shihyuho/ultrabrain
plugins/ultrabrain/skills/ultrabrain/SKILL.md
Personal wiki at ~/.ultrabrain/ that accumulates knowledge across sessions using an LLM-maintained-wiki pattern. Use when the user asks factual, technical, or decision-oriented questions that may have been previously captured (check index.md before answering), or explicitly asks to capture/記下來/save session content, ingest/整合 raw entries into the wiki, lint/檢查 the vault, or bootstrap a new vault. Skip for small talk, current-file questions, or code-execution requests.
development
Updated May 3, 2026
$ install --global
skillsauthnpx skillsauth add shihyuho/skills ultrabrainInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 3, 2026, 4:26 AM190.8s8 files scanned
SKILL.md
- name:
- ultrabrain
- description:
- Personal wiki at ~/.ultrabrain/ that accumulates knowledge across sessions using an LLM-maintained-wiki pattern. Use when the user asks factual, technical, or decision-oriented questions that may have been previously captured (check index.md before answering), or explicitly asks to capture/記下來/save session content, ingest/整合 raw entries into the wiki, lint/檢查 the vault, or bootstrap a new vault. Skip for small talk, current-file questions, or code-execution requests.
- license:
- MIT
Ultrabrain
Drive a personal, LLM-maintained wiki at ~/.ultrabrain/. This skill is a thin trigger layer — the vault is self-contained and methodology rules live in ~/.ultrabrain/AGENTS.md, not here.
Trigger Contract
Five operations. The first two are skill-side; the last three delegate to vault rules.
| Operation | Trigger examples |
|-----------|------------------|
| bootstrap | "bootstrap ultrabrain", "initialize vault", "設定 ultrabrain", or any other operation fires with no vault present |
| capture | "記下來 X", "capture this", "save to vault", "存進 vault", or "capture <path-or-url>" |
| ingest | "ingest", "integrate raw", "整合 raw", "整理 vault" |
| query | description-driven for factual/technical/decision questions, or explicit: "查 vault", "search ultrabrain" |
| lint | "lint vault", "健檢 vault", "check wiki" |
Query skip clause
Before reading any vault file for query, verify the user's question plausibly concerns retained knowledge. Skip the vault (answer normally) when the question is:
- Small talk — greetings, thanks, session meta-questions.
- Context-local — answerable from the current session or open files ("what does this file do", "why did that fail").
- Execution requests — "write this", "run that", "refactor X". Vault holds facts, not tasks.
When classification is uncertain, default to skipping. Aggressive description triggering is balanced by this negative filter, not overridden.
Operations
Full step-by-step lives in references/operations.md. Summary:
bootstrapcreates~/.ultrabrain/withAGENTS.md(copied fromreferences/agents-template.md),CLAUDE.md(one line:@AGENTS.md), emptyindex.mdandlog.md, andraw//wiki/directories. Refuses if the vault exists unless--forceis passed.capturewrites session or file content toraw/YYYY-MM-DD-<slug>.mdwith frontmatter. Resolves ambiguous "記下來" requests by proposing a scope and waiting for user confirmation. Never silently overwrites — collisions go to suffixed filenames or a user-chosen append.ingestloads~/.ultrabrain/AGENTS.mdand follows itsOperation: Ingestsection to integrate unprocessedraw/files intowiki/, moving processed raw toraw/.processed/.queryloadsAGENTS.md, readsindex.mdfirst, then follows the vault's query rules (index-first strict; no Grep fallback). Answers cite specific wiki pages. Falls back to general knowledge if the vault is empty, with an explicit note.lintloadsAGENTS.mdand produces a health report (contradictions, orphans, stale pages, index drift, missing cross-references). Never auto-fixes; asks the user which findings to address.
Every operation appends one line to log.md in the format ISO-8601 OPERATION details.
Vault Contract
Vault location: ~/.ultrabrain/.
AGENTS.md is the single source of truth for methodology. The skill's contract with it is behavioral, not structural — AGENTS.md must define how to perform ingest, query, and lint, in whatever structure the methodology author prefers. The skill makes no assumptions about section headings, page types, tag schemas, or cross-reference syntax.
