discovery-high-level-plan

$npx mdskill add Fr-e-d/GAAI-framework/discovery-high-level-plan

Transforms vague intent into a governed discovery action plan.

  • Solves unclear or broad user intent requiring multiple discovery steps.
  • Depends on filesystem access to optional contexts and memory.
  • Analyzes intent scope to select and order necessary skills.
  • Outputs a minimal, governed plan with validation gates.

SKILL.md

.github/skills/discovery-high-level-planView on GitHub ↗
---
name: discovery-high-level-plan
description: Transform vague or high-level human intent into a governed Discovery action plan. Activate when intent is unclear, broad, or when multiple discovery steps are required before any artefact is created.
license: ELv2
compatibility: Works with any filesystem-based AI coding agent
metadata:
  author: gaai-framework
  version: "1.0"
  category: discovery
  track: discovery
  id: SKILL-DISCOVERY-HIGH-LEVEL-PLAN-001
  updated_at: 2026-02-26
  status: stable
inputs:
  - human_intent
  - contexts/artefacts/**  (optional)
  - contexts/memory/**  (selective)
outputs:
  - discovery_action_plan
---

# Discovery High-Level Planning

## Purpose / When to Activate

Activate this skill when:
- Intent is unclear or broad
- Multiple discovery steps are required
- You don't know which skills to run first
- Refinement is needed before committing to artefacts

Typical triggers: "I have an idea for a feature", "Users are dropping during onboarding", "We should rethink pricing", "There's a bug where X happens but we don't know why"

**This skill plans — it does not produce artefacts.**

---

## Process

1. Understand the real problem or opportunity
2. Determine Discovery scope: new initiative / feature addition / iteration / removal / clarification / **bug triage** (complex bug with unclear root cause)
3. Identify required artefacts
4. Select necessary skills in logical order
5. Insert validation and refinement gates
6. Output a minimal, governed plan

---

## Outputs

```
Discovery Action Plan

Goal:
<what clarity must be achieved>

Steps:
1. <skill name> — purpose
2. <skill name> — purpose
3. <skill name> — purpose

Validation Gates:
- artefact completeness
- acceptance criteria present
- uncertainties flagged

Ready For Delivery:
yes / no

Blocking Reasons (if any):
- ...
```

---

## Quality Checks

- Plan is minimal and focused
- All necessary artefacts will be produced
- Skill sequence is logical
- Governance is respected
- Human can approve or adjust easily

---

## Non-Goals

This skill must NOT:
- Generate epics, stories, or PRDs
- Make product decisions
- Execute other skills
- Write artefact content

**If the next step isn't obvious — plan first. Planning prevents waste more than speed increases output.**

More from Fr-e-d/GAAI-framework

SkillDescription
abort-safe-handlerOrchestrator-level Stage 4 entry gate for /gaai:bootstrap. Presents a pre-loop "Skip Q&A entirely" option, delegates to qa-loop-ui when the user proceeds, and returns a unified abort_safe_result with telemetry on every path. Guarantees no partial state on skip or abort.
ambiguity-detectorTakes surface scan results, optional LLM synthesis open-question entries, and optional tree-sitter AST signals to score project ambiguities (1-10). Outputs structured ambiguity_feed for smart-question-generator. Pure heuristic — no LLM calls. Designed for Stage 3.5 of the /gaai:bootstrap pipeline (between LLM synthesis and Q&A).
approach-evaluationResearch industry standards and best practices, identify viable approaches for a given technical or architectural problem, and produce a structured factual comparison against project-specific constraints. Reports options — does not decide.
architecture-extractConvert raw project structure into clear architectural understanding — module boundaries, data flows, service relationships, and architectural patterns. Activate after codebase-scan during Bootstrap.
bootstrap-llm-synthesisConstruct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.
bootstrap-memory-ingest-cloudWrite structured memory entries to the Cloud workspace via gaai_memory.store MCP tool with source='bootstrap'. Loops over entries from bootstrap-llm-synthesis, calls the tool per entry, collects success/fail counts. Used as Stage 5 of the /gaai:bootstrap pipeline (Cloud path only).
browser-journey-testValidate user stories by simulating real user journeys in a live browser against deployed application. Activate after implementation to verify actual user experience against acceptance criteria, not just code logic.
build-agents-indexScan all agent and sub-agent definition files in .gaai/core/agents/, extract YAML frontmatter, merge with specialists.registry.yaml, and generate a derived agents-index.yaml at .gaai/core/agents/agents-index.yaml. Activate after adding, modifying, or removing any agent, sub-agent, or specialist entry.
build-skills-indexScan SKILL.md files in .gaai/core/skills/ and .gaai/project/skills/, extract YAML frontmatter, and regenerate separate skills indices for each layer. Core index ships with the OSS framework; project index is project-specific.
ci-watch-and-fixWatch GitHub Actions CI after PR creation, detect failures, extract logs, apply minimal fixes, and re-push — keeping the delivery session alive until CI resolves or escalating after 3 cycles. Activate immediately after gh pr create and before marking the story done.