Automated summary
Passively detects repetitive usage patterns and suggests opportunities for creating new skills, commands, or subagents.
Strengths
- Passive observation without disrupting workflow.
- Actionable suggestions with confidence scores and examples.
- Covers three component types with clear indicators.
- Configurable detection thresholds.
Limitations
- Only suggests components; creation requires /epci:create.
- May produce false positives from heuristic scoring.
- Less useful for one-off tasks with no repeated patterns.
When you want to identify repetitive workflows and missing automation in your AI-assisted development process.
When you need to actively create a component right away—use /epci:create directly.
Security analysis
SafeThe skill is purely advisory, providing pattern detection logic and suggestion formats without any executable code, destructive commands, or data exfiltration.
No concerns found
How this analysis is madeExamples
Analyze my recent coding sessions and suggest any new skills I should create, using the detection patterns from component-advisor.I keep running lint, test, and build manually in sequence. Should I create a command? If so, suggest one with a proper /epci:create proposal.I do the same security review checklist before every merge. Detect this pattern and recommend a subagent, including confidence score.name: component-advisor description: >- Passive detection of EPCI component creation opportunities. Identifies repetitive patterns that could become skills, commands or subagents. Use when: workflow analysis, recurring pattern detection. Not for: active component creation (use /epci:create).
Component Advisor
Overview
Passive skill that detects opportunities for new EPCI component creation based on usage pattern analysis.
Reference Documents:
- Detection Patterns — Scoring criteria and thresholds
- Suggestion Examples — Real-world suggestion templates
Automatic Detection
New Skill Indicators
| Signal | Score | Example | |--------|-------|---------| | Pattern repeated 3+ times | +3 | Same validation in multiple commands | | Technical domain not covered | +2 | New unsupported stack | | Documentation frequently consulted | +2 | Repeated searches on same topic | | Copy-paste of guidelines | +1 | Same conventions applied |
Suggestion threshold: Score ≥ 4
New Command Indicators
| Signal | Score | Example | |--------|-------|---------| | Repeated action sequence | +3 | Same recurring manual workflow | | Frequent skill combination | +2 | Always the same skills together | | Documented but not automated process | +2 | Guide followed manually | | Explicit user request | +3 | "I'd like a command for..." |
Suggestion threshold: Score ≥ 4
New Subagent Indicators
| Signal | Score | Example | |--------|-------|---------| | Repeated specialized validation | +3 | Specific security check | | Recurring manual review | +2 | Same checklist applied | | Narrow domain expertise | +2 | Specialized knowledge required | | Standardized report format | +1 | Same report structure |
Suggestion threshold: Score ≥ 4
Suggestion Format
When a threshold is reached:
💡 **COMPONENT OPPORTUNITY DETECTED**
### Suggested Type: [Skill | Command | Subagent]
**Identified pattern:**
[Description of detected pattern]
**Occurrences:**
- [Occurrence 1]
- [Occurrence 2]
- [Occurrence 3]
**Estimated benefits:**
- [Benefit 1]
- [Benefit 2]
**Proposal:**
/epci:create [type] [suggested-name]
**Confidence score:** [X/10]
---
*Automatic suggestion - Ignore if not relevant*
Monitored Patterns
For Skills
| Pattern | Potential Domain | |---------|------------------| | Repeated searches on a tech | New stack skill | | Manually applied conventions | Conventions skill | | Often cited best practices | Patterns skill | | Frequently used external tools | Integration skill |
For Commands
| Pattern | Potential Command | |---------|-------------------| | Repeated tool sequence | Composite command | | Manual multi-step workflow | Automation command | | Process with breakpoints | Structured command | | Action + validation + report | Workflow command |
For Subagents
| Pattern | Potential Subagent | |---------|-------------------| | Recurring validation | Validator agent | | Specialized analysis | Analyzer agent | | Review with checklist | Reviewer agent | | Formatted generation | Generator agent |
Configuration
Enable/Disable
The component-advisor is passive by default. It observes and suggests without interrupting workflow.
Customizable Thresholds
component_advisor:
skill_threshold: 4
command_threshold: 4
subagent_threshold: 4
suggestion_frequency: "on_pattern_detected" # or "end_of_session"
Detection Examples
Example 1: New Skill Detected
💡 COMPONENT OPPORTUNITY: Skill
Pattern: Kubernetes documentation consulted 5 times
Same deployment structure applied 3 times
Suggestion: /epci:create skill kubernetes-patterns
Benefits:
- Auto-detection of K8s projects
- Standardized patterns
- Reduced search time
Example 2: New Command Detected
💡 COMPONENT OPPORTUNITY: Command
Pattern: Repeated sequence
1. Lint → 2. Test → 3. Build → 4. Deploy
Suggestion: /epci:create command ci-pipeline
Benefits:
- Process automation
- Consistency across projects
- Time savings
Example 3: New Subagent Detected
💡 COMPONENT OPPORTUNITY: Subagent
Pattern: Accessibility checklist applied 4 times
Same report format generated
Suggestion: /epci:create agent a11y-auditor
Benefits:
- Automatic audit
- Standardized report
- No missed criteria
Metrics
| Metric | Description | |--------|-------------| | Patterns detected | Number of patterns identified | | Suggestions issued | Number of suggestions proposed | | Suggestions accepted | Components actually created | | Adoption rate | % suggestions → components |
Limitations
- Detection based on current session
- No memory between sessions (unless context provided)
- Suggestions are indicative, not prescriptive
- Requires repeated patterns to detect
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/component-advisor-msh3uud6/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/component-advisor-msh3uud6' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/component-advisor-msh3uud6/download' --output '.skill-downloads/component-advisor-msh3uud6/SKILL.md.part' && mv '.skill-downloads/component-advisor-msh3uud6/SKILL.md.part' '.skill-downloads/component-advisor-msh3uud6/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/component-advisor-msh3uud6/SKILL.md' && test -s '.skill-downloads/component-advisor-msh3uud6/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/component-advisor' && cp -R '.skill-downloads/component-advisor-msh3uud6' '.claude/skills/component-advisor'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/component-advisor-msh3uud6'openskills read 'component-advisor-msh3uud6'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/component-advisor-msh3uud6/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.