~/.ultrabrain/CLAUDE.md is exactly one line: @AGENTS.md. This makes the vault rules auto-load if the user cds into the vault inside Claude Code; AGENTS.md stays canonical for cross-tool compatibility.
Vault-side operations (ingest, query, lint) halt if AGENTS.md is missing. Ask the user to bootstrap or restore the file.
The skill treats the vault as read-only except for paths each operation is defined to touch (see references/operations.md).
Methodology Swap
The v1.0.0 default methodology is Karpathy's LLM-maintained-wiki pattern (see references/karpathy-original.md for the source and references/agents-template.md for the agent-readable rendering). To swap:
- Replace
references/agents-template.mdwith rules for a different methodology. Only requirement: the new template must defineingest,query, andlintbehaviors. - Run
bootstrap --forceto wipe and rebuild the vault. Destructive — back up~/.ultrabrain/raw/first if you want to preserve source material for re-capture.
Hooks
Two hooks are available but not auto-installed:
SessionStart— injects vault status (wiki count, unprocessed raw, last ingest) at session start so Claude is aware the vault is available.PreCompact— injects a reminder before context compaction to capture important session content before detail is lost.
On explicit user request ("install ultrabrain hooks"), follow references/setup.md to copy both hook scripts and merge the entries into ~/.claude/settings.json using Read → diff → confirm → Edit discipline. Both hooks install as a bundle; either can be uninstalled individually later.
References
references/karpathy-original.md— verbatim source methodology + attributionreferences/agents-template.md— bootstrap copies this to~/.ultrabrain/AGENTS.mdreferences/operations.md— full step-by-step for all five operationsreferences/setup.md— hook install/uninstall (SessionStart + PreCompact)references/hooks/session-start.sh— vault status injection on session startreferences/hooks/pre-compact.sh— capture reminder before compaction
Related Skills
shihyuho/skills/artifact-anatomy
development
VerifiedTrustedCommunity
--- name: artifact-anatomy description: Defines where spec-driven working artifacts — the spec (e.g. `SPEC.md`), the plan, and the task list (e.g. `tasks/plan.md`, `tasks/todo.md`) — live on disk under `docs/specs/<id>-<slug>/`, and how those directories are numbered, scoped, and resolved so multiple specs can run in parallel without overwriting one another. Use this BEFORE creating, locating, or updating any spec, plan, or task/todo file: whenever a spec/plan/build workflow writes these artifac
SKILL.mdUpdated Jun 11, 2026
shihyuho/review-briefing
development
VerifiedTrustedCommunity
Write a short author's briefing to hand to a code reviewer whose agent already has its own review skill, so it supplies the context that skill can't see instead of repeating how to review. Right after you finish a piece of work, it mines this session (and any kickoff implementation-notes) for what the reviewer most needs flagged — the easy-to-miss changes, the parts you're least sure about, the looks-wrong-but-intentional bits, and the blast radius — plus the exact commit range to review. Use when you've just finished work and want to hand the review off to another agent, chat, or teammate, when you want a "heads-up for the reviewer", or when packaging a change for review elsewhere. It does not perform the review and does not re-specify severity tiers or output format — that's the reviewer's own skill's job.
SKILL.mdUpdated May 28, 2026
shihyuho/writing-agents-md
testing
VerifiedTrustedCommunity
Use when creating, rewriting, pruning, or reviewing `AGENTS.md` or `CLAUDE.md`, especially to remove repo summaries, stale rules, and other low-signal global instructions. Trigger when deciding what belongs in always-on agent files versus a task-specific skill.
SKILL.mdUpdated May 27, 2026
shihyuho/tutor
development
VerifiedTrustedCommunity
Drive a structured tutoring workflow that turns Claude into a learning onramp accelerator — consultative diagnosis → custom syllabus → unit-by-unit guided lessons with notes/whiteboard → dynamic adjustment from an accumulating learner profile. Use when the user states a learning goal ("I want to systematically learn X", "teach me Y", "help me prep for Z exam"), uploads study materials and asks for a course plan, or signals sustained guided study (mentions tutor, syllabus, course, lessons, study plan, curriculum, 家教, 學習路徑). Skip for one-shot factual Q&A or quick code-context explanations.
SKILL.mdUpdated May 27, 2026