thkt/use-cli-heptabase
skills/use-cli-heptabase/SKILL.md
Read and write Heptabase cards, journals, notes, tags, and AI Tutor data via heptabase CLI. All output is JSON.
$ install --global
skillsauthnpx skillsauth add thkt/claude-config use-cli-heptabaseInstall 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: Jun 12, 2026, 2:39 AM28.7s1 file scanned
SKILL.md
- name:
- use-cli-heptabase
- description:
- Read and write Heptabase cards, journals, notes, tags, and AI Tutor data via heptabase CLI. All output is JSON.
- when_to_use:
- Heptabase, ヘプタベース, card library, カード, note card, ノートカード, journal entry, ジャーナル, AI Tutor, タグ管理, knowledge base write, ナレッジベース書き込み
- allowed-tools:
- Bash Read
- user-invocable:
- false
use-cli-heptabase
Heptabase CLI (heptabase, v0.1.0+). Desktop app must be running with CLI enabled (Settings → AI Features → CLI).
Prerequisite
Run heptabase start first.
| Output | Meaning |
| ------------------------ | ------------------------------------ |
| {"status":"ready",...} | Server up. Proceed |
| Hangs / non-JSON | Desktop app closed or CLI toggle off |
Electron writes a harmless warning to stderr on every invocation. Suppress with 2>/dev/null when parsing.
Commands
| Purpose | Command |
| ---------------------------------- | ------------------------------------------------------------- | ------ | ----------------------- | ------------ |
| Server ready check | heptabase start |
| List / search cards | heptabase card list --limit N --offset M |
| Trash / restore card | heptabase card trash <id> / heptabase card restore <id> |
| Create note (markdown) | heptabase note create (first # heading = title) |
| Read note | heptabase note read <cardId> |
| Append note (markdown) | heptabase note append <cardId> |
| Replace note (ProseMirror JSON) | heptabase note save <cardId> (needs contentMd5 from read) |
| Journal CRUD by date | heptabase journal create | read | append | save <date> |
| Tag list / create / add / remove | heptabase tag list | create | add | remove |
| Cards under a tag | heptabase tag cards <tagId> |
| AI Tutor goals / courses / lessons | heptabase goal | course | lesson ... (read-only) |
Run heptabase <sub> -h for argument details (flags vary per subcommand).
Content Format
| Operation | Format |
| --------------- | ----------------------------------------------------------- |
| create / append | Markdown |
| read | ProseMirror JSON (returns contentMd5) |
| save | ProseMirror JSON (requires latest contentMd5 from read) |
When to Use
| use-cli-heptabase | Alternative | | ---------------------------------------------------------- | ------------------------ | | Write back to knowledge base (journal append, note create) | Local markdown repo edit | | Card library lookup by title / recency | kiku (Slack) | | AI Tutor course / lesson / chat read | n/a |
Warm-up (first use in session)
heptabase startreturns{"status":"ready"}heptabase card list --limit 3for read smoke test- Use
-hon any subcommand before first write
Related Skills
thkt/outcome
documentation
VerifiedTrustedCommunity
Generates and updates .claude/OUTCOME.md interactively. When the file is absent or empty (no Behavior / all sections TBD), collects content via AskUserQuestion and writes the stub; when present, shows the current state and applies updates.
9SKILL.mdUpdated Jun 12, 2026
thkt/audit-skill-craft
development
VerifiedTrustedCommunity
Judge a SKILL.md against craft axes (single responsibility, description distinctiveness, imperative voice, verifiable completion, calibration, progressive disclosure) and apply the fixes the audit surfaces. Do not use for format-presence-only checks (use reviewer-prompt) or reproducibility loops (use /tuning).
9SKILL.mdUpdated Jun 11, 2026
thkt/use-workflow-plan-preview
tools
VerifiedTrustedCommunity
Internal helper for /think Step 11. Renders SOW.md + Spec.md as an integrated Astro view and returns a dev server URL.
9SKILL.mdUpdated Jun 1, 2026
thkt/probe
development
VerifiedTrustedCommunity
Extract repository spec while detecting bugs, spec gaps, and consistency drift via dual-purpose documentation. OUTCOME.md-axis question-driven exploration with ephemeral output. Do NOT use for code review (use /audit or /polish), feature implementation (use /code), planning only (use /think), or single-bug fix (use /fix).
9SKILL.mdUpdated Jun 1, 2026