SKILLEMALL.ai

AB building-full-social-audit-for-brand

Builds a comprehensive social media audit for a brand across all major platforms using apidojo's multi-platform scrapers. Triggers when the user asks to: do a social media audit for a brand, build a full social media presence report, analyze a brand's performance across all social platforms, create a cross-platform social media benchmark, audit a competitor's entire social media strategy, build a social media scorecard for a brand, or create a comprehensive social media analysis covering Twitter Instagram TikTok and YouTube. Returns per-platform metrics, follower counts, engagement rates, content mix, posting frequency, and overall brand health score. Ideal for social media managers, brand strategists, and agency teams doing comprehensive brand audits.

ClawHub Agent Skills author: API Dojo v1.0.0 MIT-0 2 files body ≈ 979 tokens Open the sourceclawhub.ai analyzed 3 d ago

Builds a comprehensive social media audit for a brand across all major platforms using apidojo's multi-platform scrapers.

As a process B 71/100 · Nearly there — weak spots: running it twice, progress reporting

AnalyzerYouTubeMarketingtype and topics are labelled automatically from the skill text
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
97
Quality 40%
88
Run on models
none yet
Process rating
B
71/100
Nearly there
Progress reporting w 2
0
Running it twice w 4
30
Failures and branches w 10
50
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 3

    ✓ No critical or high findings

    Medium and low: 3
    • low Exfiltration exfil-secret-in-url SKILL.md:86
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      "https://api.apify.com/v2/acts/apidojo~twitter-user-scraper/runs?token=…" \
      placeholder
    • low Exfiltration exfil-secret-in-url SKILL.md:93
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      curl "https://api.apify.com/v2/actor-runs/$RUN_ID/dataset/items?token=…"
      placeholder
    • low Exfiltration net-credential-use SKILL.md:93
      Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
      curl "https://api.apify.com/v2/actor-runs/$RUN_ID/dataset/items?token=…"
      security skill

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 71/100

    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 3 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 6 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 979 tokens

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +2Single-language instructions
    • +3Description length 762: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 6 items
    • +3Output format is stated explicitly
    • +4Has examples (8 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: suspicious
    The skill appears intended for social-media auditing, but it overstates its multi-platform capability and handles an Apify credential in a risky way.
    LLM: suspicious (high) · 3 Sept 2026