canonical-memory
Manage canonical (validated, durable) memory in INFYNON Trace. Use when user asks about architecture decisions, API contracts, promotion flows, or auditing canonical notes.
What this skill does
# Canonical Memory Management — Trace Skill ## When to Use Activate this skill when: - User asks about "truth memory", "canonical memory", or "validated knowledge" - User wants to store architecture decisions or API contracts - User asks what's safe to trust in the codebase - User wants to promote a note to the highest trust level - User needs to audit or validate existing canonical notes ## What Is Canonical Memory Canonical memory is the **smallest, most durable** layer in Trace's three-tier system. It stores knowledge that has been deliberately validated and is intended to be trusted across the team. **Not all memory should be treated equally.** "Truth memory which is always correct" is too strong a promise. Even canonical memory can become outdated when code changes. Use "canonical" or "validated" — never promise "always correct." ## What Belongs in Canonical | Category | Example | |----------|---------| | Architecture decisions | "All auth flows go through middleware" | | Stable API contracts | "POST /users returns 201 with Location header" | | Config invariants | "Rate limit is always per-IP, never global-only" | | Known security constraints | "Tokens are RS256 signed, never HS256" | | Canonical module facts | "Error handling uses InfynonError enum via thiserror" | | Migration rules | "All DB migrations must be backwards-compatible for 2 releases" | ## What Does NOT Belong in Canonical - Active caveats or temporary workarounds → **team memory** - Personal observations or unfinished thoughts → **user memory** - Branch-specific context → **team memory with branch scope** - Anything that hasn't been validated across at least one merge - Anything that changes frequently ## Promotion Rules A note should only enter canonical after: 1. **Merge** — the related code has landed in main 2. **Validation** — someone has verified the note matches current code 3. **Manual review** — a human has approved the promotion 4. **Repeated reuse without contradiction** — the note has been referenced multiple times without anyone correcting it ## Promotion Workflow ### Step 1: Identify a candidate ```bash # Find notes tagged for promotion infynon trace retrieve --tag promote # Or find long-lived, frequently-referenced team notes infynon trace retrieve --layer team --tag architecture ``` ### Step 2: Validate against current state Before promoting, verify: - Is the code still structured this way? - Has the API contract changed? - Are there any PRs that contradict this? - When was the note last updated? ### Step 3: Create the canonical note ```bash infynon trace note add canonical-<topic> \ --title "<Clear, factual statement>" \ --body "<Details with validation evidence. Include: which PRs validated this, since which version, any constraints.>" \ --layer canonical \ --scope repo \ --tags <relevant-tags> ``` ### Step 4: Archive the source note ```bash infynon trace note update <original-id> --status archived ``` ## Canonical Note Template Every canonical note should include in its body: ``` <Factual statement> Validated: PRs #X, #Y, #Z Stable since: vX.Y.Z Constraints: <any conditions under which this might change> Last verified: <date> ``` ## Auditing Canonical Memory Canonical notes can go stale. Regularly audit: ```bash # List all canonical notes infynon trace retrieve --layer canonical # Check for stale canonical notes infynon trace retrieve --layer canonical --tag stale ``` For each canonical note, ask: 1. Is this still true in the current codebase? 2. Has the code it references changed since `updated_at`? 3. Are there any contradicting team or user notes? If stale: ```bash # Mark as stale for review infynon trace note update <id> --status stale # Or archive if no longer valid infynon trace note update <id> --status archived ``` ## Tips - Keep canonical memory small — 10-20 notes for a medium project is healthy - Every canonical note should be something a new team member needs to know on day one - If you're unsure whether something is canonical, it's probably team memory - Run `infynon trace retrieve --layer canonical` at session start to ground yourself - Use SQL backends for canonical — they're durable, auditable, and queryable
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.