gitadmin 2bb59d1d92 feat(crit): rewrite skill to implement CRIT framework
Replace generic AI assistant prompt with structured CRIT
(Context-Request-Input-Tone) framework for brainstorming.

Changes:
- Add 5-step core workflow (Context Analysis, Request
  Clarification, Idea Generation, Iterative Refinement,
  Tone & Delivery)
- Add completion criteria for each workflow step
- Add quality guardrails section
- Add trigger hints for skill activation
- Add structured output format specification
- Remove generic roles and interaction guidelines
2026-06-24 00:00:36 -04:00

Skills

A collection of agent skills (slash commands and behaviors) loaded into Steve Beaulac's agents.

User-invoked

  • conversation-summary — Summarize the current AI conversation into a new Obsidian markdown note and matching transcript file.
  • crit — Brainstorm with AI using the CRIT framework to generate and evaluate ideas.
  • grill-me — A relentless interview to sharpen a plan or design.
  • handoff — Compact the current conversation into a handoff document for another agent to pick up.
  • knowledge-gardener — Run vault-aware semantic search, synthesis, note creation, linking, and Zettelkasten workflows for this Obsidian vault.
  • pkm-curation — Curate an Obsidian-style personal knowledge vault.
  • research-vault — Research a topic through a one-question-at-a-time learning conversation and save a linked Obsidian research packet.
  • writing-great-skills — Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

Model-invoked

  • audio-product-dsp — Dispatch audio product DSP hardware/software engineering requests to the best specialist workflow with measurable product-focused outputs.
  • forge-interaction — Work safely with GitHub and Gitea repositories, issues, pull requests, releases, and remote forge state.
  • forge-preferences — Apply Steve's personal or project-specific GitHub/Gitea forge preferences.
  • grilling — Interview the user relentlessly about a plan or design.
  • project-context-pack — Build and refresh a bounded repo context memory file so agents use disciplined search instead of repeated browsing.
  • research-engineering — Route DSP hardware and software research-engineering requests to the best specialist workflow and return a unified, decision-ready output.
S
Description
No description provided
Readme
759 KiB
Languages
Python 53.4%
Shell 46.6%