Foxreach Cold Outrach

Manage FoxReach cold email outreach — leads, campaigns, sequences, templates, email accounts, inbox, and analytics. Use when the user asks to create leads, m...

installs

stars

karma

SkillRank score ↗

7.3/ 10

evaluated by implexa, claude-haiku-4-5 · 2026-05-26

foxreach-io covers cold email campaign management including leads, templates, sequences, email accounts, inbox threading, and performance analytics. operations are sdk-based with pagination, filtering, and variable substitution support.

structure

9.0

trigger phrases

6.0

procedure

8.0

edge cases

6.0

documentation

8.0

strengths

view original SKILL.md from clawhubclick to expand

---
name: foxreach
description: Manage FoxReach cold email outreach — leads, campaigns, sequences, templates, email accounts, inbox, and analytics. Use when the user asks to create leads, manage campaigns, check analytics, send outreach, manage email sequences, or anything related to the FoxReach API.
argument-hint: "[resource] [action] [options]"
allowed-tools: Bash(python *), Bash(cd *), Bash(FOXREACH_API_KEY=* python *), Read, Grep, Glob
---

# FoxReach API Management Skill

You are managing the FoxReach cold email outreach platform through its Python SDK and CLI. This skill covers all API operations for leads, campaigns, sequences, templates, email accounts, inbox, and analytics.

## Setup & Authentication

The Python SDK is at `integrations/sdk-python/` and the CLI is at `integrations/cli/`. Both use API key authentication with keys prefixed `otr_`.

**Check if the SDK is available:**
```bash
python -c "from foxreach import FoxReach; print('SDK ready')"
```

**If not installed, install it:**
```bash
cd integrations/sdk-python && pip install -e .
```

**Authentication** — Always get the API key from the user or environment before making calls. Never hardcode keys. Use environment variable injection:
```bash
FOXREACH_API_KEY=otr_... python script.py
```

Or use the CLI config:
```bash
cd integrations/cli && PYTHONPATH=. python -m foxreach_cli.main config set-key --key otr_...
```

## How to Execute Operations

Write inline Python scripts using the SDK. Always follow this pattern:

```python
import json
from foxreach import FoxReach

client = FoxReach(api_key="otr_USER_KEY_HERE")

# ... perform operation ...

client.close()
```

For quick operations, use one-liners:
```bash
python -c "
from foxreach import FoxReach
client = FoxReach(api_key='otr_...')
result = client.leads.list(page_size=10)
for lead in result:
    print(f'{lead.id}  {lead.email}  {lead.status}')
print(f'Total: {result.meta.total}')
client.close()
"
```

---

## Resource Reference

For complete API details, see [api-reference.md](api-reference.md).
For usage examples of every operation, see [examples.md](examples.md).

---

## Quick Reference — Available Operations

### Leads
| Action | Method | Notes |
|--------|--------|-------|
| List | `client.leads.list(page=1, page_size=50, search=..., status=..., tags=...)` | Paginated, filterable |
| Get | `client.leads.get(lead_id)` | Returns single Lead |
| Create | `client.leads.create(LeadCreate(email=..., first_name=..., ...))` | Deduplicates by email |
| Update | `client.leads.update(lead_id, LeadUpdate(company=..., ...))` | Partial update |
| Delete | `client.leads.delete(lead_id)` | Soft-delete |

### Campaigns
| Action | Method | Notes |
|--------|--------|-------|
| List | `client.campaigns.list(status=...)` | Filter by draft/active/paused/completed |
| Get | `client.campaigns.get(campaign_id)` | Includes stats |
| Create | `client.campaigns.create(CampaignCreate(name=..., ...))` | Creates in draft |
| Update | `client.campaigns.update(campaign_id, CampaignUpdate(...))` | Can't edit if active |
| Delete | `client.campaigns.delete(campaign_id)` | Must be draft |
| Start | `client.campaigns.start(campaign_id)` | Transitions to active |
| Pause | `client.campaigns.pause(campaign_id)` | Pauses sending |
| Add Leads | `client.campaigns.add_leads(campaign_id, [lead_ids])` | Bulk add |
| Add Accounts | `client.campaigns.add_accounts(campaign_id, [account_ids])` | Assign senders |

