dougcunha
UserNon-intrusive Windows 11 desktop HUD monitoring LLM usage and agent activity across AI coding tools.
Categories
Indexed Skills (23)
architectural-analysis
Read-only architectural audit of a .NET/C# codebase — dead code, duplication, anti-patterns, nullability and type safety, code smells — written to a report, never edited. Use when a whole solution or a large module needs an architecture-level health check; it detects the stack first and offers a derived strategy when that stack is not .NET/C#. Don't use for style/formatting, performance profiling, security audits, or feature-level code review.
commit
Create commits using conventional commits (title + bullet description), handling submodules with pending changes first and then the main repository. Use when the user asks to commit, save changes in git, generate a commit message, or use /commit. Push to the remote only when the `push`/`--push` argument is supplied.
deep-review
Deep review of branch diffs, working trees, or GitHub PRs at any size. Use when the user asks for CodeRabbit-grade review, an incremental re-review after new pushes, publication of findings to a PR, a cross-LLM peer-review verdict round, or conformance review against spec artifacts. Don't use for applying fixes, reviewing specs or PRDs as documents, or quick single-file feedback.
dotnet-efficient-validation
Efficient .NET validation with low noise and no redundant work. Mandatory when running dotnet build, publish, or run, or discovering, listing, or running tests with VSTest or Microsoft.Testing.Platform (MTP). Do not use to migrate test frameworks.
no-workarounds
No workarounds. Use when debugging code or test failures, planning a fix, or reviewing changes that may hide a defect, including .NET/C# nullability, async, dependency injection, and EF Core issues. Not for formatting- or docs-only edits.
repository-cli-efficiency
Perform repository searches, grep, diff, and inspections with controlled scope and low verbosity. Mandatory when using rg, Select-String, git grep, git diff, gh api, recursive searches, or reviewing many files.
sdd-create-techspec
SDD TechSpec when a PRD exists and the solution must be specified; does not create requirements or a task plan.
sdd-execute-corrections
SDD execution when tasks from a review need correction; does not create or reclassify findings.
sdd-execute-task
Execution of one exact SDD task, standalone or delegated; does not plan or approve its own work.
sdd-orchestrate-prds
Slice SDD when a broad request must become several cohesive PRDs under a shared prefix; for a single PRD, use sdd-create-prd.
sdd-orchestrate-tasks
SDD DAG when PRD, TechSpec, and tasks are already approved and must be executed; for the cycle from PRD, use sdd-orchestrate-flow.
sdd-plan-audit
SDD audit when an architectural-analysis report must become workstreams with TechSpec and tasks; does not audit or implement.
sdd-plan-corrections
SDD corrections when a code review must become traceable tasks; does not implement or alter the report.
sdd-plan-refactoring
SDD refactoring when a structural change must preserve behavior; does not implement or add functionality.
sdd-plan-tasks
SDD tasks when a PRD and TechSpec must be decomposed into an executable DAG; does not implement the feature.
sdd-review-code
SDD review when implementation must be audited against PRD, TechSpec, and tasks; does not correct findings.
update-nuget-packages
tight NuGet: updates .NET dependencies with dotnet outdated, validates restore/build/tests, synchronizes submodules, and chooses between fixing an authorized incompatibility or rolling back. Use when a .NET solution needs package updates or tests break after a package update. Don't use to migrate a test project to MTP without package updates (use update-mtp-tests), for code changes unrelated to dependencies, or for rollback without explicit confirmation.
writing-agents-md
Author lean AGENTS.md/CLAUDE.md instruction files — resident system-prompt context where every line pays rent. Use when writing an agent instruction file from scratch, auditing or trimming a bloated one, or gating whether a new rule earns residence and at which scope. Don't use for on-demand skills (use writing-skills) or human-facing docs and READMEs.
sdd-create-prd
SDD PRD when asked to create or update product requirements; does not define architecture or tasks.
ai-ready-fix
AI Ready Fix corrects findings from AI-READY-SCORE.md and reassesses repository readiness for AI agents. Use to apply the audit or raise the score to 5. Do not use only to score (ai-ready-score) or to edit unrelated instructions.
ai-ready-score
AI Ready assesses repository readiness for AI agents with a score from 0 to 5 and verifiable findings. Use to audit instructions and skill loading or reassess ai-ready-fix corrections. Do not use to correct files or for code, security, or performance review.
domain-modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
sdd-orchestrate-flow
SDD flow for conducting a feature with subagents and HIL or resuming its checkpoint in a new session; does not replace a standalone stage.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.