mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-11 19:47:12 +03:00
Magnus HedemarkGitHubusername <username>factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>Add a conditional skill for products with recurring human relationships. Covers success plans, health evidence, renewal/expansion signals, QBRs, handoffs, escalation, and closed-loop Voice of Customer. The skill is conditional: it declines and routes away when the product has no accounts, renewals, QBRs, or customer-success team. Includes: - SKILL.md with conditional frontmatter, trigger sections, four product- model adaptations (B2B subscription, transactional, public-service, internal product), core artifacts, privacy and human-judgment boundaries, and routing to product-analytics-and-measurement, product-adoption, product-experimentation, go-to-market, and product-lifecycle-learning. - README.md with all five required human-facing sections. - references/discovery-brief.md surveying existing content and defining ownership boundaries and routing. - references/privacy-and-human-judgment.md with consent framework, surveillance-risk guidance, decision-support rules, and data classification tiers. - templates/applicability-decision.md, templates/success-plan.md, templates/health-risk-record.md, and templates/escalation-and- feedback-closure.md. - evals/evals.json with 5 output-quality cases covering B2B subscription, internal-tool decline (negative trigger), public-service routing, renewal-risk with mixed signals, and conflicting health evidence. - Updated root README.md catalog section, references/skill-triggers.md, and regenerated marketplace/Codex/llms.txt catalogs. Co-authored-by: username <username> Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
4.6 KiB
4.6 KiB
Health / Risk Record
An evidence-based record — never an automated score. For each health dimension, capture the signal, source, trend, confidence, and any conflicting signals. Surface disagreement, never average it away.
Account Context
- Customer: [name or identifier]
- Product model: [B2B Subscription / Transactional / Public Service / Internal Product]
- Review date: [date]
- Reviewer: [name or role]
- Previous review date: [date]
Health Dimensions
1. Adoption Health
Evidence from product-adoption signals.
| Signal | Source | Value | Trend | Confidence |
|---|---|---|---|---|
| Activation rate | [analytics] | [value] | [↑/→/↓] | [high/med/low] |
| Feature adoption breadth | [analytics] | [value] | [↑/→/↓] | [high/med/low] |
| Sustained use (weekly active) | [analytics] | [value] | [↑/→/↓] | [high/med/low] |
| Time-to-value | [analytics] | [value] | [↑/→/↓] | [high/med/low] |
Dimension assessment: [healthy / watch / at-risk]
Conflicting signals (if any):
- [Signal A says healthy, Signal B says at-risk. Explanation: ...]
- Resolution path: [what to investigate, who decides]
2. Engagement Health
Evidence from direct customer interaction.
| Signal | Source | Value | Trend | Confidence |
|---|---|---|---|---|
| QBR attendance / engagement | [CS observation] | [value] | [↑/→/↓] | [high/med/low] |
| Responsiveness to outreach | [CS observation] | [value] | [↑/→/↓] | [high/med/low] |
| Support-ticket volume | [support system] | [value] | [↑/→/↓] | [high/med/low] |
| Support-ticket sentiment | [support system] | [value] | [↑/→/↓] | [high/med/low] |
Dimension assessment: [healthy / watch / at-risk]
Conflicting signals (if any): [record here]
3. Value Realization Health
Evidence that the customer is achieving their desired outcomes.
| Signal | Source | Value | Trend | Confidence |
|---|---|---|---|---|
| Success-plan milestone achievement | [success plan] | [value] | [↑/→/↓] | [high/med/low] |
| Outcome metric vs. target | [analytics] | [value] | [↑/→/↓] | [high/med/low] |
| Expansion / deepening signals | [CS observation] | [value] | [↑/→/↓] | [high/med/low] |
Dimension assessment: [healthy / watch / at-risk]
Conflicting signals (if any): [record here]
4. Relationship Health
Evidence about the human relationship quality.
| Signal | Source | Value | Trend | Confidence |
|---|---|---|---|---|
| Executive sponsor engagement | [CS observation] | [value] | [↑/→/↓] | [high/med/low] |
| Reference / advocacy willingness | [CS observation] | [value] | [↑/→/↓] | [high/med/low] |
| Contract / renewal posture | [CS observation] | [value] | [↑/→/↓] | [high/med/low] |
| Unresolved escalations | [escalation record] | [value] | [↑/→/↓] | [high/med/low] |
Dimension assessment: [healthy / watch / at-risk]
Conflicting signals (if any): [record here]
5. Risk Assessment (Non-Health)
External or structural risks that are not health-dimension signals.
| Risk | Likelihood | Impact | Mitigation | Owner |
|---|---|---|---|---|
| [e.g., customer org restructure] | [high/med/low] | [high/med/low] | [mitigation] | [name] |
| [risk] | [likelihood] | [impact] | [mitigation] | [owner] |
Overall Health Summary
This is a narrative synthesis, not a score.
- Strongest dimension(s): [which dimensions have clear, positive evidence]
- Weakest dimension(s): [which dimensions have weak or negative evidence]
- Key conflicting signals: [which signals disagree and what the conflict suggests]
- Trend direction: [improving / stable / declining / mixed]
- Recommended action: [none / watch / investigate / escalate]
Decision Path (if conflicting evidence exists)
When health signals conflict (e.g., adoption is strong but support-sentiment is declining), the record must:
- Surface the conflict — name both signals explicitly.
- Propose an explanation — what could explain the disagreement?
- Define an investigation path — what additional evidence would resolve the conflict?
- Assign a decision-maker — who decides the next action?
- Set a review date — when will the conflict be re-examined?
This ensures the conflict is not buried in an average or a single "green / yellow / red" indicator.
Previous Assessments
| Date | Overall | Key Change | Reviewer |
|---|---|---|---|
| [date] | [assessment] | [what changed since prior review] | [name] |