### Sequences (nested under campaigns)
| Action | Method | Notes |
|--------|--------|-------|
| List | `client.campaigns.sequences.list(campaign_id)` | All steps |
| Create | `client.campaigns.sequences.create(campaign_id, SequenceCreate(body=..., ...))` | Add step |
| Update | `client.campaigns.sequences.update(campaign_id, seq_id, SequenceUpdate(...))` | Edit step |
| Delete | `client.campaigns.sequences.delete(campaign_id, seq_id)` | Remove step |

### Templates
| Action | Method | Notes |
|--------|--------|-------|
| List | `client.templates.list()` | Paginated |
| Get | `client.templates.get(template_id)` | Single template |
| Create | `client.templates.create(TemplateCreate(name=..., body=...))` | New template |
| Update | `client.templates.update(template_id, TemplateUpdate(...))` | Partial update |
| Delete | `client.templates.delete(template_id)` | Remove |

### Email Accounts
| Action | Method | Notes |
|--------|--------|-------|
| List | `client.email_accounts.list()` | Paginated |
| Get | `client.email_accounts.get(account_id)` | With health metrics |
| Delete | `client.email_accounts.delete(account_id)` | Remove |

### Inbox
| Action | Method | Notes |
|--------|--------|-------|
| List Threads | `client.inbox.list_threads(category=..., is_read=..., ...)` | Filterable |
| Get | `client.inbox.get(reply_id)` | Full thread |
| Update | `client.inbox.update(reply_id, ThreadUpdate(is_read=..., ...))` | Mark read/starred |

### Analytics
| Action | Method | Notes |
|--------|--------|-------|
| Overview | `client.analytics.overview()` | Dashboard KPIs |
| Campaign | `client.analytics.campaign(campaign_id)` | Metrics + daily stats |

---

## Pagination

List endpoints return `PaginatedResponse` objects:

```python
result = client.leads.list(page=1, page_size=50, search="acme")

# Access data
for lead in result:
    print(lead.email)

# Check pagination info
print(f"Page {result.meta.page}/{result.meta.total_pages}, {result.meta.total} total")

# Get next page
if result.has_next_page():
    next_result = result.next_page()

# Auto-paginate through ALL results
for lead in client.leads.list().auto_paging_iter():
    print(lead.email)
```

---

## Error Handling

Always wrap API calls in try/except:

```python
from foxreach import FoxReach, NotFoundError, RateLimitError, AuthenticationError, FoxReachError

try:
    lead = client.leads.get("cld_nonexistent")
except NotFoundError:
    print("Lead not found")
except AuthenticationError:
    print("Invalid API key")
except RateLimitError as e:
    print(f"Rate limited. Retry after {e.retry_after}s")
except FoxReachError as e:
    print(f"API error: {e}")
```

---

## Template Variables & Personalization

Email bodies support variable substitution using `{{variable}}` syntax:
- `{{firstName}}`, `{{lastName}}`, `{{email}}`
- `{{company}}`, `{{title}}`, `{{phone}}`
- `{{website}}`, `{{linkedinUrl}}`
- Custom fields: `{{customFieldName}}`

Spintax is also supported: `{Hi|Hey|Hello} {{firstName}}`

---

## Common Workflows

### 1. Full Campaign Setup
When the user wants to set up a complete campaign, follow these steps in order:
1. Create the campaign with `campaigns.create()`
2. Add sequence steps with `campaigns.sequences.create()` for each email in the chain
3. Add leads with `campaigns.add_leads()`
4. Assign email accounts with `campaigns.add_accounts()`
5. Start the campaign with `campaigns.start()`

### 2. Check Campaign Performance
1. Get campaign analytics with `analytics.campaign(id)`
2. Show sent, delivered, bounced, replied, opened stats
3. Show reply rate and bounce rate
4. If daily_stats are available, summarize trends

### 3. Manage Inbox
1. List unread threads with `inbox.list_threads(is_read=False)`
2. Categorize replies by updating with `inbox.update(id, ThreadUpdate(category="interested"))`
3. Common categories: interested, not_interested, out_of_office, wrong_person, unsubscribe

### 4. Bulk Lead Import
For adding multiple leads, create them one by one (the API deduplicates by email):
```python
leads_data = [
    {"email": "a@example.com", "first_name": "Alice", "company": "Acme"},
    {"email": "b@example.com", "first_name": "Bob", "company": "Beta"},
]
created = []
for data in leads_data:
    lead = client.leads.create(LeadCreate(**data))
    created.append(lead)
    print(f"Created: {lead.id} - {lead.email}")
```

