Index of every page on this site: llms.txt
All skills
alptugharun avatar

/comment-intelligence

@2b12408
Run it yourself

Turns public or user-provided social comments into evidence-backed audience intelligence: recurring questions, objections, pain points, buying signals, vocabulary, content gaps, and testable content ideas. Use for voice-of-customer research, comment mining, audience research, product-demand research, FAQ discovery, and content planning.

  • 1 file
  • 3 KB
  • MIT
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/alptugharun/ai-social-media-toolkit/comment-intelligence

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈90 tokens for metadata: the name and description. ≈645 when used: this file.

Description uses 4.5% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈361 characters, or 4.5%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Comment Intelligence

Turn comment sections into audience evidence, not a pile of anecdotes.

Inputs

Accept comments supplied by the user or collected from public sources the runtime can legitimately access. Useful fields include:

  • comment text
  • source URL / post ID
  • platform
  • date
  • likes or replies when available
  • creator / brand / topic

Do not claim access to private, deleted, login-gated, or unavailable comments.

Workflow

  1. Define the research question before clustering comments.
  2. Remove obvious spam, duplicates, bot-like repetition, and context-free noise when justified.
  3. Preserve source references so findings remain auditable.
  4. Cluster comments by meaning rather than keyword alone.
  5. Separate observed language from analyst interpretation.
  6. Rank themes using frequency plus strength of intent, not frequency alone.
  7. Extract representative short phrases only when allowed; otherwise paraphrase.
  8. Convert strong themes into hypotheses and content tests.

Signal Types

Look for:

  • repeated questions
  • objections and friction
  • pain points
  • desired outcomes
  • misconceptions
  • comparisons and alternatives
  • purchase / signup / download intent
  • requests for tutorials or examples
  • emotional language
  • recurring audience vocabulary
  • missing information
  • positive proof and reasons people care

Evidence Rules

Never infer precise demographics, sentiment percentages, market size, or purchase probability unless the data supports them.

A loud minority is not automatically representative. Distinguish:

  • Repeated signal — appears across multiple independent comments
  • Strong single signal — specific and useful but not repeated
  • Hypothesis — plausible interpretation requiring testing

When engagement counts are available, treat them as context rather than proof that a comment represents the whole audience.

Output

Comment Intelligence Brief

Research Question

[Question]

Dataset

  • Sources:
  • Comments reviewed:
  • Date range:
  • Important limitations:

Signal Table

Theme Signal type Evidence strength Audience language Interpretation

Questions & Objections

[Prioritized list]

Content Opportunities

Opportunity Evidence Format Hook hypothesis Test

Product / Offer Signals

[Only when supported]

Watchlist

[Weak or emerging signals worth monitoring]

Recommended Next Tests

Prioritize a small number of measurable tests. Keep evidence separate from creative recommendations.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 2b12408. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 days ago.

Activeupdated 2 months ago

README badge

README badge for alptugharun/ai-social-media-toolkit/comment-intelligence