30 Day Action Plan

What it does

Convert analytical findings from at least two other approved skills using FullMention payloads into a highly structured, execution-ready 30-day action plan distributed over a 4-week timeline.

Execution Contract

Every execution of this skill must operate under the following contract:
- **ingestion_plan**: A documented plan for pulling data.
- **max_api_calls**: 3 (default, strictly enforced).
- **cache_key**: A unique key identifying the cached API dataset.
- **dataset_timestamp**: ISO timestamp of the ingested dataset.
- **analysis_mode**: `offline_only`

Data Access Policy

• API Target: Consume data from the FullMention API at GET /v2/runs/{runId}.
• Controlled Ingestion: Perform exactly one controlled ingestion pull from the FullMention API. Paginated batch fetching is preferred.
• API Decoupling: Do NOT treat the FullMention API as a persistent database or state-store; it is a read-only snapshot provider.
• 24-Hour TTL: FullMention v2 deletes run data after 24 hours, meaning offline persistence/database caching is a strict requirement for historical tracking.
• Local Persistence: Save all analytical outputs locally in the current workspace directory.
  • Raw structured JSON must be saved to [skill_name].json (e.g. 30-day-action-plan.json).
  • A premium, beautifully styled markdown report must be saved to [skill_name].md (e.g. 30-day-action-plan.md).
• Caching: Reuse the same stored dataset across iterative prompts. Do not repeat identical API calls.
• Refresh Window: Make additional API calls only if the user explicitly requests a refresh window or a missing page fetch.
• Rate Limits & Backoff: Respect API rate limits and backoff policies. Never run open-ended call loops.
• Allowed Sources:
  • Outputs from at least 2 approved skills using FullMention payloads (e.g., Share of Voice Snapshot, Gap Analysis, Top 20 Over Time, etc.).
  • Optional user-provided local file/DB snapshot (read-only).
  • No repeated API fetching during analysis.

Required Input Fields & Parameters

The input dataset from the approved analytical skills must map to these fields:

• findings[].id (string, unique finding identifier)
• findings[].metric (string, name of the analyzed metric)
• findings[].delta (string/number, calculated delta or change)
• findings[].evidence (string/object, source evidence backing the finding)

Analytical Method

Follow these step-by-step logic rules during analysis:

1. Impact Categorization: Group proposed actions by business/technical impact: high, medium, or low.
2. Owner & Metrics Allocation: Assign a specific owner type (e.g., Content Team, Technical SEO, PPC Manager) and a measurable success metric to each proposed action.
3. Weekly Scheduling: Distribute the prioritized actions across a 4-week timeline (week_1, week_2, week_3, week_4). High impact, urgent actions should be placed in earlier weeks.
4. Action Limitation: Select and refine a maximum of 12 highly relevant and feasible actions.

Expected Output

The skill must generate two outputs in the local workspace:

1. 30-day-action-plan.json: Contains the raw structured analytical output, including the execution contract metadata, prioritized week-by-week actions list, assumptions, dependencies, confidence metrics, and the evidence map.

2. 30-day-action-plan.md: A premium, beautiful human-readable report. This report must contain:

   • 30-Day Executive Summary: Formatted calendar or week-by-week checklist.
   • Week-by-Week Action Items: Max 12 actions detailed with:
     • Priority (High/Medium/Low)
     • Owner (Owner Type)
     • Success Metric
     • Target Week (Week 1 to Week 4)
     • Associated Finding ID
   • Assumptions & Dependencies: Detailed lists of operational or technical assumptions and dependencies.
   • Confidence & Limitations:
     • A confidence score from 0-100.
     • Confidence Rationale: Explanation of how the confidence score was derived.
     • Limitations: A list of data limitations or gaps.
   • Evidence Map: An array of objects evidence_map[] with:
     • finding_id
     • metric_name
     • source_field_paths[]
     • sample_result_ids[]

Guardrails & Constraints

• Finding Mapping Constraint: Every proposed action item must explicitly map to a valid, verified finding from the input analytical reports. No actions may be proposed without direct finding references.
• No Web Lookups: Do not perform external web lookups or enrichment of brand data.
• No Hallucination: Do not invent findings, brands, or evidence that are not present in the input datasets.

