From vault-mind
Use when the user asks a question about the contents of their own vault, e.g. "what did I conclude about functionalism", "what do my notes say about lag time in MSMs", "which books did I rate above 8", "summarize what I know about Koopman operators". Answers strictly from their notes/readings, cited to the source files. Read-only, never writes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/vault-mind:askThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Answer the user's questions about *their own* vault, what they've written, read, rated,
Answer the user's questions about their own vault, what they've written, read, rated, concluded. The answer must come from the vault and be cited to the notes/readings it came from, so they can trust and trace it. This is retrieval, not teaching and not opinion.
Core rule: read-only. Writes nothing.
Read the vault profile (.vault-mind/profile.md) first if you haven't this session (paths +
frontmatter schema; run /vault-mind:init if missing). Below, "notes dir", "resources dirs",
"status/rating keys" refer to the profile's values.
Search broadly before answering, names, tags, wikilinks, frontmatter fields.
# from the vault root; substitute the profile's dir/key names:
rg -l -i 'term' <notes_dir> <resources_dirs> # files on the topic
rg -i 'term' "<notes_dir>/X.md" # what a note actually says
rg -l '^<status_key>: <read_value>$' <resources_dirs> # consumed readings (anchor $, "read" is a prefix of "reading")
rg -N '^(<rating_key>|<status_key>|tags|genres):' <resources_dirs>/**/*.md # metadata queries
For metadata questions (ratings, status, counts, "what have I read on X"), read frontmatter across the relevant folder rather than guessing.
/vault-mind:gaps candidate
(something they haven't written up) or a /vault-mind:recommend topic (something to read).Never create or edit files. If answering reveals a gap or error, report it and point to the
right skill (/vault-mind:gaps, :connect, :lint, :feynman); they act on it.
npx claudepluginhub jeff7712/vault-mind --plugin vault-mindGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.