Agent skill
fastnote-cli-operator
Operate the FastNote local notebook through natural language by mapping requests to note CRUD, search, pin, and tag commands. Use this whenever the user wants to create, list, inspect, update, pin, unpin, delete, or review FastNote notes or tags, even if they never mention the CLI. Execute the bundled zero-dependency script directly instead of relying on the project package runtime.
Install this agent skill to your Project
npx add-skill https://github.com/hexbee/hello-skills/tree/main/skills/fastnote-cli-operator
SKILL.md
FastNote CLI Operator
Use this skill to turn natural-language FastNote requests into direct local note operations.
What this skill does
- Executes FastNote note operations without importing the FastNote app
- Uses the bundled script at
scripts/fastnote_cli.py - Reads and writes the same SQLite database schema as the project CLI
- Returns a short human summary first, then the raw JSON payload
Command coverage
Map user intent onto one of these commands:
listget <id>createupdate <id>delete <id>pin <id> --value true|falsetags
list returns note summaries to keep agent context small.
get returns the full note, including content.
For long or multi-line note bodies, prefer --content-file or --content-stdin over --content.
Safety and decision rules
- Treat
updateas full replacement. - If the user asks to update a note but omits title, content, or pinned state, ask for the missing fields instead of guessing.
- Only execute
deleteimmediately when the user is explicit that no confirmation is needed, such as "delete note 12 now" or "remove 12, no need to confirm". - If the delete intent is not explicit enough, ask for confirmation before running it.
- Preserve the CLI's strict boolean style: use
trueandfalse. - If the note body is long, contains multiple paragraphs, or includes Chinese long-form text, use
--content-fileor--content-stdinto avoid shell length, quoting, and newline issues.
Execution
Run the bundled script with Python from any shell:
python skills/fastnote-cli-operator/scripts/fastnote_cli.py <command> ...
If needed, pass an explicit database path:
python skills/fastnote-cli-operator/scripts/fastnote_cli.py --db /absolute/path/to/fastnote.sqlite3 <command> ...
If --db is omitted, the script resolves the default FastNote database path by platform:
- Windows:
%LOCALAPPDATA%\FastNote\fastnote.sqlite3 - macOS:
~/Library/Application Support/FastNote/fastnote.sqlite3 - Linux:
~/.local/share/FastNote/fastnote.sqlite3
The script itself is cross-platform. Avoid shell-specific wrappers unless the user explicitly asks for one.
Response format
Always reply in two parts:
- A concise natural-language summary of what happened
- The raw JSON returned by the script
Examples:
- Create success: "Created note 14 titled
Inboxwith tagswork,urgent." - List success: "Found 3 notes, including 2 pinned notes."
- Delete success: "Deleted note 9."
- Not found: "Note 9 does not exist."
Then include the JSON payload in a fenced json block.
For context efficiency:
listreturnsid,title,preview,is_pinned,created_at,updated_at, andtagsgetreturns the full note object, includingcontent
First-use transparency
On every run, the script includes a meta object with:
db_path: the exact SQLite file path in usedb_initialized: whether this run created the database file for first usedata_dir_created: whether this run created the parent data directorybackup_reminder: a reminder to back up the database file regularly
When db_initialized is true, tell the user plainly that:
- the skill created a local FastNote SQLite database for them
- where the database file is located
- that the data stays local on this machine
- they should back up the SQLite file periodically
Keep this explanation short but explicit. The point is transparency and trust, not verbosity.
Use this template on first use, adapting only the path:
This is the first time this FastNote skill has been used on this machine, so it created a local SQLite database for your notes.
Database path: <db_path>
Your data stays on this machine. Back up this SQLite file periodically if you want to avoid accidental data loss.
On later runs, if it helps the task, you can use this shorter template:
FastNote database in use: <db_path>
Remember to back up this SQLite file periodically.
Common mappings
Example 1 User: "Create a pinned note titled sprint plan with content finalize API scope and tags work, planning" Action:
python skills/fastnote-cli-operator/scripts/fastnote_cli.py create --title "sprint plan" --content "finalize API scope" --tag work --tag planning --pinned true
Example 1b User: "Create a note from this long draft" Action:
python skills/fastnote-cli-operator/scripts/fastnote_cli.py create --title "draft" --content-file /absolute/path/to/draft.txt --pinned false
Example 2 User: "Show pinned notes tagged work" Action:
python skills/fastnote-cli-operator/scripts/fastnote_cli.py list --tag work --pinned true
Example 3 User: "Set note 7 to unpinned" Action:
python skills/fastnote-cli-operator/scripts/fastnote_cli.py pin 7 --value false
Example 4 User: "Update note 5 title to Draft v2 and content to Updated body, keep it unpinned, tags todo and urgent" Action:
python skills/fastnote-cli-operator/scripts/fastnote_cli.py update 5 --title "Draft v2" --content "Updated body" --tag todo --tag urgent --pinned false
When the content comes from stdin:
python skills/fastnote-cli-operator/scripts/fastnote_cli.py update 5 --title "Draft v2" --content-stdin --tag todo --pinned false
Implementation notes
- The script intentionally has zero third-party dependencies.
- It mirrors the current FastNote CLI JSON envelopes and exit codes.
- It depends on the repository's SQLite schema staying compatible.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
analogy-commentary
Turn source content into a familiar analogy framework, then produce concise commentary angles and a short take. Use when the user asks whether a post, article, speech, or idea is “like” a known story, theory, faction, historical pattern, or strategic lens.
deep-productivity
Master deep work productivity through the three types of work framework (Building, Maintenance, Recovery). Use when user needs to: (1) Build a sustainable deep work routine with just 1 hour/day, (2) Create vision/anti-vision for life direction, (3) Structure goals using the 10-year → 1-year → 1-month → 1-week hierarchy, (4) Apply project-based learning to bridge skill gaps, (5) Identify lever-moving tasks that actually progress goals, (6) Balance focus work with necessary recovery for creativity.
multi-agent-systems
Design and implement multi-agent LLM architectures using the orchestrator-subagent pattern. Use when: (1) Deciding whether to use multi-agent vs single-agent systems, (2) Implementing context isolation for high-volume operations, (3) Parallelizing independent research tasks, (4) Creating specialized agents with focused tool sets, (5) Building verification subagents for quality assurance, or (6) Analyzing context-centric decomposition boundaries.
agent-first-product-strategy
Reframe AI product and SaaS strategy from human-user assumptions to agent-first execution. Use when redefining product positioning, success metrics, API/docs priorities, go-to-market, or roadmap decisions for an AI-native market where agents are primary software users.
claim-ledger
将研究与写作中的主张转成“Claim-Evidence-Boundary”可核验账本。用于在产出前强制补齐证据、反证、边界与可发布性判断,防止无依据断言并提升复用性。
debog-yourself
Help users identify and escape psychological traps that are holding them back. Use when user feels stuck, unable to progress, facing a deadlock, or experiencing decision paralysis. Provide diagnostic frameworks and specific strategies to help users understand which trap pattern they're in and find a path forward.
Didn't find tool you were looking for?