OpenSkillIndex← back to search
claude-code

GAAI-framework discovery-high-level-plan

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.

install
source · Clone the upstream repo
git clone https://github.com/Fr-e-d/GAAI-framework
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/Fr-e-d/GAAI-framework "$T" && mkdir -p ~/.claude/skills && cp -r "$T/.gaai/core/skills/discovery/discovery-high-level-plan" ~/.claude/skills/fr-e-d-gaai-framework-discovery-high-level-plan && rm -rf "$T"
manifest: .gaai/core/skills/discovery/discovery-high-level-plan/SKILL.md
source content

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.