Detects when user requests warrant critical analysis via /advise command
npx skills add https://github.com/majiayu000/claude-skill-registry --skill advisor-triggers
Detect patterns in user requests that indicate a need for critical thinking analysis. Suggests running /advise when users propose significant changes without first considering trade-offs.
Triggers:
Examples:
Why advise? New dependencies increase complexity and maintenance burden.
Triggers:
Examples:
Why advise? Architectural changes have far-reaching implications.
Triggers:
Examples:
Why advise? Scope creep can derail projects.
Triggers:
Examples:
Why advise? Tech replacements have migration costs.
Triggers:
Examples:
Why advise? Premature optimization is common.
function shouldInvokeAdvisor(userRequest: string): boolean {
const triggers = [
// Dependencies
/add (redis|mongodb|postgres|graphql|webpack|docker)/i,
/use (tensorflow|pytorch|react|vue|angular)/i,
/integrate (stripe|auth0|sendgrid|aws)/i,
/switch to (typescript|rust|go|kubernetes)/i,
// Architecture
/refactor to (microservices|serverless|event-driven)/i,
/restructure as/i,
/migrate to/i,
/convert to/i,
// Scope
/also add/i,
/extend to/i,
/support (mobile|multi-tenant|real-time|offline)/i,
// Technology replacement
/instead of/i,
/replace \w+ with/i,
/swap \w+ for/i,
// Scale
/scale to/i,
/handle \d+[kmb]/i, // 1k, 1m, 1b
/support \d+k/i,
];
return triggers.some((pattern) => pattern.test(userRequest));
}
When trigger detected:
⚠️ **Significant decision detected**
Your request involves [architecture change / new dependency / scope expansion].
Consider running critical analysis first:
/advise "{user's proposal}"
This will provide:
- Alignment check with PROJECT.md
- Complexity assessment
- Trade-off analysis
- Alternative approaches
- Risk identification
Takes 2-3 minutes, could save weeks.
Proceed with analysis? [Y/n]
# .claude/config.yml
advisor_triggers:
enabled: true
# Sensitivity
sensitivity: medium # low | medium | high
# Specific triggers
triggers:
new_dependencies: true
architecture_changes: true
scope_expansions: true
technology_swaps: true
scale_changes: true
# Auto-invoke (don't ask, just run)
auto_invoke: false # If true, runs /advise automatically
User: "Let's add Redis caching"
↓
advisor-triggers: Detected new dependency
↓
[Suggest /advise]
↓
User: Accepts suggestion
↓
/advise "Add Redis caching"
↓
User: Reviews analysis, decides
↓
/plan [chosen approach]
User: "/auto-implement add WebSocket support"
↓
advisor-triggers: Detected architecture change
↓
[Suggest /advise first]
↓
User: Either runs /advise or proceeds anyway
orchestrator receives feature request
↓
Check advisor-triggers
↓
IF significant decision detected
↓
Invoke advisor agent first
↓
Present analysis to user
↓
THEN proceed with planning
Some requests trigger falsely:
False Positive:
Solution: Context-aware detection:
// Only trigger if action verb present
if (containsActionVerb(request) && containsTriggerKeyword(request)) {
return true;
}
Users can bypass:
# Explicit skip
/plan --skip-advisor "Add Redis caching"
# Or acknowledge in prompt
"Add Redis caching (already analyzed, proceeding)"
This skill is successful if:
User: "Let's add Elasticsearch for search"
⚠️ Significant decision detected
Your request involves adding a new dependency (Elasticsearch).
Consider critical analysis first:
/advise "Add Elasticsearch for full-text search"
This will check:
- Alignment with PROJECT.md goals
- Complexity cost (Elasticsearch cluster, maintenance)
- Alternatives (PostgreSQL full-text search, simple indexing)
- Trade-offs (features vs operational complexity)
Takes 2-3 minutes. Run analysis? [Y/n]
User: "Refactor to event-driven architecture"
⚠️ Significant decision detected
Your request involves a major architectural change.
Consider critical analysis first:
/advise "Refactor to event-driven architecture"
This will evaluate:
- Alignment with current architecture (PROJECT.md:78)
- Migration complexity (message bus, event schemas)
- Pros/cons of event-driven vs current approach
- Alternative patterns (queue-based, CQRS lite)
This is a 6-8 week decision. Run analysis? [Y/n]
User: "Also add mobile app support"
⚠️ Significant decision detected
Your request expands project scope to mobile platforms.
Consider critical analysis first:
/advise "Add mobile app (iOS + Android)"
This will check:
- Alignment with PROJECT.md scope (currently web-only)
- Effort estimate (React Native vs native vs PWA)
- Trade-offs (mobile features vs maintenance burden)
- MVP options (PWA first, native later)
Major scope change. Run analysis? [Y/n]
If users find this annoying:
# Disable globally
echo "advisor_triggers:\n enabled: false" >> .claude/config.yml
# Or reduce sensitivity
echo "advisor_triggers:\n sensitivity: low" >> .claude/config.yml
Philosophy: Help users pause and think before committing to significant changes. The goal is not to slow down development, but to prevent costly mistakes.
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take majiayu000/advisor-triggers from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.