code/exploration-to-spec/SKILL.md
Converts an exploration conversation (architecture discussions, codebase analysis, design decisions) into a structured technical specification document. Generates a comprehensive but concise product-engineering doc suitable for PMs, tech leads, designers, frontend/backend engineers, and QA. Use when you've finished exploring and want to formalize decisions into a shareable deliverable.
npx skillsauth add mostafa-drz/claude-skills exploration-to-specInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Convert exploration conversations into structured, professional technical documents that satisfy the needs of an entire startup product team — from PM to QA.
On startup, use the Read tool to load ~/.claude/skills/exploration-to-spec/preferences.md. If it doesn't exist, use defaults.
On startup, use Bash to detect: current git branch, repo name, and working directory. Check if ~/.claude/skills/exploration-to-spec/reference/ exists for templates.
Check $ARGUMENTS:
help → display help then stopconfig → interactive setup then stopreset → delete ~/.claude/skills/exploration-to-spec/preferences.md, confirm, stopExploration to Spec — Convert conversations into technical specifications
Usage:
/exploration-to-spec Interactive (asks for output path)
/exploration-to-spec ./docs/design.md Write to specific path
/exploration-to-spec --format roadmap Use roadmap template
/exploration-to-spec --format design-doc Use design document template
/exploration-to-spec --format adr Architecture Decision Record
/exploration-to-spec --format rfc Request for Comments
/exploration-to-spec --audience pm Optimize for product managers
/exploration-to-spec --audience engineering Optimize for engineers
/exploration-to-spec --audience all Full cross-functional doc (default)
/exploration-to-spec config Set preferences
/exploration-to-spec reset Clear preferences
/exploration-to-spec help This help
Examples:
/exploration-to-spec ./technical-docs/insight-engine.md
/exploration-to-spec --format roadmap --audience all ./docs/roadmap.md
/exploration-to-spec --format adr (asks for output path)
Current preferences:
(read from preferences.md)
Use AskUserQuestion:
Q1 — "Default document format?" (Roadmap, Design Doc, ADR, RFC)
Q2 — "Default audience?" (Product — executive summary focus, Engineering — schema/API focus, All — cross-functional)
Q3 — "Default output directory?" (text input, e.g., ./technical-docs/)
Q4 — "Include diagrams style?" (ASCII art — works everywhere, Mermaid — rendered in GitHub/Notion, Both)
Save to ~/.claude/skills/exploration-to-spec/preferences.md.
Delete ~/.claude/skills/exploration-to-spec/preferences.md and confirm: "Preferences cleared. Using defaults."
If no preferences file exists, show:
"First time using /exploration-to-spec? Run /exploration-to-spec config to set defaults, or continue — I'll use sensible defaults."
Then proceed.
Scan the current conversation to extract:
Build an internal outline of the key content areas.
If not specified via flags, use preferences. If no preferences, ask via AskUserQuestion:
Q1: Document format
Q2: Primary audience
If provided in $ARGUMENTS, use it. Otherwise ask:
Where should I save this document? (e.g.,
./technical-docs/my-spec.md)
Apply the selected template structure. Every document must follow these rules:
Principles:
Template structures by format:
1. Executive Summary ← PM: what & why in one paragraph
2. Current State ← Context for anyone new
2.1 What exists today
2.2 What was explored/prototyped
2.3 Gap analysis (table)
3. Architecture ← Tech leads, engineers
3.1 System overview (diagram)
3.2 Data flow (step-by-step)
3.3 Component inventory (new/reuse/extend table)
3.4 Storage strategy
4. Schema Design ← Backend, QA
4.1 Source → target mappings
4.2 Table definitions (SQL)
4.3 Cross-reference table (source → storage → API → UI)
5. API Contracts ← Backend + frontend
5.1 Ingest APIs
5.2 Query APIs
5.3 Events
6. UI Requirements ← Design, frontend
6.1 Component specs with ASCII mockups
6.2 Field mapping tables
6.3 Pages & routes
7. Implementation Phases ← PM, project managers
Phase N: Goal, tasks table, acceptance criteria
8. Testing Strategy ← QA
Per-phase test matrix (type, test, owner)
9. Open Questions ← Everyone
Numbered table with impact and status
1. Overview ← Problem, goals, non-goals
2. Background ← Current state, prior art
3. Architecture ← System design with diagrams
4. Detailed Design ← Schemas, APIs, algorithms
5. Alternatives Considered ← What else was evaluated and why not
6. Cross-cutting Concerns ← Security, observability, migration
7. Implementation Plan ← Sequencing, dependencies
8. Open Questions
# ADR-NNN: [Title]
Status: [Proposed | Accepted | Deprecated]
Date: YYYY-MM-DD
## Context ← What situation led to this decision
## Decision ← What was decided and why
## Options Considered ← Alternatives with trade-offs
## Consequences ← What follows from this decision
## References ← Related docs, tickets, conversations
# RFC: [Title]
Author: [name] | Date: YYYY-MM-DD | Status: Draft
## Summary ← One paragraph
## Motivation ← Why this change is needed
## Proposal ← Detailed design
## Alternatives ← What else was considered
## Risks & Mitigations ← What could go wrong
## Rollout Plan ← How to ship it
## Open Questions ← What needs resolving
After generating, do a self-review pass:
Write the document to the specified path.
Report:
Document written to: [path]
Format: [format]
Audience: [audience]
Sections: [count]
Lines: [count]
Via AskUserQuestion:
If the user made corrections:
Save patterns to preferences.
development
--- name: triage-board description: >- Generates a structured triage artifact from the current conversation's findings — a self-contained Desktop folder with a JSON Schema, schema-conformant report.json, prose markdown, and a single-file HTML viewer. Viewer ships with MD / CSV / JSON download buttons in the header and a per-finding "Copy as Markdown" action that produces a GitHub/Linear/Notion-ready ticket block. Stateless — triage state lives in the user's ticket system, not in the
development
Runs a beginner-mind end-to-end UI audit of any running app — local dev server, staging, production, or a specific URL. Drives Chrome through every interactive element on the target surface, collects structured findings (severity, category, where, symptom, impact, repro, triage), and hands the result off to `/triage-board` which produces the Desktop folder (schema + JSON + Markdown + single-file HTML viewer with MD/CSV/JSON exports and a per-finding Copy as Markdown button). Use when you want fresh-eyes verification of a feature, page, modal, flow, branch, or whole app — before shipping, before review, before a demo, or any time the UI deserves a careful poke.
development
Reviews the user's past Claude Code conversations from a wellbeing perspective — sentiment, tone, emotional arc, recurring patterns — and generates a supportive, science-grounded report in both Markdown and HTML. Default lookback is 48 hours across all projects. Uses recognised emotion frameworks (Plutchik, Ekman, Russell's circumplex, Pennebaker linguistic markers) and cites the science behind every observation. Learns the user's baseline tone over time so future reports flag genuine shifts, not noise. Use when the user asks for an emotional/wellbeing recap, mood check, sentiment review, or wants to understand their own ups and downs across recent work sessions.
development
--- name: workflow-advisor description: >- Analyzes recent Claude Code conversations and local Claude state (skills, settings, memory files, CLAUDE.md), researches the latest Claude Code features and best practices online, and suggests one workflow improvement at a time with reasoning and a concrete action item. Can save accepted suggestions to memory for tracking. Use when you want to discover underused Claude Code features, improve your development workflow, stay current with the lat