sqlite-notes
Personal note-taking, thinking trails, and knowledge management using plain SQLite. Supports capture-heavy workflows with clear provenance tracking, AI-generated thinking snapshots (breadcrumbs), and synthesis into permanent knowledge. Uses the sqlite3 CLI directly with SQL schemas for notes, resources, clippings, reflections, and breadcrumbs.
What this skill does
# SQLite Notes - Personal Thinking Environment **A minimalist sqlite skill for note-taking, thinking trails, and knowledge building.** This skill uses SQLite as a local-first, composable thinking environment that captures the story of how you ended up thinking the way you do, with full lineage and provenance tracking. SQL is the interface, schemas are DDL, and the database is portable. ## Overview **sqlite-notes** transforms SQLite into a personal knowledge system that: - Captures notes, resources, clippings, and reflections with clear provenance - Generates AI thinking trail snapshots (breadcrumbs) to track intellectual momentum - Organizes notes through workflow stages (inbox, working, permanent, archive) - Links entities naturally through a flexible links table and structural foreign keys - Synthesizes insights from multiple sources with full lineage tracking - Provides full-text search with FTS5 (ranking, boolean operators, snippets) - Keeps all data local in a single `.sqlite/notes.db` file - Works seamlessly with Claude Code for AI-assisted thinking and synthesis ## Philosophy ### Capture-Heavy, Not Pristine This system prioritizes capturing the raw materials of thinking over maintaining a perfectly organized knowledge graph. Notes are allowed to be messy, incomplete, and evolving. The goal is to preserve the trail of how ideas developed, not to present a polished final product. ### Story Over Structure Rather than forcing everything into a predetermined taxonomy, this system captures the story of how you ended up thinking the way you do. Notes evolve from fleeting captures to permanent references. Breadcrumbs snapshot your thinking at a moment in time. Reflections synthesize patterns that emerge. ### Clear Provenance Every piece of content explicitly tracks its origin: - **me**: You authored it - **llm**: AI generated it entirely - **external**: Imported from elsewhere - **llm-assisted**: Collaborative creation between you and AI This transparency ensures you always know what came from where, and can trace the lineage of any idea. ### Epistemic Status Separate from *who* created content is *how validated* it is. The `epistemic` field tracks confidence: | Status | Meaning | |--------|---------| | **fleeting** | Uncaptured intuition, shower thought, might be nothing | | **developing** | Actively thinking about, exploring, not concluded | | **supported** | Has backing - evidence, reasoning, sources | | **settled** | Firm belief, integrated into worldview, acting on it | This applies equally to human and AI content. A shower thought (`origin: me, epistemic: fleeting`) and a Claude synthesis (`origin: llm, epistemic: fleeting`) both start unvalidated. Through review, either can become `supported` or `settled`. This enables workflows like syntopic reading where Claude explores sources and generates speculative connections. Those start as `fleeting`, get upgraded to `supported` when evidence backs them, and to `settled` when you've reviewed and accepted them into your thinking. ### AI as Thinking Partner Breadcrumbs and reflections leverage AI to: - Surface patterns you might miss - Connect ideas across time - Ask questions that push thinking forward - Synthesize insights from scattered notes But they preserve full context - the prompts used, the notes considered, the relationships formed - so you can verify and understand the AI's reasoning. ## When to Use This Skill **Use sqlite-notes as your memory-on-disk for thinking.** This skill is relevant whenever you need to: ### Capture & Organize Thoughts - Quick capture of fleeting ideas without friction - Save interesting quotes and highlights from reading - Track external resources (articles, papers, videos, repos) - Organize notes through workflow stages as they mature ### Track Thinking Over Time - Generate breadcrumb snapshots of current intellectual state - See what themes are emerging in your notes - Identify momentum (exploring, converging, scattered, breakthrough) - Maintain continuity between thinking sessions ### Synthesize Knowledge - Generate AI reflections from notes, breadcrumbs, and clippings - Promote valuable reflections into permanent notes - Build evergreen notes from accumulated insights - Trace lineage from source material to synthesized knowledge ### Link Ideas - Connect notes through explicit relationships in the links table - Query relationships between notes, resources, and clippings with JOINs - Discover unexpected patterns through graph traversal queries - Leverage SQL to find multi-hop connections ### Review & Process - Weekly review of inbox notes - Move notes between workflow stages - Tag and categorize during review - Identify stale working notes ### Replace Scattered Notes Instead of maintaining notes in: - Scattered markdown files - Ephemeral chat messages - Bookmarks that never get read - Mental notes that get forgotten Keep everything in one queryable, linkable, persistent database with full-text search. ## Core Tables ### notes The atomic unit of thought. Can be anything from a fleeting idea to a permanent reference note. **Key fields:** `id`, `title`, `body`, `folder`, `origin`, `epistemic`, `tags` (JSON array), `source_url`, `source_title`, `captured_at`, `reviewed_at` **Workflow stages (folder):** - **inbox**: Unsorted, recently captured - **journal**: Date-bound entries - **working**: Active development, exploring ideas - **permanent**: Evergreen, reference-quality - **archive**: Preserved but no longer active **Provenance (origin):** me, llm, external, llm-assisted **Epistemic status:** fleeting, developing, supported, settled ### breadcrumbs AI-generated snapshot of your thinking state at a moment in time. Analyzes recent notes to surface themes, connections, questions, and momentum. Forms a continuous trail over time through the `prev_breadcrumb_id` foreign key. **Key fields:** `id`, `summary`, `themes` (JSON array), `connections`, `questions` (JSON array), `momentum`, `window_start`, `window_end`, `notes_considered`, `prev_breadcrumb_id` (FK to breadcrumbs) **Momentum states:** exploring, converging, scattered, dormant, breakthrough ### resources External reference material (articles, books, papers, videos, repos, etc.) that you want to track and potentially extract highlights from. **Key fields:** `id`, `url`, `title`, `resource_type`, `status`, `author`, `domain`, `rating`, `summary`, `tags` (JSON array), `added_at`, `finished_at` **Resource types:** article, book, paper, video, podcast, repo, tool, course, thread, other **Status workflow:** queued → reading → finished (or abandoned/reference) ### clippings Quote, highlight, or excerpt from a resource. Captures exact text along with location and personal annotations. Uses `resource_id` foreign key for structural relationship (no separate link needed). **Key fields:** `id`, `content`, `annotation`, `location`, `chapter`, `source`, `resource_id` (FK to resources), `external_id`, `tags` (JSON array), `clipped_at` **Sources:** readwise, kindle, manual, web, pdf, other ### reflections AI-generated synthesis of notes, breadcrumbs, and clippings. Can be weekly reviews, theme explorations, connection maps, or custom formats. Tracks full generation context and can be promoted to permanent notes via `promoted_to_note_id` FK. **Key fields:** `id`, `title`, `content`, `reflection_type`, `template_used`, `prompt_context`, `model`, `status`, `epistemic`, `rating`, `feedback`, `promoted_to_note_id` (FK to notes), `generated_at` **Reflection types:** weekly-review, theme-synthesis, question-exploration, connection-map, insight, custom **Status workflow:** draft → reviewed → promoted (or discarded) ### links Generic relationship table for flexible many-to-many connections between any entities. This is the graph table. **Key fields:** `source_id`, `target_id`, `rel_type` **Relationship vocabulary:** - **linksTo**: Conceptual connection (note → note) - **derivedFrom**: Evo
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.