review-crate
Deep-review a Rust crate end to end: read every file, run the crate tests, verify real findings, and write or append a canonical issue file under the current repository's `.ulpi/issues/` directory. Runs as a forked analysis workflow so the audit has separate reasoning budget.
What this skill does
<EXTREMELY-IMPORTANT> This skill is only valid if it actually reads the whole crate. Non-negotiable rules: 1. Enumerate and read every file in the target crate. 2. Run the crate's tests unless there is a concrete blocker. 3. Ground every finding in exact `file:line` evidence. 4. Check the current repository's canonical issue file before writing new findings. 5. Write findings only to `.ulpi/issues/<crate-name>.md` in this repository. </EXTREMELY-IMPORTANT> # review-crate ## Inputs - `$crate_path`: Path to the crate directory ## Goal Perform a complete crate audit that: - reads the entire crate - runs tests - reports real bugs and coverage gaps - updates the canonical local issue file without duplicating prior findings ## Step 0: Resolve crate identity Determine: - crate path - crate name from `Cargo.toml` - canonical issue file path: `.ulpi/issues/<crate-name>.md` If the crate path is invalid, stop and say so clearly. **Success criteria**: The crate and issue-file target are explicit before review begins. ## Step 1: Enumerate and read the whole crate Read every file in the crate, including: - `Cargo.toml` - source files - test files - crate-local docs such as `CLAUDE.md` - supporting docs in the crate directory Do not sample. Do not stop after "main files". **Success criteria**: You can honestly state that the whole crate was read. ## Step 2: Run crate tests Run the narrowest full-crate verification that makes sense, typically: - `cargo test -p <crate-name> -- --nocapture` If tests cannot run, report the exact blocker. **Success criteria**: The review includes real crate-test signal or a concrete reason it is unavailable. ## Step 3: Check the existing issue file If `.ulpi/issues/<crate-name>.md` already exists: - read it first - avoid duplicating existing findings - append only genuinely new issues If it does not exist: - create it when there are findings worth recording **Success criteria**: The issue file remains canonical and non-duplicative. ## Step 4: Analyze and write findings Look for: - correctness bugs - panic or crash risks - validation gaps - race or state issues - data corruption risks - performance traps that are clearly real - coverage gaps around risky behavior For each finding include: - severity - category - exact `file:line` - why the issue is real - suggested fix direction Label uncertain claims as `INFERENCE` and explain why they are uncertain. **Success criteria**: Findings are evidence-driven and actionable. ## Step 5: Finish with residual risk Report: - files read - test results - findings written or appended - remaining uncertainty or coverage gaps If there are no material findings, say so explicitly. **Success criteria**: The user understands both what was reviewed and what risk remains. ## Guardrails - Do not write findings to external absolute paths outside this repository. - Do not claim full review if files were skipped. - Do not invent issues from intuition alone. - Do not add `disable-model-invocation`; this is a valid deep-audit workflow. - Do not turn this into a multi-crate sweep. ## Output Contract Report: 1. crate reviewed 2. file count and statement that the whole crate was read 3. test results 4. findings by severity 5. issue file written or appended 6. residual risk or clean result
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.