CtrlK
BlogDocsLog inGet started
Tessl Logo

andrebrov/viral-scout

Find high-performing short-form videos on AI × e-commerce topics across YouTube and Instagram, in English and Russian, filtered by view count. Presents a shortlist for the user to pick from, then saves the picks to the shared reel backlog with a note on what format or hook is worth stealing. Use when the user asks what is working on video right now, wants viral video references, wants ideas for what to shoot, or says "viral scout" / "what's popping". Research and selection only — no video is produced here.

77

Quality

97%

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

Overview
Quality
Evals
Security
Files

Quality

Content

93%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 tight, actionable workflow document: executable commands, a real externalized script, an explicit human-in-the-loop gate, and disciplined reject/keep criteria. The only gap is a missing append-verification/feedback loop on the backlog save, which keeps workflow clarity just below full marks.

Suggestions

Add an explicit verification step after appending to backlog/ideas.json (e.g., re-read the file to confirm the new entry landed and its JSON is valid) to turn the save into a validate→retry loop and lift workflow_clarity to 5.

Make the shortlist table's expected output explicit (a concrete 2–3 row example with the columns filled) so Step 2's deliverable is unambiguous beyond the header row.

DimensionReasoningScore

Conciseness

Lean prose that assumes Claude's competence; the only explanatory passage (reading each platform's embedded JSON instead of scraping) is the genuinely non-obvious method, not basic-concept padding. Every section earns its place.

5 / 5

Actionability

Fully executable, copy-paste-ready bash invoking the real scripts/find_viral.py with concrete flags and thresholds, plus a concrete JSON backlog-entry template; examples cover both the EN and RU cases.

5 / 5

Workflow Clarity

Clear Step 1 → Step 2 → Gate → Step 3 sequence with an explicit user-pick checkpoint and a reject-on-sight checklist, but no verification that the backlog append succeeded and no error-recovery feedback loop, which the anchor-5 calls for. It is above a 3 because the gate is a genuine validation checkpoint.

4 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled, one-level-deep reference to scripts/find_viral.py (a verified real file holding implementation detail); no nested references, and no bulk content inlined that belongs in a separate file.

5 / 5

Total

19

/

20

Passed

Description

100%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.

An exemplary description: third-person voice, concrete actions, explicit what-and-when with natural trigger phrases, a distinctive niche, and a clear scope boundary. No fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Find high-performing short-form videos... filtered by view count", "Presents a shortlist for the user to pick from", "saves the picks to the shared reel backlog with a note on what format or hook is worth stealing" — with comprehensive coverage of the skill's purpose.

5 / 5

Completeness

Explicitly answers both what (find/filter/shortlist/save-to-backlog) and when via a concrete "Use when..." clause with multiple trigger phrases; no inference needed.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say — "what is working on video right now", "viral video references", "ideas for what to shoot", plus the invocation terms "viral scout" and "what's popping".

5 / 5

Distinctiveness Conflict Risk

A clear niche (AI × e-commerce short-form video research across YouTube/Instagram in EN+RU) with distinctive triggers and an explicit scope boundary ("Research and selection only — no video is produced here"), minimizing conflict risk.

5 / 5

Total

20

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents