fetch_article.py invocation appears three times (top, Scripts section, Migration) and the Jina-key/no-fallback caveat is repeated twice; dated observations (2026-08-30, 2026-09-12, twitter-cli 0.8.5) sit in the main flow rather than a verification-log section.	3 / 5
Actionability	Fully executable, copy-paste-ready commands (curl with the fxtwitter API, uv run invocations with a real example URL), exact refusal-envelope JSON shapes, and precise internal details (maxCount under rateLimit:, _ABSOLUTE_MAX_COUNT = 500) covering the common cases.	5 / 5
Workflow Clarity	The fetch → download → generate sequence is clear with a real validation checkpoint (the Markdown Content: marker test before accepting a response) and documented loud-failure behavior for the batch script; error recovery during a Jina block is left implicit (no retry/wait loop spelled out), keeping it below 5.	4 / 5
Progressive Disclosure	All referenced script paths (scripts/fetch_article.py, fetch_tweet.py, fetch_tweets.sh) exist in the bundle and are one level deep, with well-labeled sections; however the Jina-failure forensics and the twitter-cli 500-ceiling deep-dive are inline in a ~220-line body where reference files would fit, matching the 'minor organization gaps' anchor.	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 description: third-person voice, concrete multi-action capability statement, explicit 'Use when' triggers, and even a disambiguation hint against a sibling approach. The only gap is a few missing natural trigger variations such as 'thread' or 'x.com link'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — fetching text, author, engagement metrics and embedded media, downloading images locally, and generating Markdown with image references — covering the skill comprehensively, matching the top anchor.	5 / 5
Completeness	Explicitly answers both what (fetch content/metrics/media, download images, generate Markdown) and when ("Use when retrieving a tweet's text or an X Article with images, or pulling post metadata for a Markdown/PKM record") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage (tweet, X Article, images, post metadata, Markdown/PKM), but a few natural variations users would say are missing (thread, x.com/twitter.com link, media).	4 / 5
Distinctiveness Conflict Risk	Clear Twitter/X-fetching niche with distinct triggers, plus explicit disambiguation ("Preferred over Jina alone for X Articles with images") minimizing overlap with generic reader 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: daymade/claude-code-skills
Path: twitter-reader/SKILL.md
Commit: bb6ad55

Reviewed: 5 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.