---

## Important Notes

- **Base URL**: `https://api.foxreach.io/api/v1`
- **Rate limit**: 100 requests per minute. The SDK auto-retries on 429.
- **ID prefixes**: Leads `cld_`, Campaigns `cmp_`, Replies `rpl_`, Templates `tpl_`
- **Timezone**: All datetimes in UTC ISO 8601 format.
- **Sending days**: Array of integers, 1=Monday through 7=Sunday.
- **Sending hours**: 0-23 range, in the campaign's timezone.
- **Campaign status flow**: draft → active → paused → active → completed
- **Soft deletes**: Leads are soft-deleted and can reappear on re-import.
- Always confirm with the user before destructive operations (delete, start campaign).
- When listing data, default to showing a formatted summary, not raw JSON.
- When creating resources, confirm the details with the user before executing.

don't have the plugin yet? install it then click "run inline in claude" again.

restructured into implexa's 6-component framework with explicit decision points, edge cases (rate limits, auth expiry, empty results, validation), pagination handling, and clear input/output contracts for all foxreach operations while preserving original sdk patterns and workflows.

FoxReach Cold Outreach

intent

manage the foxreach cold email outreach platform through its python sdk and cli. use this skill when the user asks to create leads, manage campaigns, check analytics, send outreach, manage email sequences, or perform any operation on the foxreach api. covers all operations for leads, campaigns, sequences, templates, email accounts, inbox, and analytics across cold email workflows.

inputs

API Authentication

FOXREACH_API_KEY environment variable or passed directly to FoxReach() client. keys are prefixed otr_. obtain from user or secure config, never hardcode.
alternative: cli config at integrations/cli/ with foxreach_cli.main config set-key

SDK/CLI Location

python sdk: integrations/sdk-python/
cli: integrations/cli/

External Connection: FoxReach API

base url: https://api.foxreach.io/api/v1
rate limit: 100 requests per minute (sdk auto-retries on 429)
auth: api key bearer token
response format: json with PaginatedResponse or single resource objects

Installation Check

verify sdk availability: python -c "from foxreach import FoxReach; print('SDK ready')"
if missing: cd integrations/sdk-python && pip install -e .

procedure

step 1: authenticate and initialize client

input: api key (from environment or user input) output: authenticated foxreach client object

set FOXREACH_API_KEY env var or capture from user
instantiate: client = FoxReach(api_key="otr_USER_KEY")
verify connection by making lightweight call (e.g., client.analytics.overview())
on auth failure, catch AuthenticationError and prompt user for valid key

step 2: identify requested resource and action

input: user request (natural language or structured) output: resource type (leads/campaigns/sequences/templates/email_accounts/inbox/analytics) + action (list/get/create/update/delete/start/pause)

parse user intent to map to one of: leads, campaigns, sequences, templates, email_accounts, inbox, analytics
identify action: list, get, create, update, delete, start, pause, add_leads, add_accounts
confirm destructive actions (delete, start, pause) with user before execution

step 3: execute resource operation

input: resource, action, parameters (ids, filters, payload) output: api response object or paginated result

for list operations: call client.[resource].list(filters), returns PaginatedResponse
- apply filters: page, page_size, search, status, tags, category, is_read, etc.
- loop through results or use .auto_paging_iter() for all pages
for get operations: call client.[resource].get(id), returns single resource
for create operations: instantiate data class (e.g., LeadCreate(email=..., first_name=...)) then call client.[resource].create(data)
- deduplicates leads by email automatically
- confirm details with user before executing
for update operations: instantiate update class (e.g., LeadUpdate(company=...)) then call client.[resource].update(id, data) (partial update only)
for delete operations: call client.[resource].delete(id) (soft-delete for leads)
for campaign-specific: client.campaigns.start(id), client.campaigns.pause(id), client.campaigns.add_leads(id, [lead_ids]), client.campaigns.add_accounts(id, [account_ids])
for sequences (nested): client.campaigns.sequences.list(campaign_id), .create(campaign_id, SequenceCreate(...)), .update(campaign_id, seq_id, ...), .delete(campaign_id, seq_id)

step 4: handle pagination (for list operations)

input: paginated response object output: formatted summary or paginated data

check result.meta.page, result.meta.total_pages, result.meta.total
iterate through current page: for item in result: ...
fetch next page: if result.has_next_page(): next_result = result.next_page()
auto-paginate all results: for item in result.auto_paging_iter(): ...
default behavior: show formatted summary (table or list), not raw json

