Social channel analysis
Skill duandigi/duandigi-growth-marketing-skill/skills/social-channel-analysis
Use this skill when analyzing organic or paid social performance across content, formats, topics, creators, pages, profiles, audiences, reach, engagement, traffic, leads, assisted outcomes, and content operations.From its SKILL.md
npx -y skills add duandigi/duandigi-growth-marketing-skill --skill social-channel-analysisAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.7 KB, 625 tokens by cl100k_base, as published. Nobody here has run it
Social Channel Analysis
Purpose
Determine which social activities create awareness, consideration, traffic, leads, retention, or referral rather than ranking posts by engagement alone.
Inputs
- Platform content, profile, audience, reach, engagement, click, and video data
- Publishing cadence, format, topic, creator, campaign, and creative metadata
- Analytics, UTM, CRM, assisted-conversion, and revenue data
- Brand, moderation, platform-policy, and production constraints
If a required input is unavailable, label it unknown, state how it limits the decision, and create a collection, mapping, validation, or instrumentation task. Never invent credentials, assets, metrics, permissions, or business outcomes.
Workflow
- Define the role of each account and content pillar in the growth model.
- Validate platform metrics, tracking links, attribution limitations, and content taxonomy.
- Analyze reach quality, engagement quality, traffic, lead quality, assisted outcomes, follower or audience growth, and operational efficiency.
- Drill down by format, topic, hook, CTA, creator, posting time, distribution method, and destination page.
- Detect fatigue, overreliance on vanity engagement, weak message-match, inconsistent cadence, and content that assists later conversion.
- Separate organic learning from paid amplification effects.
- Recommend content experiments, distribution changes, repurposing, landing-page alignment, or measurement fixes.
Required output
Return a concise, decision-oriented result containing:
- Social channel role and health summary
- Content-pillar, format, topic, and CTA findings
- Awareness, traffic, lead, and assisted-outcome analysis
- Operational and measurement constraints
- Prioritized content and distribution experiments
Label material statements as confirmed, calculated, inferred, assumed, or unknown. Include the data period, last complete period, source lineage, and confidence whenever they can change the decision.
Guardrails
-
Do not treat likes, comments, or followers as business outcomes without context.
-
Do not recommend fake engagement, impersonation, unsolicited bulk messaging, or policy evasion.
-
Do not compare platform reach as if it represented deduplicated people across networks.
-
Do not attribute later branded search entirely to social without evidence.
-
Do not claim guaranteed growth or present an estimate as observed fact.
-
Do not reveal secrets, personal data, private provider payloads, or cross-project information.
-
When an action can spend money, publish, contact people, alter access, modify production, or delete data, prepare an approval request instead of executing automatically.
Completion check
Before finishing, verify that the output:
- answers a specific business or implementation decision;
- uses the correct organization, project, asset, date range, time zone, and currency;
- separates performance problems from data, connection, and attribution problems;
- includes evidence, uncertainty, affected scope, and a measurable next step;
- respects least privilege, approval, audit, and rollback requirements;
- is no longer than necessary for the decision.
What ships with it: 1 file
875 B alongside SKILL.md
evals/
- evals.json875 B
Gives 0 of the 12 instructions most research analysis skills give in 625 tokens
Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-07
- Generate a markdown reportin 32 of 1063, across 23 files
- Cite each claim's sourcein 30 of 1063, across 15 files
- Define the ideal customer profilein 20 of 1063, across 2 files
- Search for companies matching the criteriain 20 of 1063, across 2 files
- Assign a fit score from one to tenin 20 of 1063, across 2 files
- Analyze the codebase to understand the productin 19 of 1063, across 1 file
- Ask clarifying questions about the value propositionin 19 of 1063, across 1 file
- Look for signals of immediate needin 19 of 1063, across 1 file
- Identify the target decision maker rolein 19 of 1063, across 1 file
- Suggest a personalized contact strategyin 19 of 1063, across 1 file
- Provide conversation starters for outreachin 19 of 1063, across 1 file
- Format results in a scannable markdown templatein 19 of 1063, across 1 file
Said here and by no other author read
- label unavailable inputs as unknown
- define the role of each account
- validate platform metrics and tracking links
- analyze reach and engagement quality
- drill down by format, topic, and creator
- separate organic learning from paid effects
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.