mcpbeat Sign in

Advisor Triggers Skill for Claude

Detects when user requests warrant critical analysis via /advise command

2k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
532
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/majiayu000/claude-skill-registry --skill advisor-triggers

What comes with it

395 bytes besides the instruction
metadata.json

The instruction itself

24 sections, as written by the author

Advisor Auto-Invoke Triggers

Purpose

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.

Detection Patterns

Pattern 1: New Dependencies

Triggers:

  • "add [package/library/service]"
  • "use [technology]"
  • "integrate [external service]"
  • "switch to [different tool]"

Examples:

  • "Let's add Redis for caching"
  • "Use TensorFlow for ML"
  • "Integrate Stripe for payments"
  • "Switch to PostgreSQL"

Why advise? New dependencies increase complexity and maintenance burden.

Pattern 2: Architecture Changes

Triggers:

  • "refactor to [pattern]"
  • "restructure as [architecture]"
  • "migrate to [architecture]"
  • "convert to [pattern]"

Examples:

  • "Refactor to microservices"
  • "Restructure as event-driven"
  • "Migrate to serverless"
  • "Convert to monorepo"

Why advise? Architectural changes have far-reaching implications.

Pattern 3: Scope Expansions

Triggers:

  • "also add [feature]"
  • "extend to [capability]"
  • "support [new use case]"
  • "make it [do more]"

Examples:

  • "Also add real-time collaboration"
  • "Extend to mobile platforms"
  • "Support multi-tenancy"
  • "Make it work offline"

Why advise? Scope creep can derail projects.

Pattern 4: Technology Replacements

Triggers:

  • "[X] instead of [Y]"
  • "replace [X] with [Y]"
  • "swap [X] for [Y]"

Examples:

  • "GraphQL instead of REST"
  • "Replace Express with Fastify"
  • "Swap MySQL for MongoDB"

Why advise? Tech replacements have migration costs.

Pattern 5: Scale Changes

Triggers:

  • "handle [large number]"
  • "scale to [big metric]"
  • "support [many users]"

Examples:

  • "Handle 1M requests/day"
  • "Scale to 100K users"
  • "Support 10K concurrent"

Why advise? Premature optimization is common.

Detection Logic

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));
}

Response Format

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]

Configuration

# .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

Integration Points

Point 1: Before /plan Command

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]

Point 2: Before /auto-implement

User: "/auto-implement add WebSocket support"
↓
advisor-triggers: Detected architecture change
↓
[Suggest /advise first]
↓
User: Either runs /advise or proceeds anyway

Point 3: In Orchestrator Agent

orchestrator receives feature request
↓
Check advisor-triggers
↓
IF significant decision detected
↓
Invoke advisor agent first
↓
Present analysis to user
↓
THEN proceed with planning

False Positives

Some requests trigger falsely:

False Positive:

  • "Fix bug in Redis connection" ← mentions Redis but not adding it
  • "Document the microservices" ← mentions architecture but not changing it

Solution: Context-aware detection:

// Only trigger if action verb present
if (containsActionVerb(request) && containsTriggerKeyword(request)) {
  return true;
}

Override

Users can bypass:

# Explicit skip
/plan --skip-advisor "Add Redis caching"

# Or acknowledge in prompt
"Add Redis caching (already analyzed, proceeding)"

Success Metrics

This skill is successful if:

  • ✅ Catches 80%+ of significant decisions
  • ✅ False positive rate < 20%
  • ✅ Users find suggestions helpful (not annoying)
  • ✅ Reduces regretted decisions (measured via rollbacks)

Example Outputs

Example 1: New Dependency

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]

Example 2: Architecture Change

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]

Example 3: Scope Expansion

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]

Disabling

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

Version History

  • 1.0.0 (2025-10-26): Initial release
  • Pattern detection for 5 trigger types
  • Configurable sensitivity
  • Integration with /advise command

Philosophy: Help users pause and think before committing to significant changes. The goal is not to slow down development, but to prevent costly mistakes.

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

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.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

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.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

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.

16k tokens
Benchling Integration
by christophacham
×3

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.

14k tokens
Biopython
by christophacham
×3

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.

24k tokens

How to use it

Copy the folder

Take majiayu000/advisor-triggers from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

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.