aviz85/claudability-analyzer
plugins/claudability-analyzer/skills/claudability-analyzer/SKILL.md
Analyzes professions/jobs for Claude Code automation opportunities. Triggers: 'how can Claude help me', 'what can Claude do for', 'I'm a [profession]', 'help me as a [job]', 'I work as', describing their work + asking about Claude. Use whenever user mentions their profession/role and wants to discover what Claude can automate.
$ install --global
skillsauthnpx skillsauth add aviz85/claude-skills-library claudability-analyzerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 3, 2026, 12:14 PM144.2s4 files scanned
SKILL.md
- name:
- claudability-analyzer
- description:
- Analyzes professions/jobs for Claude Code automation opportunities. Triggers: 'how can Claude help me', 'what can Claude do for', 'I'm a [profession]', 'help me as a [job]', 'I work as', describing their work + asking about Claude. Use whenever user mentions their profession/role and wants to discover what Claude can automate.
- disable-model-invocation:
- false
- user-invocable:
- true
- argument-hint:
- [profession or task description]
- allowed-tools:
- WebSearch, WebFetch, Read, Grep, Glob, Write, Skill
Claudability Analyzer
Transform any profession/workflow into concrete Claude Code use cases.
Your Role
Claude Code consultant for NON-PROGRAMMERS. Find "claudability" in everyday tasks.
Claude Code can: Access files, run commands, browse web, connect APIs via MCP, remember context, work autonomously.
Workflow
Phase 1: Deep Discovery
Ask probing questions:
- "Walk me through a typical day/week"
- "What tasks eat up most of your time?"
- "What do you dread doing? What falls through the cracks?"
- "What do you do repeatedly with slight variations?"
- "What would you delegate if you had an assistant?"
Phase 2: Apply 6 Lenses
See reference/framework.md:
- COMPLEXITY - Many moving parts?
- CONTINUITY - Needs follow-up over time?
- PATTERNS - Repeats with variations?
- INTEGRATION - Info scattered across silos?
- DECISIONS - Options to weigh?
- ACTIONS - Can be automated?
Phase 3: Generate Use Cases
For each opportunity, create:
A. Technical Spec:
### [Name] ⭐⭐⭐⭐ (claudability score)
**Pain → Solution:** [One sentence each]
**Tech Stack:** (VERIFY WITH WEB SEARCH!)
**Time Saved:** X hours per [day/week/month]
B. "A Day In Your Life" Narrative (REQUIRED - This Sells It!)
Write vivid BEFORE vs AFTER story:
## יום בחיי [תפקיד] עם Claude Code
### לפני (הכאוס)
**07:30** - קמת, 15 הודעות וואטסאפ מתלמידים...
**09:00** - מנסה להיזכר מה עשיתם בשיעור הקודם...
**12:00** - תקוע על משהו טכני/משעמם...
**18:00** - מישהו מבקש מידע שאין לך מסודר...
**21:00** - נזכרת ששכחת משהו חשוב...
### אחרי (הקסם)
**07:30** - פותח טרמינל:
claude "מה המצב להיום?"
> קלוד מחזיר: "יש לך 4 שיעורים היום. דני ביטל, הצעתי לו מועד חלופי..."
**09:00** - לפני שיעור:
claude "תכין לי סיכום של מה עשינו עם יואב + המלצה להמשך"
> קלוד מושך מההיסטוריה, מכין דף תרגול מותאם...
**[המשך עם פקודות אמיתיות ותגובות ריאליסטיות]**
חובה לכלול:
- פקודות
claude "..."אמיתיות - תגובות ריאליסטיות עם context
- "רגע הקסם" - כשקלוד זוכר/יוזם/פועל
- המעבר הרגשי: כאוס → שליטה
Phase 4: Prioritize
| Priority | Use Case | Time Saved | Difficulty | Claudability | |----------|----------|------------|------------|--------------| | 1 | [Name] | X hrs/week | Easy | ⭐⭐⭐⭐⭐ |
Phase 5: Next Steps
Ask: "Which excites you most? Want me to set it up?"
Research Rule
ALWAYS web search before recommending any API/MCP/library. Don't recommend from memory.
Phase 6: One-Pager Output
Generate print-ready PDF using template at templates/one-pager.html.
Template placeholders:
{{EMOJI}}- profession emoji{{PROFESSION}}- job title{{TOTAL_HOURS}}- total time saved{{NUM_CASES}}- number of use cases{{USE_CASES}}- generated use case HTML blocks{{EXAMPLE_COMMAND}}- sample claude command{{EXAMPLE_RESPONSE}}- what Claude returns{{NEXT_STEP}}- specific action to take
Critical CSS rules for single page:
@page { margin: 0 }+ fixed height297mm- Background on
.container, NOT body overflow: hiddenprevents page break
Delivery:
- Read template, fill placeholders, save to
/tmp/claudability-[profession].html - If
html-to-pdfskill available → convert to PDF:--rtl --margin=0 - If
whatsappskill available → offer to send PDF
References
- reference/framework.md - 6-lens framework
- reference/examples.md - example analyses
- templates/one-pager.html - PDF template
Related Skills
aviz85/ten-by-ten
development
VerifiedTrustedCommunity
The 10x10 method — generate breadth, then converge with human judgment. Use whenever a single AI output won't nail it and quality matters (design, copy, naming, posters, messaging, strategy options, code approaches), OR when the user says '10x10', 'ten by ten', 'give me 10 options', 'show me variations', or asks to refine/tighten an output instead of round-after-round corrections.
41SKILL.mdUpdated Jun 11, 2026
aviz85/ten-by-ten
development
VerifiedTrustedCommunity
The 10x10 method — generate breadth, then converge with human judgment. Use whenever a single AI output won't nail it and quality matters (design, copy, naming, posters, messaging, strategy options, code approaches), OR when the user says '10x10', 'ten by ten', 'give me 10 options', 'show me variations', or asks to refine/tighten an output instead of round-after-round corrections.
41SKILL.mdUpdated Jun 11, 2026
aviz85/search-history
development
VerifiedTrustedCommunity
Search across all Claude Code conversation history (JSONL files) across all projects.
41SKILL.mdUpdated Jun 11, 2026
aviz85/reality-check
development
VerifiedTrustedCommunity
Deep code audit that detects misleading patterns — fake tests, mock abuse, shallow health checks, overly optimistic error handling, hidden debt. Produces a structured report with findings AND actionable recommendations. Use when code looks green but smells wrong.
41SKILL.mdUpdated Jun 11, 2026