Copy-ready Skill Prompt

Use this as a full copy/paste prompt in your AI tool:

Skill: 30 Day Action Plan
Goal: Convert analytics findings into execution-ready actions.

Data Access Policy:
- **API Target**: Consume data from the FullMention API at `GET /v2/runs/{runId}`.
- **Controlled Ingestion**: Perform exactly one controlled ingestion pull from the FullMention API. Paginated batch fetching is preferred.
- **API Decoupling**: Do NOT treat the FullMention API as a persistent database or state-store; it is a read-only snapshot provider.
- **24-Hour TTL**: FullMention v2 deletes run data after 24 hours, meaning offline persistence/database caching is a strict requirement for historical tracking.
- **Local Persistence**: Save all analytical outputs locally in the current workspace directory.
  - Raw structured JSON must be saved to `[skill_name].json` (e.g. `30-day-action-plan.json`).
  - A premium, beautifully styled markdown report must be saved to `[skill_name].md` (e.g. `30-day-action-plan.md`).
- **Caching**: Reuse the same stored dataset across iterative prompts. Do not repeat identical API calls.
- **Refresh Window**: Make additional API calls only if the user explicitly requests a refresh window or a missing page fetch.
- **Rate Limits & Backoff**: Respect API rate limits and backoff policies. Never run open-ended call loops.
- **Allowed Sources**:
  - Outputs from at least 2 approved skills using FullMention payloads (e.g., Share of Voice Snapshot, Gap Analysis, Top 20 Over Time, etc.).
  - Optional user-provided local file/DB snapshot (read-only).
  - No repeated API fetching during analysis.

Input Fields & Params:
The input dataset from the approved analytical skills must map to these fields:
- `findings[].id` (string, unique finding identifier)
- `findings[].metric` (string, name of the analyzed metric)
- `findings[].delta` (string/number, calculated delta or change)
- `findings[].evidence` (string/object, source evidence backing the finding)

Method:
Follow these step-by-step logic rules during analysis:
1. **Impact Categorization**: Group proposed actions by business/technical impact: `high`, `medium`, or `low`.
2. **Owner & Metrics Allocation**: Assign a specific `owner type` (e.g., Content Team, Technical SEO, PPC Manager) and a measurable `success metric` to each proposed action.
3. **Weekly Scheduling**: Distribute the prioritized actions across a 4-week timeline (`week_1`, `week_2`, `week_3`, `week_4`). High impact, urgent actions should be placed in earlier weeks.
4. **Action Limitation**: Select and refine a maximum of 12 highly relevant and feasible actions.

Expected Output:
The skill must generate two outputs in the local workspace:

1. **`30-day-action-plan.json`**:
   Contains the raw structured analytical output, including the execution contract metadata, prioritized week-by-week actions list, assumptions, dependencies, confidence metrics, and the evidence map.

2. **`30-day-action-plan.md`**:
   A premium, beautiful human-readable report. This report must contain:
   - **30-Day Executive Summary**: Formatted calendar or week-by-week checklist.
   - **Week-by-Week Action Items**: Max 12 actions detailed with:
     - `Priority` (High/Medium/Low)
     - `Owner` (Owner Type)
     - `Success Metric`
     - `Target Week` (Week 1 to Week 4)
     - `Associated Finding ID`
   - **Assumptions & Dependencies**: Detailed lists of operational or technical assumptions and dependencies.
   - **Confidence & Limitations**:
     - A confidence score from 0-100.
     - **Confidence Rationale**: Explanation of how the confidence score was derived.
     - **Limitations**: A list of data limitations or gaps.
   - **Evidence Map**: An array of objects `evidence_map[]` with:
     - `finding_id`
     - `metric_name`
     - `source_field_paths[]`
     - `sample_result_ids[]`

Guardrails:
- **Finding Mapping Constraint**: Every proposed action item must explicitly map to a valid, verified finding from the input analytical reports. No actions may be proposed without direct finding references.
- **No Web Lookups**: Do not perform external web lookups or enrichment of brand data.
- **No Hallucination**: Do not invent findings, brands, or evidence that are not present in the input datasets.