risk-cycle
Continuously identify, assess, track, and retire risks throughout the SDLC with register and RAG reporting
What this skill does
# risk-cycle
Continuous risk identification, assessment, tracking, and retirement throughout SDLC.
## Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "RAG status" / "RED/AMBER/GREEN" → risk dashboard summary
- "risk register" → update or view risk register
- "RAID log" → Risks/Assumptions/Issues/Dependencies log
## Purpose
This skill manages continuous risk management by:
- Identifying new risks from project activities
- Assessing risk severity and probability
- Tracking mitigation progress
- Escalating overdue or critical risks
- Retiring completed risk mitigations
- Generating risk reports for stakeholders
## Behavior
When triggered, this skill:
1. **Reviews current state**:
- Load risk register
- Check mitigation status
- Identify overdue items
2. **Identifies new risks**:
- Analyze recent changes
- Review technical decisions
- Check external factors
- Gather team input
3. **Assesses risks**:
- Score probability and impact
- Calculate risk score
- Prioritize by exposure
4. **Plans mitigations**:
- Assign owners
- Define mitigation actions
- Set target dates
5. **Tracks progress**:
- Update mitigation status
- Escalate overdue items
- Retire completed risks
6. **Reports status**:
- Generate risk dashboard
- Highlight top risks
- Show trend over time
## Risk Categories
### Technical Risks
```yaml
technical_risks:
architecture:
examples:
- Scalability bottleneck
- Single point of failure
- Technology obsolescence
- Integration complexity
indicators:
- Performance degradation
- System failures
- Upgrade difficulties
development:
examples:
- Technical debt accumulation
- Code quality issues
- Testing gaps
- Dependency vulnerabilities
indicators:
- Increasing bug count
- Slower velocity
- Failed deployments
security:
examples:
- Data breach potential
- Authentication weaknesses
- Compliance gaps
- Third-party risks
indicators:
- Security scan findings
- Audit failures
- Incident reports
```
### Project Risks
```yaml
project_risks:
schedule:
examples:
- Scope creep
- Delayed dependencies
- Unrealistic estimates
- Resource constraints
indicators:
- Missed milestones
- Velocity decline
- Scope changes
resource:
examples:
- Key person dependency
- Skill gaps
- Team turnover
- Burnout risk
indicators:
- Unbalanced workload
- Low morale
- Resignation signals
stakeholder:
examples:
- Changing requirements
- Sponsor availability
- Organizational changes
- Competing priorities
indicators:
- Decision delays
- Priority conflicts
- Reduced engagement
```
### External Risks
```yaml
external_risks:
market:
examples:
- Competitor actions
- Market shift
- Economic factors
- Regulatory changes
indicators:
- Market news
- Competitor releases
- Industry reports
vendor:
examples:
- Vendor stability
- API changes
- Price increases
- Support quality
indicators:
- Vendor communications
- Service issues
- Contract terms
compliance:
examples:
- Regulatory requirements
- Industry standards
- Audit requirements
- Data regulations
indicators:
- Regulatory updates
- Audit findings
- Compliance gaps
```
## Risk Assessment Matrix
### Probability Scoring
```yaml
probability:
certain:
score: 5
likelihood: ">90%"
description: "Almost certain to occur"
likely:
score: 4
likelihood: "60-90%"
description: "More likely than not"
possible:
score: 3
likelihood: "30-60%"
description: "Could occur"
unlikely:
score: 2
likelihood: "10-30%"
description: "Not expected but possible"
rare:
score: 1
likelihood: "<10%"
description: "Very unlikely"
```
### Impact Scoring
```yaml
impact:
catastrophic:
score: 5
schedule: ">3 months delay"
cost: ">50% budget"
quality: "Unusable product"
reputation: "Major damage"
major:
score: 4
schedule: "1-3 months delay"
cost: "25-50% budget"
quality: "Significant defects"
reputation: "Serious concern"
moderate:
score: 3
schedule: "2-4 weeks delay"
cost: "10-25% budget"
quality: "Noticeable issues"
reputation: "Some concern"
minor:
score: 2
schedule: "1-2 weeks delay"
cost: "5-10% budget"
quality: "Minor issues"
reputation: "Limited impact"
negligible:
score: 1
schedule: "<1 week delay"
cost: "<5% budget"
quality: "Trivial issues"
reputation: "No impact"
```
### Risk Score Matrix
```
│ Impact
│ 1 2 3 4 5
───────────┼─────────────────────
Prob 5 │ 5 10 15 20 25 ←Critical
4 │ 4 8 12 16 20
3 │ 3 6 9 12 15 ←High
2 │ 2 4 6 8 10
1 │ 1 2 3 4 5 ←Medium
└─────────────────────
↑ ↑
Low Medium
```
```yaml
risk_levels:
critical:
range: [20, 25]
response: "Immediate action required"
escalation: "Executive notification"
high:
range: [12, 19]
response: "Priority mitigation"
escalation: "Manager notification"
medium:
range: [6, 11]
response: "Planned mitigation"
escalation: "Team lead notification"
low:
range: [1, 5]
response: "Monitor and accept"
escalation: "None required"
```
## Risk Register Format
```markdown
# Risk Register
**Project**: [Name]
**Last Updated**: 2025-12-08
**Next Review**: 2025-12-15
## Summary Dashboard
| Risk Level | Count | Trend |
|------------|-------|-------|
| Critical | 1 | ↑ +1 |
| High | 3 | → 0 |
| Medium | 8 | ↓ -2 |
| Low | 12 | → 0 |
| **Total** | **24** | - |
### Risk Trend
```
Week 1: ████████████████████████ 24 risks
Week 2: ██████████████████████ 22 risks
Week 3: ████████████████████████ 24 risks (2 new)
Week 4: ████████████████████████ 24 risks
↑ Stable with critical +1
```
## Active Risks
### RISK-001: Database Scalability [CRITICAL]
| Attribute | Value |
|-----------|-------|
| ID | RISK-001 |
| Title | Database Scalability Bottleneck |
| Category | Technical / Architecture |
| Probability | 4 (Likely) |
| Impact | 5 (Catastrophic) |
| Score | 20 (Critical) |
| Owner | Sarah Chen |
| Status | Mitigating |
**Description**:
Current PostgreSQL single-instance architecture cannot handle projected 10x traffic growth. Performance degradation expected within 6 months.
**Impact if Realized**:
- Service degradation or outage
- Customer churn
- Revenue loss estimated at $500K/month
**Mitigation Plan**:
1. [x] Evaluate sharding options (complete)
2. [x] Design read replica architecture (complete)
3. [ ] Implement connection pooling (in progress, due Dec 15)
4. [ ] Deploy read replicas (planned, due Jan 15)
5. [ ] Implement sharding (planned, due Feb 15)
**Contingency**:
Emergency vertical scaling + temporary traffic limiting
**Progress**:
```
[████████████░░░░░░░░] 60%
```
---
### RISK-002: Key Person Dependency [HIGH]
| Attribute | Value |
|-----------|-------|
| ID | RISK-002 |
| Title | Key Person Dependency on Lead Architect |
| Category | Project / Resource |
| Probability | 3 (Possible) |
| Impact | 4 (Major) |
| Score | 12 (High) |
| Owner | David Kim |
| Status | Mitigating |
**Description**:
Lead architect holds critical system knowledge. No backup identified.
**Mitigation Plan**:
1. [ ] Document architecture decisions (in progress)
2. [ ] Schedule knowledge transfer sessions
3. [ ] Identify and train backup
---
## Recently Retired Risks
### RISK-012: Third-Party ARelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.