kb-elicit
Skill1 starsChanged 33 days agoMITView on GitHub
Use to run a structured knowledge-gathering dialogue in this repo — collaboratively frame the mind-map of areas, then drill top-down, turning the conversation into atomic notes. Reusable across knowledge bases via kb.framework.yml.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- kb-captureSkill
- kb-dashboardSkill
- kb-evolveSkill
- kb-goalSkill
- kb-orientSkill
- kb-planSkill
- kb-recallSkill
- kb-recapSkill
- kb-sanitizeSkill
- kb-visualizeSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 2 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read kb.config.yml (mode, language) and run kb-orient.
- Very specific: line 16
Read kb.framework.yml. Propose its areas as a recommended top-level skeleton — explicitly a starting point, not a mandate.
- Very specific: line 22
Update STATE.md: map framed.
- Very specific: line 43
Update STATE.md (current focus, next step — intent only.
- Very specific: line 55
Run npm run clarify -- [--topic TOP-xxx]: the ranked queue of open Q- notes and inline markers (must-priority, referenced and blocking …
- Distinctive: line 57
Ask at most 5 questions per round, one at a time, in queue order.
- Distinctive: line 60
After EACH answer, immediately write it through the pipeline:
- Very specific: line 66
Stop after 5, or when the owner says stop / defers.
- Very specific: line 85
Never edit index/ by hand.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
kb-elicit — dialogue engine (mind-map)
Goal: turn a conversation into a well-structured knowledge graph, top-down, saving each note only once it is a logically consistent, complete thought.
Method
Stage 0 — frame the map (when the map is empty, or on request)
- Read
kb.config.yml(mode, language) and runkb-orient. Check whether a map exists (anytype: topicnotes /index/mindmap.md). - Read
kb.framework.yml. Propose itsareasas a recommended top-level skeleton — explicitly a starting point, not a mandate. - Adapt WITH the user: add / rename / drop areas to fit this base.
- For each agreed top-level area, create a
topicnote (parent: null) viakb-capture, placed inknowledge/<key>/. Use the area'sframingquestions to seed the conversation. - Update
STATE.md: map framed; recommended next area. (Intent only — never copy counts/progress; those are generated inindex/. See CLAUDE.md → "STATE.md scope".)
Stage 1 — drill top-down (when a map exists)
- Present the agenda (see "Coverage / agenda" below) and propose where to dive. Agree on a node with the user.
- Frame the node: propose "what's worth collecting here" (sub-aspects). Capture
agreed sub-aspects as child
topicnotes (parent: <node>). A node's skeleton lives as prose in its body + child topics — there is no rigid checklist field (LLM-native: structure is the graph + prose). - Fill each sub-aspect: converse, asking clarifying questions, UNTIL the note is
logically consistent (a complete, coherent thought). Only then save it via
kb-capturewithtopic: <node>. - Anything unresolved is recorded, not dropped. A gap local to ONE note stays
inline in that note:
[NEEDS CLARIFICATION: …]/[ASSUMPTION: …](the note remainsdraft/proposed). A gap that spans notes or needs its own decision becomes a note: open question ->Q-, assumption ->ASMP-, risk ->RISK-, attached to the same node. - On request, propose options or research (web/evidence) and fold conclusions
back into notes — every external finding becomes a
sourcenote (SRC-) cited viasources:(see kb-capture → Evidence check). - Update
STATE.md(current focus, next step — intent only; no counts/progress, see "STATE.md scope").
Saving rule
Save when a note is logically consistent. Ask a clarifying question instead of saving a half-formed note. Confirm with the user only when a write OVERWRITES existing knowledge; new, consistent knowledge is captured as it forms.
Recurring concern? If the same risk/assumption/trade-off recurs across ≥2 notes, canonicalize it into ONE note and link the others to it — don't re-state the same thought in multiple bodies (see kb-capture "Recurring-concern check").
Clarify loop (resolve gaps — on request, or when the agenda is mostly gaps)
- Run
npm run clarify -- [--topic TOP-xxx]: the ranked queue of openQ-notes and inline markers (must-priority, referenced and blocking items first). - Ask at most 5 questions per round, one at a time, in queue order. Each question offers a recommended answer (with a one-line why) plus 2–4 alternatives, or asks for a short free answer. Never batch them into a wall.
- After EACH answer, immediately write it through the pipeline:
- edit the affected note: replace the marker / contradicting text with the
answer (a resolved
Q-→status: acceptedwith the answer in its body, linked viarelations: { answers: [Q-…] }from the note it settles); - append to that note's body, under
## Clarifications→### YYYY-MM-DD:- Q: <question> → A: <answer>(append-only; the dated log of why it changed).
- edit the affected note: replace the marker / contradicting text with the
answer (a resolved
- Stop after 5, or when the owner says stop / defers. Deferred items stay as
markers / open
Q-— never silently dropped. Report: resolved / deferred / still open.
Coverage / agenda (what to work on next)
Compose, do not maintain a separate drifting artifact:
- Empty areas — from
index/MAP.md(count 0). - Open
Q-/ASMP-/RISK-notes and "Unresolved markers" inindex/health.md— known gaps. - Topic nodes with no attached notes — from
index/mindmap.md. - Coverage gaps — from
index/coverage.md(e.g. a must-requirement no story delivers, a pain nothing addresses, a risk nothing mitigates).
Output (per mode)
debug: state which notes you created/updated, their ids, and the agenda.autonomous: short human acknowledgements; hide ids and wiki mechanics.
Rules
- Capture only via
kb-capture; resolve-before-write to avoid duplicates. - Never edit
index/by hand. After writes, the Stop hook reindexes. - One concept per note. Keep
topic/parentpointing at realTOP-notes. - Suggest running
kb-visualizewhen the user wants to see the map.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

