memory-ops
Store, retrieve, and manage codebase knowledge in INFYNON Trace. Use when user asks about shared notes, handoffs, PR context, architecture memory, backends (Redis/SQL), knowledge graph, or when .infynon/trace/ is detected.
What this skill does
# Memory Operations — Trace Skill ## When to Use Activate this skill when: - User asks about coding memory, shared notes, or repo context - User wants to store, retrieve, or update knowledge about the codebase - User mentions handoffs, PR notes, architecture decisions, or team knowledge - User asks about canonical memory, team memory, or user memory - User wants to set up a memory backend (Redis or SQL) - User asks about Trace or `infynon trace` - `.infynon/trace/config.toml` is detected in the project - User asks about knowledge graph, entity relationships, or how things connect in the repo - User wants to visualize code relationships, file dependencies, or people-to-file mappings - User asks about graph diff, impact analysis, or path finding between entities ## Critical Rules 1. **Layer discipline.** Always place notes in the correct layer: - **Canonical** — architecture decisions, API contracts, config invariants, security constraints, module facts, migration rules - **Team** — active caveats, branch notes, handoffs, PR summaries, risky areas, unresolved issues - **User** — personal reminders, local observations, unfinished thoughts, task context 2. **Never auto-create canonical notes.** Canonical notes are promoted, not auto-written. 3. **Always resolve default user** from `infynon trace` config when `--author` is not specified. 4. **Every note should track provenance:** source commit, status, confidence, updated_at. ## Prerequisites ```bash infynon --version ``` If not installed: ```bash npm install -g infynon ``` ## Initialize Trace ```bash # Initialize with repo identity infynon trace init # Add a SQL backend (recommended for canonical + team memory) infynon trace source add-sql team-db \ --engine sqlite \ --url sqlite://.infynon/trace/trace.db \ --user <username> \ --default # Or add Redis for fast session-style coordination infynon trace source add-redis team-redis \ --url redis://localhost:6379/0 \ --namespace infynon \ --user <username> ``` ## Command Reference by User Intent ### "I want to store a note about the codebase" ```bash # Team-level note (most common) infynon trace note add <id> \ --title "Description" \ --body "Details" \ --layer team \ --scope repo # Branch-specific handoff infynon trace note add <id> \ --title "Handoff note" \ --body "What the next person needs to know" \ --layer team \ --scope branch \ --target feature/my-branch \ --tags handoff # PR-linked note infynon trace note add <id> \ --title "PR context" \ --body "Why this change was made" \ --layer team \ --scope pr \ --target 142 \ --related-pr 142 # File-scoped note infynon trace note add <id> \ --title "Watch out" \ --body "This module has a known race condition" \ --layer team \ --scope file \ --target src/auth.rs \ --files src/auth.rs \ --tags caveat,race-condition # Package note (who introduced a risky dependency) infynon trace note add <id> \ --title "chrono added" \ --body "Added for Trace sync timestamps. Low risk." \ --layer user \ --scope package \ --target chrono ``` ### "I want to find relevant notes" ```bash # All canonical memory infynon trace retrieve --layer canonical --format markdown # Team notes for current branch infynon trace retrieve --layer team --scope branch --target <branch-name> --format markdown # Notes about a specific file infynon trace retrieve --scope file --target src/auth.rs # Notes by a specific author infynon trace retrieve --author alien # Notes with a specific tag infynon trace retrieve --tag handoff # Package notes infynon trace retrieve --scope package --target chrono # PR-linked notes infynon trace retrieve --scope pr --target 142 ``` ### "I want to update or clean up notes" ```bash # Mark a note as stale infynon trace note update <id> --status stale # Update note content infynon trace note update <id> --title "New title" --body "Updated content" # Remove a note infynon trace note remove <id> # Compact stale and session notes infynon trace compact ``` ### "I want to sync with a remote backend" ```bash # Push local notes to remote infynon trace sync --direction push # Pull remote notes locally infynon trace sync --direction pull # Bidirectional sync infynon trace sync --direction both # Sync with a specific backend infynon trace sync --source team-db --direction both ``` ### "I want to promote a note to canonical" Canonical notes are never auto-created. The promotion path: 1. Start as user or team note 2. Validate against current code state 3. Confirm the note has been stable (no contradictions across merges) 4. Create the canonical version ```bash # Step 1: Flag for promotion infynon trace note update my-note --tags promote,canonical-candidate # Step 2: After review, create canonical note infynon trace note add arch-<topic> \ --title "Architectural decision: ..." \ --body "Validated across PRs #x, #y. Stable since v0.x.x." \ --layer canonical \ --scope repo \ --tags architecture # Step 3: Archive the original team note infynon trace note update my-note --status archived ``` ### "I want to set up backends" ```bash # List current backends infynon trace source list # Add SQLite (local, good for canonical + team) infynon trace source add-sql local-db \ --engine sqlite \ --url sqlite://.infynon/trace/trace.db \ --user <username> \ --default # Add PostgreSQL (shared team database) infynon trace source add-sql team-db \ --engine postgres \ --url postgres://user:[email protected]:5432/infynon \ --user <username> # Add Redis (fast session state) infynon trace source add-redis session-redis \ --url redis://localhost:6379/0 \ --namespace infynon \ --user <username> # Set default backend infynon trace source default team-db # Remove a backend infynon trace source remove old-source # View backend schema infynon trace schema sql infynon trace schema redis ``` ## Backend Selection Guide | Use Case | Backend | Why | |----------|---------|-----| | Canonical memory | SQL (SQLite/Postgres) | Durable, auditable, structured queries | | Team memory | SQL or Redis | SQL for history, Redis for live coordination | | User memory | Local files or SQLite | Personal, low overhead | | Session state | Redis | Fast, ephemeral, auto-expiring | | CI/CD integration | SQL (Postgres) | Shared across runners, queryable | | Multi-machine sync | Redis or Postgres | Network-accessible | ## Note Scopes | Scope | Use For | Example Target | |-------|---------|----------------| | `repo` | Repository-wide facts | `current` | | `branch` | Branch-specific context | `feature/auth-refresh` | | `pr` | PR-linked notes | `142` | | `file` | File-specific caveats | `src/auth.rs` | | `user` | User-specific notes | `alien` | | `session` | Temporary session context | `current` | | `package` | Dependency provenance | `chrono` | ## TUI ```bash infynon trace tui ``` **6 Tabs:** | Key | Tab | Purpose | |-----|-----|---------| | 1 | Overview | Trace status, config summary, layer counts | | 2 | Sources | Backend list, connection status, default indicator | | 3 | Notes | Browse all notes, filter by layer/scope/status | | 4 | Packages | Package findings with `installed_by` attribution | | 5 | EditLog | History of note changes | | 6 | Graph | Knowledge graph: entities, edges, visual view, branch switching | **TUI Keys:** - `Tab` / `Shift+Tab` — navigate fields - `Enter` — edit field - `q` — quit - Arrow keys — scroll and navigate - `b` — switch branch (Graph tab) - `a` — toggle all-branches view (Graph tab) - `B` — auto-build graph (Graph tab) - `n` — new entity/edge (Graph tab) - `d` — delete entity/edge (Graph tab) ### "I want to use the knowledge graph" The knowledge graph maps entities (files, packages, people, decisions, vulnerabilities) and relationships between them, scoped per branch. ```bash # Auto-build graph from git history and existing notes infynon trace graph build # Add entities manually infynon trace
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.