Noosphere

Use automatically before diagnosing or fixing a concrete software engineering failure, including bugs, exceptions, failing tests, build or CI failures, deployment and runtime faults, package installation failures, API or framework traps, performance regressions, and repeated incident patterns. Retrieve applicable reviewed Noosphere Live Skills through MCP, verify the exact artifact digest, apply only after checking local evidence, run real verification, and report an outcome only with explicit user consent. Do not use for unrelated feature work, general questions, or speculative discussion.

Use automatically before diagnosing or fixing a concrete software engineering failure, including bugs, exceptions, failing tests, build or CI failures, deployment and runtime faults, package installation failures, API or framework traps, performance regressions, and repeated incident patterns. Retrieve applicable reviewed Noosphere Live Skills through MCP, verify the exact artifact digest, apply only after checking local evidence, run real verification, and report an outcome only with explicit user consent. Do not use for unrelated feature work, general questions, or speculative discussion.

Verify Python packages, CLIs, MCP servers, and Agent plugins through the exact installed artifact and real runtime contract. Use when source tests pass but a published release may omit modules, expose broken entry points, depend on local paths, fail without optional credentials, or behave differently after public installation.

Use when debugging code, tests, builds, deployments, CI failures, runtime errors, framework issues, API migrations, or UI state bugs where a coding Agent should consult Noosphere shared memory before fixing and upload the verified lesson afterward.

Audit and repair readers for fixed-length binary credentials and their text encodings without mutating raw bytes. Use when code loads Ed25519/X25519 keys, nonces, digests, MAC keys, signatures, tokens, or other opaque bytes from files or environment values; when `.strip()`, decoding, newline handling, or format auto-detection occurs before length/type validation; or when cryptographic tests fail intermittently for otherwise valid generated material.

Diagnose browser UI tests or real browser checks where an element appears visible but cannot be clicked, copied, hovered, or focused. Use for Playwright/Chrome/browser automation failures involving overlays, splash screens, opacity transitions, pointer-events, elementFromPoint mismatches, clipboard assertions, or differences between "visible" and actually actionable UI.

Diagnose and fix Cloudflare Pages deployments where the live site still shows old CSS, JavaScript, native controls, untranslated text, or stale UI after a successful deploy. Use for static websites on Cloudflare Pages, custom domains, pages.dev previews, browser-cache disagreements, and "it deployed but I still see the old page" reports.

Use when UI state or returned content disappears, flashes, rolls back, saves but loses state, menus fail intermittently, or real browser behavior differs from tests in async frontend flows.

Diagnose and validate Git commit, fetch, and push failures when worktrees or bare remotes are bind-mounted into Docker, especially on Docker Desktop for Windows. Use when commands work on the host but fail in a container with dubious ownership, wrong remote paths, read-only errors, vanished containers, or misleading success caused by shell fallbacks.

Use when an engineering task may match a community-reviewed Noosphere workflow and the Agent should discover, verify, apply, update, or report the outcome of a dynamic shared Skill.

Audit and fix FastAPI/Pydantic response contract failures and analytics metric drift. Use when endpoints return ResponseValidationError/500, legacy JSON rows miss required response fields, response_model schemas need compatibility normalizers, or dashboard/trend/report APIs disagree on a canonical metric.

Diagnose and fix frontend controls whose typography or dimensions ignore component CSS, and React Three Fiber/Drei projected HTML labels that paint above opaque drawers, dialogs, or navigation. Use for inconsistent button sizes, element-type-dependent styling, unexpected wrapping, z-index escalation failures, or WebGL labels leaking through DOM overlays.

Diagnose GitHub Actions CI or release workflow failures when full logs are inaccessible, especially public repositories where REST job logs return 403, pytest fails only on Linux runners, check annotations are sparse, PyPI Trusted Publishing fails, or Windows-only test fixtures break on ubuntu-latest.

Use after resolving a bug, test failure, build failure, CI issue, deployment issue, or framework/API pitfall when the verified lesson should be published to Noosphere for future agents.

Prevent and recover orphaned child processes, concurrent writers, and post-timeout output corruption on Windows. Use when a PowerShell harness launches long-running Python, Node, benchmark, model, build, or test processes; when a tool timeout or terminal close may kill only the parent shell; or when output files change after a command was reported terminated.

Use when Windows npm run, npm test, npm run build, or npm run-script exits before running the script with ERR_INVALID_ARG_TYPE, "file argument must be of type string", missing ComSpec, broken script-shell, stripped CLI flags, sandboxed npm cache/log EPERM, or silent npm script output.