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

/pinterest-opportunity-radar

@2b12408
Run it yourself

Researches Pinterest Trends, seasonality, visual-search opportunities, Pinterest automation tools and destination-fit gaps to identify evidence-backed Pin clusters and growth opportunities. Use when the user asks what to publish on Pinterest, what is rising, what Pinterest automation to build, or how to turn Pinterest discovery into website traffic.

  • 1 file
  • 4.7 KB
  • MIT
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/alptugharun/ai-social-media-toolkit/pinterest-opportunity-radar

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈95 tokens for metadata: the name and description. ≈1.1k when used: this file.

Description uses 4.8% 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 ≈381 characters, or 4.8%.

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.

Pinterest Opportunity Radar

Find evidence-backed Pinterest opportunities before content production.

Required References

Read:

  • references/EVIDENCE-POLICY.md
  • references/PINTEREST-AUTOMATION-PLAYBOOK.md
  • PINTEREST-RESEARCH-FRAMEWORK.md

Use pinterest-growth-engine after the opportunity has been selected.

Evidence hierarchy

Prefer:

  1. Pinterest Trends API
  2. Pinterest Business / Trends evidence
  3. authorized account analytics
  4. current official Pinterest documentation
  5. open-source ecosystem evidence
  6. user-provided exports
  7. clearly labeled hypotheses

Never convert a hypothesis into a "trend".

Research questions

  1. Which keywords are actually rising now?
  2. Which opportunities are seasonal versus evergreen?
  3. Which visual patterns can support multiple original Pins?
  4. Which topics match a real destination page?
  5. Which content clusters are likely to produce saves versus outbound clicks?
  6. Which Pinterest automation features already have mature open-source implementations?
  7. What should be built or published next?

API-aware mode

Treat Pinterest Trends API access as a separate capability gate, not as something implied by merely having a Pinterest access token. Pinterest currently documents the Trends & Insights API for agencies, Enterprise clients and partner platforms, with a limited subset of the consumer Trends experience.

If authorized Pinterest Trends API access is available, collect region, keyword, WoW growth, MoM growth, YoY growth and time-series shape. Record the evidence date because the API currently returns today's trend data rather than arbitrary historical dates.

If a token is missing, the Trends capability is unavailable, or the endpoint returns an authorization/access-tier error, continue non-authenticated research, mark live trend evidence unavailable, and do not fabricate numbers. Do not repeatedly treat HTTP 401/403 responses as evidence that no trend exists.

Before recommending any Pinterest write automation, require a staged validation path:

  1. authenticated app access
  2. read-only connection test
  3. Pinterest API v5 Sandbox test for the intended supported operation
  4. verified board and destination mapping
  5. explicit publishing authorization
  6. production writes kept disabled by default until every prior gate passes

A successful Sandbox test proves only that the integration can execute the tested operation in Sandbox. It is not evidence of production authorization, audience demand, traffic or content performance.

Opportunity score

When live trend data exists:

  • 25% trend growth
  • 20% seasonal timing
  • 20% search / intent fit
  • 15% visual potential
  • 10% destination fit
  • 10% repeatability

When live trend data does not exist, return an incomplete score and name the missing evidence.

Output

Pinterest Opportunity Radar

Evidence Window

  • Date:
  • Regions:
  • Pinterest API status:
  • Confidence:

Rising Keywords

Keyword Region WoW MoM YoY Pattern Confidence

Seasonal Opportunities

Topic Planning window Intent Destination Evidence

Tool / Competitor Changes

Project Signal Capability Gap

Content Cluster Candidates

Cluster Intent Visual potential Destination fit Evidence Priority

Best Cluster to Build

  • Cluster:
  • Search intent:
  • Why now:
  • Destination:
  • Hero Pin:
  • Educational Pin:
  • Checklist Pin:
  • Comparison Pin:
  • Seasonal variant:
  • KPI:

Automation Recommendation

Separate automatic research, automatic draft generation, human-reviewed publishing and measurement.

Guardrails

  • No invented trend data
  • No copied Pin
  • Destination matches Pin promise
  • Trends API capability/access tier verified separately from token presence
  • API / access-tier requirements are explicit
  • Sandbox validation completed before recommending production writes
  • Board and destination mapping verified before live publishing
  • No secret committed to repository
  • Human approval before live publishing unless explicitly configured otherwise

Core Principle

Pinterest growth starts with discovery intent, not posting volume.

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
metadata
{
  "version": "0.1.2",
  "author": "Alptuğ Harun"
}

README badge

README badge for alptugharun/ai-social-media-toolkit/pinterest-opportunity-radar