sales-planhat
Planhat platform help — Health Scores, Agentic Automation, Revenue Management, CRM Sync, Enduser Tracking, Projects, NPS, REST API, MCP Server. Use when health scores aren't reflecting churn risk, CRM sync is overwriting fields or not pulling data, metrics take hours to build and formulas keep breaking, automation rules aren't triggering, revenue or license data doesn't match Salesforce, enduser tracking isn't capturing product usage, or the Planhat API returns unexpected errors. Do NOT use for general customer success strategy (use /sales-customer-success) or NPS/CSAT survey methodology (use /sales-customer-feedback).
What this skill does
# Planhat Platform Help
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated platform knowledge.
Ask the user:
1. **What area of Planhat do you need help with?**
- A) Health Scores — building composite scores, weighting indicators, debugging scores that don't reflect reality
- B) CRM Sync — Salesforce, HubSpot, or Pipedrive sync issues, field mappings, bidirectional conflicts
- C) Revenue Management — Licenses, Opportunities, Invoices, renewal tracking, ARR/MRR calculations
- D) Automation — triggers, flows, connections, code execution, actions not firing
- E) Enduser & Usage Tracking — user activity, product analytics, Segment/Mixpanel/Pendo integration
- F) Metrics & Reporting — custom metrics, calculated fields, dashboards, metric build delays
- G) REST API — creating/updating Companies, Endusers, Assets, bulk upsert, authentication
- H) MCP Server — Claude/ChatGPT integration, OAuth setup, CRUD operations
- I) NPS — sending surveys, response tracking, scoring
- J) Projects & Tasks — onboarding templates, task management, milestones
- K) Integrations — Slack, Teams, Zendesk, Intercom, Gong, data warehouse sync
- L) Admin — Service Accounts, roles, SSO, billing
2. **What CRM are you using?** (Salesforce, HubSpot, Pipedrive, none)
3. **Which Planhat plan?** (Start-Up, Professional, Enterprise, unsure)
**Skip-ahead rule:** if the user's prompt already contains enough context, skip to Step 2.
## Step 2 — Route or answer directly
| Problem domain | Route to |
|---|---|
| Customer success strategy (health score methodology, churn playbooks, expansion) | `/sales-customer-success {your question}` |
| NPS/CSAT survey design or response rate optimization | `/sales-customer-feedback {your question}` |
| Salesforce/HubSpot CRM configuration (not Planhat-specific sync) | `/sales-integration {your question}` |
| Data enrichment for customer profiles | `/sales-enrich {your question}` |
| Comparing Planhat vs Vitally vs Gainsight vs ChurnZero | `/sales-customer-success {your question}` |
When routing, provide the exact command with the user's original question.
Otherwise, answer directly using the platform reference.
## Step 3 — Planhat platform reference
**Read `references/platform-guide.md`** for the full platform reference — modules, pricing, integrations, data model, workflows.
If the question involves API endpoints, **also read `references/planhat-api-reference.md`**.
Answer the user's question using only the relevant section. Don't dump the full reference.
## Step 4 — Actionable guidance
Focus on the user's specific situation. For health score questions, walk through indicator selection and weighting. For CRM sync issues, check field mappings, sync direction, and conflict resolution rules. For metric problems, check formula syntax and the 2-3 hour build cycle. For automation issues, trace the trigger→condition→action chain.
If you discover a gotcha, workaround, or tip not covered in `references/learnings.md`, append it there.
## Gotchas
> *Best-effort from research — review these, especially items about plan-gated features and integration gotchas that may be outdated.*
- **Steep learning curve is the #1 complaint.** G2 reviewers consistently flag being overwhelmed by flexibility. Plan 3-6 weeks for full setup. Start with one module (health scores OR automation), get it working, then expand.
- **Metrics take 2-3 hours to build.** If the formula is wrong, you wait that long to find out. Test metric formulas on a small dataset first. Save frequently. Double-check before triggering a full rebuild.
