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/dotclaude 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 14, 2026, 3:02 AM178.5s1 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. Electron writes a harmless warning to stderr on every invocation. Suppress with 2>/dev/null when parsing.
| Output | Meaning |
| ------------------------ | ------------------------------------ |
| {"status":"ready",...} | Server up. Proceed |
| Hangs / non-JSON | Desktop app closed or CLI toggle off |
Commands
Run heptabase <sub> -h for argument details (flags vary per subcommand).
| 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) |
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/use-cli-herdr
tools
VerifiedTrustedCommunity
Delegate implementation to codex (coder) via the herdr-agentchat plugin and drive a two-pane conversation to completion.
11SKILL.mdUpdated Jul 27, 2026
thkt/scribe
development
VerifiedTrustedCommunity
Extract recurring patterns from past closed PRs/issues and the research findings in workspace/research/, verify them against the latest code, and propose them to docs/wiki/ via PR.
11SKILL.mdUpdated Jul 20, 2026
thkt/dr
development
VerifiedTrustedCommunity
Create Decision Records (DR) in MADR v4 format with auto-numbering.
11SKILL.mdUpdated Jul 15, 2026
thkt/shake
development
VerifiedTrustedCommunity
Detect flaky tests by shaking them — repeated runs under varied order, parallelism, and seed — plus a static smell scan that flags latent flakiness in tests that currently pass. Classify each target as confirmed-flaky, latent-flaky, or stable and fix the root cause without weakening the test. Do NOT use to fix a confirmed single bug (use /fix) or for static-only code review (use /audit).
11SKILL.mdUpdated Jul 13, 2026