xanadassistant

Use when: reviewing .prompt.md, .agent.md, SKILL.md, or .instructions.md files for contradictions, ambiguity, persona consistency, cognitive load, coverage gaps, and composition conflicts.

Use when: checking xanadAssistant workspace health, install status, repair reasons, or lockfile validity before proposing install, update, repair, or restore operations.

Use when: designing or reviewing CI/CD pipelines, GitHub Actions, stage design, environment gates, or artifact discipline.

Use when: writing or reviewing Dockerfiles, container images, multi-stage builds, layer caching, or image security.

Use when: writing or reviewing Infrastructure as Code for naming, state management, modularity, and drift detection.

Use when: reviewing DevOps changes for pipeline safety, secret hygiene, permissions, rollback, and deployment risk.

Use when: writing or reviewing API and code documentation, including docstrings, OpenAPI patterns, and parameter tables.

Use when: reviewing documentation for accuracy, completeness, clarity, link health, and merge readiness.

Use when: structuring documentation with Diátaxis, README anatomy, ADR format, or section ordering conventions.

Use when: improving documentation writing style, prose register, active voice, imperative mood, or term consistency.

Use when: designing or reviewing ML data pipelines for versioning, feature engineering discipline, and leakage prevention.

Use when: designing, reviewing, or debugging ML experiments for reproducibility, hyperparameter discipline, and metric logging.

Use when: designing or reviewing model serving workflows, registry usage, versioning, A/B tests, canary deployments, or drift monitoring.

Use when: reviewing ML code or experiment plans for data leakage, bias, reproducibility, and serving risk.

Use when: generating or reviewing OSS changelog entries with Keep a Changelog format, versioning discipline, or git history.

Use when: reviewing OSS pull requests against review standards, comment etiquette, and contribution gate criteria.

Use when: writing or reviewing OSS contributing guidance, CONTRIBUTING.md structure, DCO/CLA guidance, or contributor onboarding checklists.

Use when: choosing or reviewing OSS licenses, LICENSE file format, SPDX identifiers, or header placement.

Use when: running or participating in a Shape Up betting table, evaluating pitches for the next cycle, setting appetite, sizing teams, or deciding which pitches to bet on.

Use when: executing or tracking Shape Up cycle work, managing in-cycle scope, using hill charts, applying scope hammering, or deciding whether to invoke the circuit breaker.

Use when: writing, reviewing, or refining Shape Up pitches for drafting, completeness critique, or betting table preparation.

Use when: auditing a Shape Up pitch for completeness, reviewing in-cycle scope discipline, or validating that a betting table decision meets Shape Up principles.

Use when: running pre-commit or pre-push CI-equivalent checks in any workspace — discovers the project's CI workflow commands using workspace tools, filters for local executability, scopes to staged changes, and runs checks cheapest-first before delegating failures.

Use when: discovering package manifests, querying registry metadata, assessing dependency health signals, finding replacement candidates, or confirming import usage before removing a package.

Use when: discovering, recommending, installing, enabling, disabling, or uninstalling VS Code extensions by intent or known extension ID.

Use when: fetching, classifying, and resolving a GitHub issue — covering intake triage, duplicate search, code location, fix proposal, and PR readiness assessment.

Use when: reviewing .prompt.md files for contradictions, ambiguity, persona consistency, cognitive load, coverage gaps, and composition conflicts before merge or troubleshooting.

Use when: conducting a security-focused review of source code, API surfaces, authentication flows, or trust boundaries — covering injection, secret exposure, access control, and cryptographic failures.

Use when: diagnosing unexpected Copilot Chat behavior, slow responses, missing instructions or skills, tool call failures, extension conflicts, MCP registration issues, or workspace configuration problems.

Use when: running targeted or full tests in any workspace, choosing the safest available test command, summarizing test results, or deciding when to hand failing tests to debugger.

Use when: choosing the right search strategy for a workspace query, executing and refining searches, and acting on results — covering exact text, regex, semantic, file-path, and VS Code search-panel modes.