twitter-algorithm-optimizer
Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.
65
47%
Does it follow best practices?
Impact
97%
1.31xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/twitter-algorithm-optimizer/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is strong in specificity and distinctiveness, clearly articulating concrete actions (analyze, optimize, rewrite tweets) within a well-defined niche (Twitter algorithm optimization). However, it lacks an explicit 'Use when...' clause, which limits completeness, and could benefit from broader trigger term coverage including modern terminology like 'X' and common user phrases like 'go viral' or 'get more impressions'.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to improve a tweet, optimize a post for engagement, or asks about Twitter/X algorithm ranking.'
Include additional natural trigger terms users might say, such as 'X', 'post', 'viral', 'impressions', 'social media optimization', and 'thread'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'analyze and optimize tweets', 'rewrite and edit user tweets', 'improve engagement and visibility', and references specific methodology ('Twitter's open-source algorithm insights', 'recommendation system ranks content'). | 3 / 3 |
Completeness | Clearly answers 'what does this do' (analyze, optimize, rewrite tweets for engagement), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes natural terms like 'tweets', 'Twitter', 'engagement', 'reach', and 'algorithm', but misses common user variations like 'X' (Twitter's rebrand), 'post', 'viral', 'impressions', or 'social media'. Also lacks a 'Use when...' clause to explicitly list trigger scenarios. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific niche: Twitter/tweet optimization using the open-source algorithm. This is unlikely to conflict with other skills due to the very targeted domain of Twitter content optimization and algorithm-based ranking. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely verbose, spending most of its token budget explaining Twitter's algorithm architecture in tutorial fashion rather than providing lean, actionable optimization instructions. The before/after tweet examples are the strongest element, but they're buried in excessive context. The content would benefit enormously from being split into a concise SKILL.md overview with references to detailed files, and from cutting the explanatory material Claude doesn't need.
Suggestions
Cut the algorithm architecture section drastically — move detailed Real-graph/SimClusters/TwHIN/Tweepcred explanations to a separate ALGORITHM_REFERENCE.md and keep only a brief summary in the main skill
Remove the 'When to Use This Skill' and 'What This Skill Does' meta-sections entirely — these describe the skill rather than instructing Claude
Add a structured output format (e.g., a template for tweet analysis results) so Claude knows exactly what to produce when optimizing a tweet
Add a validation/feedback step to the workflow — e.g., after optimization, score the rewritten tweet against the signal checklist and iterate if it doesn't meet criteria
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Extensively explains how Twitter's algorithm works (Real-graph, SimClusters, TwHIN, feed generation pipeline) — background knowledge Claude can infer or doesn't need spelled out in this detail. The 'When to Use This Skill' and 'What This Skill Does' sections are meta-descriptions that waste tokens. Much of the algorithm architecture section reads like a tutorial for a human, not actionable instructions for Claude. | 1 / 3 |
Actionability | Provides concrete before/after tweet examples which are genuinely useful, and the 4-step optimization process is somewhat actionable. However, there's no executable code or structured output format — it's mostly descriptive guidance and general strategies rather than precise, copy-paste-ready instructions Claude can follow mechanically. | 2 / 3 |
Workflow Clarity | The 4-step optimization process (Identify Core Message → Map to Algorithm Strategy → Optimize for Signals → Check Against Negatives) provides a reasonable sequence, but lacks validation checkpoints or feedback loops. There's no explicit 'verify the optimization worked' step or criteria for when an optimization is sufficient vs. needs another pass. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content — algorithm architecture, optimization strategies, examples, best practices, pitfalls — is crammed into a single document. The algorithm architecture section alone could be a separate reference file, and the examples could be in an EXAMPLES.md. No navigation aids or clear hierarchy for discovery. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.