- **CRM sync can overwrite fields.** Salesforce bidirectional sync + ingestion rules assume clean data. If CRM data is messy, fields get overwritten or duplicates are created. Define clear source-of-truth rules per field.
- **License ingestion assumes clean opportunity data.** Converting Salesforce opportunities to Planhat licenses requires uniform close dates, amounts, and stage names. Bad data produces bad licenses.
- **Rate limit is 200 API calls/min (soft limit).** Hard limit ~150 req/sec with up to 50 parallel. Bulk upsert supports up to 5,000 objects per request. Analytics endpoint (`analytics.planhat.com`) has separate, higher limits.
- **Email marketing is plan-gated.** Full email campaign features require add-on purchase. Don't assume email marketing is included on your plan.
- **Renewal-centric revenue model.** Most revenue calculations assume renewal-based business. If your model isn't renewal-based (usage-based, project-based), you'll need custom metric workarounds.
- **Reporting tables can't sum fields or drag columns.** Workaround: export to CSV/spreadsheet or use data warehouse sync + BI tool for advanced reporting.
- **Self-improving**: If you discover something not covered here, append it to `references/learnings.md` with today's date.
## Related skills
- `/sales-customer-success` — Customer success strategy: health scores, churn prevention, onboarding, expansion, playbook design, CS platform comparison. Install: `npx skills add sales-skills/sales --skill sales-customer-success`
- `/sales-vitally` — Vitally platform help: Health Scores, Playbooks, Projects, API — alternative CS platform. Install: `npx skills add sales-skills/sales --skill sales-vitally`
- `/sales-customer-feedback` — NPS, CSAT, CES, VoC program design — survey methodology, response rates, closed-loop feedback. Install: `npx skills add sales-skills/sales --skill sales-customer-feedback`
- `/sales-integration` — Connect Planhat to CRM, billing, and analytics tools via native integrations, Zapier, or API. Install: `npx skills add sales-skills/sales --skill sales-integration`
- `/sales-do` — Not sure which skill to use? The router matches any sales objective to the right skill. Install: `npx skills add sales-skills/sales --skill sales-do`
## Examples
### Example 1: Health score shows green for accounts that churned
**User**: "My health scores aren't predicting churn — green accounts are leaving."
**Approach**: Read platform-guide.md health scores section. Audit indicator selection — likely missing usage/engagement signals or over-weighting login frequency. Check if data sources (product analytics via Segment/Mixpanel, support tickets via Zendesk) are syncing. Recommend adding lagging indicators (support ticket trend, days since last key-feature use) and validating weights against 6-12 months of churn data. Use the 4-metric framework from /sales-customer-success if building from scratch.
### Example 2: Salesforce sync creating duplicate companies
**User**: "Every time I sync, Planhat creates duplicate companies instead of updating existing ones."
**Approach**: Read platform-guide.md CRM sync section. Check: (1) Is the external ID (Salesforce Account ID) mapped correctly as the keyable/unique identifier? (2) Are ingestion rules matching on the right field? Planhat uses "keyables" for uniqueness — if the external ID isn't set or doesn't match, it creates a new record. (3) Check the help center article on "Data Uniqueness and Keyables" for field mapping rules. Fix the keyable mapping, then deduplicate existing records via bulk upsert with the correct external IDs.
### Example 3: Custom metric formula keeps failing
**User**: "I built a metric to track expansion revenue but the formula gives wrong results and takes 3 hours to rebuild."
**Approach**: Read platform-guide.md metrics section. Check: (1) Is the formula referencing the correct license/revenue fields? (2) Are date ranges set correctly (expansion = new licenses minus renewals in period)? (3) Test on a single company first to validate before running full rebuild. Recommend using the API to pull raw license data and validate the expected values before rebuilding the metric. If the formula keeps breaking, consider a simpler metric + data warehouse calculation as a workaround.
## Troubleshooting
### CRM data not syncing or fieRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.