feat: add research-vault skill and reorganize skill paths

- Add research-vault skill with conversational research workflow and Obsidian packet output
- Add research packet template with Index, Sources, Synthesis, Claims, Questions, Conversation, and Glossaries
- Add personal/README.md listing personal skills
- Reorganize common/README.md paths into personal/ and productivity/ subdirectories
This commit is contained in:
2026-06-22 15:04:14 -04:00
parent 503193793f
commit 8b16e97052
4 changed files with 218 additions and 1 deletions
+8 -1
View File
@@ -4,7 +4,14 @@ Skills that work in all CLI agents.
## User-invoked ## User-invoked
- [pkm-curation](pkm-curation/SKILL.md) — Curate an Obsidian-style personal knowledge vault. - [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.
- [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.
## Model-invoked ## Model-invoked
+13
View File
@@ -0,0 +1,13 @@
# Personal Skills
## User-invoked
- [conversation-summary](conversation-summary/SKILL.md) — Create compact conversation summaries for continuity.
- [forge-preferences](forge-preferences/SKILL.md) — Apply Steve's personal or project-specific forge preferences.
- [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
_None yet._
+48
View File
@@ -0,0 +1,48 @@
---
name: research-vault
description: Research a topic through a one-question-at-a-time learning conversation, answer directly, share resources when useful, and save a linked Obsidian research packet.
disable-model-invocation: true
---
# Research Vault
Use when the user wants to learn or research a topic conversationally and save the outcome in an Obsidian vault.
## Packet
Create one vault folder per research run, normally `Research/<YYYY-MM-DD> <Topic>/`, containing all notes from the run: `Index.md`, `Sources.md`, `Synthesis.md`, `Claims.md`, `Questions.md`, `Conversation.md`, `Glossaries.md`, and any atomic notes. Load `references/research-packet-template.md` before writing packet files or when exact structure matters.
## Workflow
1. **Locate the vault.** Confirm the exact vault root and write only inside it.
2. **Frame the goal.** Ask one question at a time until you can restate the topic, learning objective, scope, and success criteria. Discover the user's goal, prior knowledge, intended use, depth, constraints, output preference, and trusted/distrusted sources only as needed.
3. **Create or defer the folder.** Create the packet folder once the topic has a stable working title; if still vague, keep conversing. Before writing durable notes, every artifact must have a path inside the packet folder.
4. **Map context.** Search the vault for the topic, synonyms, projects, and neighboring concepts. Read enough relevant notes to make meaningful links, not keyword matches.
5. **Research and teach.** Answer the user directly, explain findings in small chunks, cite claims, preserve uncertainty, share resources when they improve learning or evidence quality, and correct misunderstandings before moving on.
6. **Check understanding and completeness.** Ask one diagnostic or completeness question per turn. Answer follow-ups with evidence, examples, counterarguments, implementation details, or resources as needed. Capture unresolved gaps in `Questions.md`.
7. **Write incrementally.** For long sessions, update `Conversation.md`, `Questions.md`, `Glossaries.md`, and `Sources.md` as the work progresses. By the end, no research, teaching insight, user question, glossary term, source, or durable knowledge should exist only in chat.
8. **Link into the vault.** Add wikilinks from packet notes to relevant existing notes; suggest backlinks instead of editing unrelated existing notes unless the user asked for full integration.
9. **Report.** Summarize the packet path, files changed, links or backlink suggestions, top takeaways, what the user now understands, and remaining questions.
## Conversation Rules
- Ask only one question per turn; if several details are missing, choose the most blocking one.
- Answer the user's question before asking another.
- If the user is uncertain, offer a small set of options and ask them to choose one.
- Use a teach-back loop for complex topics: plain-language explanation → concrete example → one check question or restatement prompt → correction → continue only when the user is satisfied or uncertainty is captured.
- Ask checks before research, after initial framing, after major findings, and before finalizing notes.
- When the user corrects you, record the correction in `Conversation.md`, update affected packet notes, and prefer the corrected framing unless later evidence contradicts it.
- Record important answers and useful resources in `Conversation.md`; reflect scope-changing details in `Index.md`, `Sources.md`, or `Synthesis.md`.
## Capture Rules
- Put every acronym, abbreviation, domain-specific phrase, specialized term, jargon term, and piece of domain nomenclature in `Glossaries.md`, even when explained elsewhere.
- Keep sources, synthesis, claims, questions, conversation, glossary, and atomic knowledge separate.
- Keep citations close to claims; mark confidence when evidence is incomplete or contested.
- Preserve useful quotes verbatim with attribution.
- Distinguish source claims from interpretation; record failed searches or missing evidence when they affect the conclusion.
- Create atomic notes in the packet folder for durable concepts; link each from `Index.md` and back to its source or synthesis section.
## Linking Rules
Use Obsidian wikilinks: `[[Note Title]]` or `[[path/to/Note|alias]]`. Add links only when they explain context: broader concepts, projects, areas, MOCs, sources, authors, methods, tools, domains, supporting/refining/contradicting claims, or active problems. Do not link on shared words alone.
@@ -0,0 +1,149 @@
# Research Packet Template
Use inside `Research/<YYYY-MM-DD> <Topic>/` unless the vault has a clearer convention.
## Required files
### `Index.md`
```markdown
# <Topic>
## Purpose
- Learning goal:
- Scope:
- Success criteria:
## Main Takeaways
-
## Packet Map
- [[Sources]]
- [[Synthesis]]
- [[Claims]]
- [[Questions]]
- [[Conversation]]
- [[Glossaries]]
## Related Vault Notes
-
## Open Questions
-
```
### `Sources.md`
```markdown
# Sources
| Source | Type | Why useful | Reliability notes | Accessed |
|---|---|---|---|---|
| | | | | |
## Notes
-
```
Include source links, books, papers, docs, videos, examples, search terms, or relevant vault notes only when they improve learning or evidence quality.
### `Synthesis.md`
```markdown
# Synthesis
## Short Answer
## Explanation
## Examples
## Disagreements or Uncertainty
## Practical Implications
## Links
-
```
### `Claims.md`
```markdown
# Claims
## Claim: <claim>
- Evidence:
- Source:
- Confidence: high | medium | low
- Implications:
- Related notes:
```
### `Questions.md`
```markdown
# Questions
## User Questions
-
## Open Questions
-
## Deferred or Out of Scope
-
## Follow-up Search Terms
-
```
### `Conversation.md`
```markdown
# Conversation
## Learning Goal
## Assumptions
## Understanding Checks
## User Corrections
## Decisions
## Resources Shared
-
```
Record important answers, corrections, and scope decisions as the session progresses.
### `Glossaries.md`
```markdown
# Glossaries
## <Term or Acronym>
- Expansion:
- Plain-language definition:
- Domain/context:
- Appeared in:
- Related links:
```
Add every acronym, abbreviation, domain-specific phrase, specialized term, jargon term, and domain nomenclature encountered.
## Atomic note
```markdown
# <Concept>
## Idea
## Why it matters
## Evidence or source
## Related notes
-
```