step 5: format and return output

input: api response output: human-readable result or structured data

for lists: present as formatted table with key fields (id, email, status, name, etc.)
for single resources: present as key-value pairs or json
include pagination info: "page X of Y, Z total results"
on errors: display error type and message with actionable guidance

step 6: close client connection

input: client object output: clean disconnection

always call client.close() after operations complete
use try/finally to ensure close is called even on exceptions

decision points

if api key missing or invalid

prompt user to provide valid FOXREACH_API_KEY
catch AuthenticationError and retry with new key
do not proceed with api calls without valid auth

if rate limit exceeded (429 error)

catch RateLimitError, extract retry_after value
wait and auto-retry (sdk does this by default)
inform user of rate limit hit if critical operation

if resource not found (404 error)

catch NotFoundError
return clear message: "lead/campaign/template not found with id: X"
ask user to verify id or list available resources

if campaign is active or paused

cannot edit active/paused campaigns (only draft campaigns are editable)
if user tries to update active campaign, catch validation error and suggest pausing first
can only delete draft campaigns; must pause/pause active ones before deletion

if user requests destructive action (delete, start campaign, pause)

explicitly confirm action with user: "delete lead X? [yes/no]"
do not execute without confirmation

if leads list is empty or search returns no results

return: "no leads found matching criteria"
suggest broadening search filters or creating new leads

if email account connection fails (health metrics show degraded)

surface account health status to user
suggest reviewing account credentials or reconnecting

if template body contains invalid syntax

validate variable syntax: {{variable}} and spintax {option1|option2}
warn user of malformed variables before saving

if creating bulk leads and deduplication occurs

inform user: "X leads skipped due to duplicate email"
show which emails were duplicated

output contract

success state:

api call completes without exception
response contains expected data structure (resource object or paginated result)
operation aligns with requested action

output format by operation:

list operations: table with columns (id, key field, status/timestamp) + pagination footer ("page X of Y, Z total")
get operations: key-value pairs or json block
create operations: confirmation message with new resource id + summary of created fields
update operations: confirmation with updated resource id + changed fields
delete operations: confirmation: "resource X deleted" or "resource X marked for deletion"
start/pause campaign: confirmation: "campaign X started/paused"
analytics: formatted dashboard summary (kpis, daily stats if available)

file outputs: none (all operations are api-based, no local file writes)

data structures: responses follow foxreach api schema

leads: id (cld_*), email, first_name, last_name, company, title, phone, website, linkedin_url, status, tags, custom fields, created_at, updated_at
campaigns: id (cmp_*), name, status (draft/active/paused/completed), sequence_count, lead_count, account_count, stats (sent, delivered, bounced, replied, opened), created_at
sequences: step order, template_id, body, delay (days), delay_unit, send_days, send_hours
templates: id (tpl_*), name, body, created_at, updated_at
email_accounts: id (acc_*), email, health (connected/degraded/disconnected), last_sync, created_at
inbox threads: id (rpl_*), sender_email, subject, body, category, is_read, is_starred, created_at
analytics: kpis (sent, delivered, bounced, replied, opened, reply_rate, bounce_rate), daily_stats (array of {date, sent, delivered, bounced, replied, opened})

outcome signal

user knows the skill worked when:

list operations: user sees formatted table or list of resources with correct count and filters applied
get operations: user sees full details of requested resource
create operations: user receives confirmation message with new resource id and can reference it in subsequent operations
update operations: user sees confirmation that fields were changed and can verify in a subsequent get call
delete operations: user sees soft-delete confirmation; lead no longer appears in list (or marked as deleted)
campaign workflow: user can see campaign transition from draft → active → paused and lead counts update correctly
analytics: user sees kpi dashboard with sent/opened/replied counts and can spot trends in daily stats
inbox: user can filter and categorize replies, mark threads as read/starred
error handling: on any failure, user receives clear error message (e.g., "lead not found: cld_123") and knows what to do next (e.g., "list all leads to find correct id")
pagination: when listing large datasets, user can navigate pages or auto-paginate without manual looping

Foxreach Cold Outrach

related skills

FoxReach Cold Outreach

intent

inputs

procedure

step 1: authenticate and initialize client

step 2: identify requested resource and action

step 3: execute resource operation

step 4: handle pagination (for list operations)

step 5: format and return output

step 6: close client connection

decision points

output contract

outcome signal