ahk-ask
Ask a question about this codebase — where is X, does Y exist, how does Z work. Read-only. No tasks created, no harness tracking.
Turn an idea or Jira request into a reviewable, evidence-backed feature specification.
$ npx -y skills add enmanuelmag/agent-harness-kit --skill ahk-feature --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ahk-featureContext preview
The summary Claude sees to decide when to auto-load this skill.
Turn an idea or Jira request into a reviewable, evidence-backed feature specification.
name: ahk-feature description: Turn an idea or Jira request into a reviewable, evidence-backed feature specification.
Read [the feature workflow](resources/feature-workflow.md) before discovery and [the feature template](resources/feature-template.md) before saving.
After the required questions and project evidence produce a complete first synthesis, create or update a `feature` draft with structured specification MCP tools. Use `specs.list` and `specs.search` to find related context, `specs.get` to read it, and `specs.validate` after every write. Keep drafts reviewable and editable through MCP; transition to `approved` only after explicit user confirmation.
Do not choose an implementation design. Offer `ahk-use-case-tech` only after this feature is approved and the user asks for technical design.
A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.
Repo: enmanuelmag/agent-harness-kit
Ask a question about this codebase — where is X, does Y exist, how does Z work. Read-only. No tasks created, no harness tracking.
Get technical advice or review on an approach, idea, or change. References available skills for best practices. No tasks created, no harness tracking.
Turn a reported defect or Jira issue into a reviewable, evidence-backed fix specification.
Preview a code review against ticket/objective alignment, with deep semantic (name-vs-behavior) analysis. No tasks created, no harness tracking.
Design, write, and run behavior-focused tests for an objective or existing code. Writes test files only and reports evidence. No tasks created, no harness…
Triage a bug or unexpected behavior. Deep diagnostic analysis with structured report. No tasks created, no harness tracking.