brainstorming
Structured design dialogue that validates ideas before implementation begins.
discovery-pack
Complete project discovery workflow using Jobs-to-be-Done, Amazon PR/FAQ, ADR, and Lean Startup validation. Transforms ambiguous ideas into structured specifications ready for implementation. Activate when user mentions "discovery", "requirements discovery", "project framing", "validate assumptio...
Full skill instructions
Structured project discovery using proven methodologies (JTBD, Amazon PR/FAQ, ADR, Lean Startup, DDD). Transforms ambiguous ideas into clear, validated specifications ready for spec-kit handoff.
Activation Triggers: "discovery", "requirements discovery", "project framing", "validate assumptions", "JTBD analysis"
Two Modes:
Pre-Flight Check:
bash scripts/pre-flight-check.sh <output-dir> <mode>
| Methodology | Purpose | Applied In |
|---|---|---|
| Jobs-to-be-Done (JTBD) | User motivation & context | Problem framing (00) |
| Amazon PR/FAQ | Customer clarity | Problem framing (00) |
| ADR | Decision rationale | Decision log (06) |
| Lean Startup | Assumption validation | Validation plan (05) |
| DDD | Domain language | Domain model (02) |
📖 Details: shared-references/methodologies.md, shared-references/glossary.md
Supported Locations:
~/.copilot/skills/discovery-pack/ (GitHub Copilot CLI)~/.claude/skills/discovery-pack/ (Claude Code).claude/skills/discovery-pack/ (project-local)Script Invocation:
# From skill root:
python3 scripts/validate.py <output-dir>
# From anywhere:
python3 ~/.copilot/skills/discovery-pack/scripts/validate.py <output-dir>
All scripts use relative path resolution (Path(__file__) / ${BASH_SOURCE[0]}).
🛑 ALWAYS ask first:
| Mode | Artifacts | Time | Best For |
|---|---|---|---|
| lite | 3 (00, 03, 07) | 15-30 min | Small projects, low risk, <5 people |
| full | 8 (00-07) | 1-2 hours | Enterprise, compliance, high risk |
Decision Tree:
Automation Check:
# Optional but recommended (30-40% token savings)
pip install -r scripts/requirements.txt
Target: <project-root>/docs/discovery/YYYY-MM-DD-<topic-slug>
Examples:
/docs/discovery/2026-01-07-user-auth/docs/discovery/2026-01-07-api-redesignAuto-create if missing (scripts handle this).
Progressive Disclosure Strategy: Load detailed workflow only when starting execution.
Workflow File: shared-references/workflows/lite-mode.md
Quick Overview:
templates/00_problem-frame.md, fill YAML, validatetemplates/03_option-space.md, compare 2+ options, recommendtemplates/07_speckit-handoff.md, prepare spec-kit inputLoad detailed instructions: Read shared-references/workflows/lite-mode.md before starting Phase 1.
Workflow File: shared-references/workflows/full-mode.md
Quick Overview:
extract_assumptions.pyLoad detailed instructions: Read shared-references/workflows/full-mode.md before starting Phase 1.
🛑 After artifact generation:
python3 scripts/validate.py <output-dir>
Expected Output:
✅ 00_problem-frame.md: Valid
✅ 03_option-space.md: Valid
✅ 07_speckit-handoff.md: Valid
📊 Summary: 3/3 artifacts valid (100%)
If validation fails:
No progression without 100% validation pass (schema compliance mandatory).
| ID | Name | Lite | Full | Auto | Template |
|---|---|---|---|---|---|
| 00 | Problem Frame | ✓ | ✓ | - | templates/00_problem-frame.md |
| 01 | Constraints & NFRs | - | ✓ | - | templates/01_constraints-nfr.md |
| 02 | Domain Model | - | ✓ | - | templates/02_domain-model.md |
| 03 | Option Space | ✓ | ✓ | - | templates/03_option-space.md |
| 04 | Assumptions | - | ✓ | ✓ | Auto via extract_assumptions.py |
| 05 | Validation Plan | - | ✓ | - | templates/05_validation-plan.md |
| 06 | Decision Log | - | ✓ | - | templates/06_decision-log.md |
| 07 | Spec-Kit Handoff | ✓ | ✓ | - | templates/07_speckit-handoff.md |
Template Loading: Load template only when generating that specific artifact (progressive disclosure).
| Script | Purpose | When to Use |
|---|---|---|
scripts/pre-flight-check.sh | Validate environment | Before starting workflow |
scripts/discovery-pack-run.sh | Full workflow executor | Automated end-to-end execution |
scripts/validate.py | Schema validation | After each artifact / end of workflow |
scripts/extract_assumptions.py | Generate 04 from 00-03 | Full mode, after 00-03 complete |
scripts/ci-validate.sh | CI/CD integration | Automated validation in pipelines |
Token Savings: Automation provides ~30-40% token reduction vs manual execution.
ready_for_speckit: trueProgressive Disclosure Pattern:
Target Token Budget:
High Token Operations (avoid unless necessary):
| Error Type | Symptom | Fix |
|---|---|---|
| Missing field | Missing required field: X.Y.Z | Add field to YAML frontmatter |
| Type mismatch | Expected array, got object | Convert format (e.g., single → list) |
| Invalid enum | Value not in enum: [...] | Use valid enum value from error |
| YAML syntax | could not parse YAML | Check indentation, colons, quotes |
Scripts not found:
~/.copilot/skills/discovery-pack/scripts/...Automation unavailable:
pip install -r scripts/requirements.txtTemplate loading fails:
templates/ directory exists relative to skill rootscripts/pre-flight-check.sh)/speckit.constitutionshared-references/methodologies.mdshared-references/glossary.mdshared-references/workflows/lite-mode.mdshared-references/workflows/full-mode.mdschemas/*.schema.jsontemplates/*.mdStructured design dialogue that validates ideas before implementation begins.
Comprehensive design intelligence for web and mobile UI/UX across 10 technology stacks.
Comprehensive implementation plans for multi-step tasks, breaking down specs into bite-sized, testable steps.
Introduction to the obra skills system with mandatory skill invocation rules and best practices.
Execute a written implementation plan with critical review and task checkpoints.
Delegate independent tasks to specialized agents working concurrently with isolated context.
Isolated git worktrees with smart directory selection and safety verification.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Plan searchable and shareable content that drives traffic, builds authority, and generates leads.
README-first repository scanner that extracts commands and classifies reproduction candidates without executing them.
Brainstorm and prioritize marketing strategies tailored to your SaaS stage, budget, and goals.
Plan and optimize your website's page hierarchy, navigation, URL structure, and internal linking.
The world's fastest calendar for remote work
Capture, organize, and utilize your knowledge effortlessly.
Instant Summaries of Audio & Video Interviews with AnySummary
Transform PDFs into engaging mind maps.
Chat with any PDF instantly
Create an optimal daily plan using your voice
A productivity platform to centralize organizational knowledge and workflows with contextual AI assistance.
AskYourPDF Pricing Plans: Tailored to Your Needs