CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

x-research

X/Twitter research via Composio — search, threads, profiles, watchlists

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./src/skills/bundled/x-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

The body is a highly actionable, token-efficient command reference with complete syntax, defaults, real invocations, and useful search operators, organized into clean sections. It is slightly redundant in flag explanations, and the research workflow would benefit from termination and synthesis guidance, but overall it is a strong skill document.

Suggestions

Trim flag prose that restates the syntax line (e.g. "Supports engagement sorting, time filtering, pagination, and multiple output formats") since the flags in the command block are self-explanatory.

Add termination and synthesis guidance to the Research Workflow, e.g. when to stop searching and to consolidate findings into a summary before adding accounts to the watchlist.

DimensionReasoningScore

Conciseness

Mostly lean copy-paste command blocks with no beginner-concept explanations, but flag prose restates the syntax already shown ("Supports engagement sorting, time filtering, pagination, and multiple output formats") and the intro line "Zero API cost" adds little operational value. Not 5 due to these trimmable redundancies; not 3 because padding is minor.

4 / 5

Actionability

Fully executable: every command has complete syntax with flags and defaults (e.g. "/x search <query> [--sort likes|recent] [--since 1h|1d|7d]"), and the Examples section provides seven copy-paste-ready invocations covering common cases such as "/x search \"prediction markets\" --sort likes --since 7d".

5 / 5

Workflow Clarity

The Research Workflow gives a clear 5-step sequence ("Decompose your question into 3-5 targeted search queries... Follow high-engagement threads... Add important accounts to watchlist") with read-only operations, so the destructive/batch validation cap does not apply. Not 5 because it lacks decision checkpoints such as when to stop searching or how to synthesize findings; not 3 because the sequence is explicit and well-ordered.

4 / 5

Progressive Disclosure

Well-organized single-file structure (Commands, Research Workflow, Search Operators, Examples, Environment Variables) with no bundle files and no references needed. Not 5 because at roughly 87 lines — above the under-50-line simple-skill threshold — sections like Search Operators or Examples are approaching the size where splitting them out would aid navigation; not 3 because nothing is buried or clearly misplaced.

4 / 5

Total

17

/

20

Passed

Description

70%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.

The description is specific and distinctive, clearly naming the platform and four concrete capabilities in a compact phrase. Its main weakness is the complete absence of "when to use" trigger guidance, which caps completeness; adding a "Use when..." clause with natural phrases like "tweets" would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when researching topics, breaking news, or expert opinions on X/Twitter, or when the user mentions tweets, X threads, or Twitter profiles."

Include natural synonyms users would actually say — "tweets", "find tweets", "Twitter search" — to broaden trigger term coverage.

Mention the single-tweet fetch capability (or fold it under search) so capability coverage is comprehensive.

DimensionReasoningScore

Specificity

Lists four concrete capabilities — "search, threads, profiles, watchlists" — plus the delivery mechanism "via Composio". Not 5 because the actions are terse nouns and coverage has minor gaps (single-tweet fetch and cache management are unlisted); not 3 because it clearly exceeds 1-2 actions.

4 / 5

Completeness

The "what" is clear (search, threads, profiles, watchlists on X/Twitter via Composio) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"X/Twitter" covers both platform names and "search", "threads", "profiles", "watchlists" are terms users naturally say. Not 5 because common natural phrases like "tweets" or "find tweets" are missing; not 3 because keyword coverage is genuinely good across platform and operations.

4 / 5

Distinctiveness Conflict Risk

"X/Twitter research via Composio" carves out a clear niche with distinct, platform-specific triggers; minimal risk of firing for the wrong skill. Not 4 because the platform scoping leaves little overlap even with closely related research skills.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

alsk1992/CloddsBot

Path

src/skills/bundled/x-research/SKILL.md

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.