docs: reorganize skills into pkm category and add crit skill

- Create new `pkm` directory for Personal Knowledge Management skills
- Move conversation-summary, knowledge-gardener, and research-vault from `personal` to `pkm`
- Add new crit skill for brainstorming with the CRIT framework
- Update skill descriptions for clarity and consistency
- Add audio-product-dsp, grilling, and research-engineering to model-invoked listings
- Update skill paths across README files to reflect new directory structure
This commit is contained in:
2026-06-22 22:20:08 -04:00
parent e7fcc51e86
commit af96c9e331
9 changed files with 87 additions and 13 deletions
+11 -8
View File
@@ -4,16 +4,19 @@ Skills that work in all CLI agents.
## User-invoked
- [conversation-summary](personal/conversation-summary/SKILL.md) — Create compact conversation summaries for continuity.
- [grill-me](productivity/grill-me/SKILL.md) — Run a terse adversarial critique.
- [grilling](productivity/grilling/SKILL.md) — Prepare grilling guidance.
- [handoff](productivity/handoff/SKILL.md) — Create a handoff note for continuing work.
- [knowledge-gardener](personal/knowledge-gardener/SKILL.md) — Run vault-aware semantic search, synthesis, note creation, linking, and Zettelkasten workflows.
- [conversation-summary](pkm/conversation-summary/SKILL.md) — Summarize the current AI conversation into a new Obsidian markdown note and matching transcript file.
- [crit](pkm/crit/SKILL.md) — Brainstorm with AI using the CRIT framework to generate and evaluate ideas.
- [grill-me](productivity/grill-me/SKILL.md) — A relentless interview to sharpen a plan or design.
- [handoff](productivity/handoff/SKILL.md) — Compact the current conversation into a handoff document for another agent to pick up.
- [knowledge-gardener](pkm/knowledge-gardener/SKILL.md) — Run vault-aware semantic search, synthesis, note creation, linking, and Zettelkasten workflows for this Obsidian vault.
- [pkm-curation](personal/pkm-curation/SKILL.md) — Curate an Obsidian-style personal knowledge vault.
- [research-vault](personal/research-vault/SKILL.md) — Research a topic through a one-question-at-a-time conversation and store the packet in a new Obsidian vault folder with relevant links.
- [writing-great-skills](productivity/writing-great-skills/SKILL.md) — Reference for writing and editing predictable skills.
- [research-vault](pkm/research-vault/SKILL.md) — Research a topic through a one-question-at-a-time learning conversation and save a linked Obsidian research packet.
- [writing-great-skills](productivity/writing-great-skills/SKILL.md) — Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
## Model-invoked
- [forge-preferences](personal/forge-preferences/SKILL.md) — Apply Steve's personal or project-specific GitHub/Gitea forge preferences.
- [audio-product-dsp](deprecated/audio-production-dispatcher/SKILL.md) — Dispatch audio product DSP hardware/software engineering requests to the best specialist workflow with measurable product-focused outputs.
- [forge-interaction](engineering/forge-interaction/SKILL.md) — Work safely with GitHub and Gitea repositories, issues, pull requests, releases, and remote forge state.
- [forge-preferences](personal/forge-preferences/SKILL.md) — Apply Steve's personal or project-specific GitHub/Gitea forge preferences.
- [grilling](productivity/grilling/SKILL.md) — Interview the user relentlessly about a plan or design.
- [research-engineering](deprecated/dsp-research-dispatcher/SKILL.md) — Route DSP hardware and software research-engineering requests to the best specialist workflow and return a unified, decision-ready output.
-3
View File
@@ -2,10 +2,7 @@
## User-invoked
- [conversation-summary](conversation-summary/SKILL.md) — Create compact conversation summaries for continuity.
- [knowledge-gardener](knowledge-gardener/SKILL.md) — Run vault-aware semantic search, synthesis, note creation, linking, and Zettelkasten workflows.
- [pkm-curation](pkm-curation/SKILL.md) — Curate an Obsidian-style personal knowledge vault.
- [research-vault](research-vault/SKILL.md) — Research a topic through a one-question-at-a-time conversation and store the packet in a new Obsidian vault folder with relevant links.
## Model-invoked
+12
View File
@@ -0,0 +1,12 @@
# PKM Skills
## User-invoked
- [conversation-summary](conversation-summary/SKILL.md) — Summarize the current AI conversation into a new Obsidian markdown note and matching transcript file.
- [crit](crit/SKILL.md) — Brainstorm with AI using the CRIT framework to generate and evaluate ideas.
- [knowledge-gardener](knowledge-gardener/SKILL.md) — Run vault-aware semantic search, synthesis, note creation, linking, and Zettelkasten workflows for this Obsidian vault.
- [research-vault](research-vault/SKILL.md) — Research a topic through a one-question-at-a-time learning conversation and save a linked Obsidian research packet.
## Model-invoked
_None yet._
+52
View File
@@ -0,0 +1,52 @@
---
name: crit
description: brainstorm with AI using the CRIT framework to generate and evaluate ideas.
disable-model-invocation: true
---
### Goal
Act as an adaptive AI assistant that provides expert-level guidance across multiple domains. Your primary objective is to deliver accurate, practical, and context-aware solutions tailored to the user’s needs.
### Context
Consider the following in every interaction:
- The user's skill level, background, and familiarity with the topic
- The complexity and scope of the request
- Any constraints (time, resources, technical limitations)
- The real-world application and implications of your advice
### Roles
You can dynamically switch between these roles based on user needs:
- **Subject Matter Expert**: Provide deep technical or domain-specific knowledge
- **Consultant**: Offer strategic advice and actionable recommendations
- **Teacher**: Explain complex concepts in simple, clear terms
- **Collaborator**: Co-create solutions with the user
- **Analyst**: Evaluate problems from multiple perspectives and provide insights
### Interaction Guidelines
Before providing solutions:
1. **Clarify the Request**: Ask targeted questions to confirm the user’s goal
2. **Identify Constraints**: Understand deadlines, limitations, or special requirements
3. **Assess Context**: Determine intended use case and experience level
4. **Define Scope**: Confirm whether the user needs a quick answer, detailed analysis, or ongoing support
Sample clarifying questions:
- “Could you share more details about your goal?”
- “Are there any constraints I should consider?”
- “What’s your experience level with this topic?”
### Response Framework
When delivering answers:
1. Provide **clear, actionable solutions**
2. Organize information **logically and concisely**
3. Offer **multiple approaches or perspectives** when relevant
4. Include **examples or analogies** for clarity
5. Suggest **next steps or follow-up questions**
### Tone & Quality
- Be professional, approachable, and adaptive
- Ensure accuracy and transparency
- Acknowledge uncertainties when applicable
- Encourage iteration and collaboration
**Key Principle**: Every interaction should feel like a meaningful, user-focused conversation that helps achieve their goals.