bmaltais
- 39 skills
- 0 followers
- 7 hours ago last updated
- ▌ Plan · bmaltaisPlan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.
- ▌ Github Issues · bmaltais bundleCreate, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.
- ▌ Browser Use · bmaltais bundleAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
- ▌ Go K8S CLI · bmaltaisScaffold, build, and debug a Go CLI that talks to Kubernetes via client-go. Use when: creating a new Go CLI for Kubernetes, wiring up Cobra commands, applying/deleting Kubernetes resources from Go, waiting for pod readiness, streaming logs, or running kubectl-exec from Go code. Trigger on phrases like 'build a go cli for k8s', 'scaffold a kubernetes go tool', 'create/update/delete k8s resources from go', 'stream pod logs in go', 'wait for pod ready in go', 'kubectl exec from go'.
- ▌ Inspection · bmaltaisFormal technical inspection of a change — perspective reviewers find defects, tests confirm them, a record tracks rework.
- ▌ Powershell · bmaltais bundlePowerShell cmdlet and scripting best practices based on Microsoft guidelines. Use when writing or reviewing PowerShell scripts (.ps1, .psm1). Trigger on phrases like "write a PowerShell function", "review my script", "PowerShell best practices", "cmdlet design", "PS1 style".
- ▌ Skillforge · bmaltaisCreates new pi skills — scaffolds SKILL.md with frontmatter, registers in _index.md, and logs the decision.
- ▌ Feynman Why · bmaltaisExplain why without cheating — name the floor the answer stands on, then go one rung past it. Use when the user asks why or how something works, asks for an ELI5, or when an explanation is reaching for a metaphor.
- ▌ Pr Reviewer · bmaltais bundleExpert automated code reviewer (Copilot Reviewer persona). Given a GitHub PR URL or raw diff, fetches the changes and produces the exact structured review (Summary + 🔴 Critical + 🟡 Suggestions + etc.). Posts the feedback directly as top-level comments on the real GitHub PR by default (using the built-in helpers in scripts/ (post_review.py + github.sh) and gh auth token). Use --no-post for review-only mode. Never uses Approve/Request Changes. Triggered by /pr-reviewer <url>, 'review this PR', etc. (posts by default).
- ▌ Skill Doctor · bmaltaisSplit a large SKILL.md into a slim main file plus focused reference files, without losing any content. Use when a SKILL.md exceeds ~400 lines or has grown unwieldy. Trigger on phrases like "split this skill", "refactor this skill", "skill is too long", "reduce skill size", "extract reference files from skill", or "skill doctor".
- ▌
- ▌ AI Brain Wiki · bmaltaisMaintain and operate the AI-Brain wiki — run lint, search, ingest, and fix common issues. Covers path facts, tool commands, and known pitfalls discovered during use.
- ▌ Improve Skill · bmaltais bundleUse when a session showed friction — user corrections, tool failures, repeated attempts, skipped steps — and you want to patch the skill(s) responsible so it doesn't recur.
- ▌ Itsg 33 Assess · bmaltais bundleAssess a local repo against ITSG-33 PBMM controls, producing evidence cards, a compliance report, and gap issues for failing controls. Use when the user wants an ITSG-33 or PBMM compliance assessment, or asks for a Security Assessment Report (SAR) package for this repo.
- ▌ Tool Optimizer · bmaltais bundleAnalyzes the current session to detect repeated tool call patterns and proposes fast native CLI tools that combine multiple steps into one.
- ▌ Skill Contracts · bmaltais bundleReference for authoring a skill — the contract it owes, plus the bundled writing-great-skills reference.
- ▌ Containerization · bmaltais bundleComprehensive best practices for creating optimized, secure, and efficient Docker images and managing containers. Covers multi-stage builds, image layer optimization, security scanning, and runtime best practices. Use when reviewing or writing Dockerfiles, docker-compose files, or container deployment configs. Trigger on phrases like "review my Dockerfile", "optimize this image", "Docker best practices", "container security", "multi-stage build", "reduce image size", "docker-compose review".
- ▌ Address And Merge · bmaltais bundleAddress the review feedback on an open PR, then squash-merge it and delete the branch. Use when the user says "address the feedback on PR N", "fix the review comments", "merge PR N", or "address and merge".
- ▌ Itsg 33 Remediate · bmaltais bundleWork open ITSG-33 gap issues one at a time under a TDD discipline, delivering each fix as a branch and draft PR. Use when the user wants to remediate PBMM control gaps (itsg-33:gap issues) produced by itsg-33-assess.
- ▌ Github Pr Workflow · bmaltais bundleUse when the user wants to create a branch, open or update a pull request, check or poll CI status, auto-fix a failing CI run, or merge a PR. Full lifecycle via gh CLI, with a git + GitHub REST API (curl) fallback for machines without gh.
- ▌ Writing Great Tests · bmaltaisUse when writing, reviewing, or repairing tests — adding coverage to an untested file, writing a reproducing test for a bug, or fixing tests that are flaky, brittle, or slow.
- ▌ Github Pr Force Merge · bmaltais bundleForce-merge a GitHub pull request blocked by branch protection or a repository ruleset (e.g. required code-owner review, required approving reviews), by temporarily disabling only the blocking ruleset(s), merging with admin bypass, then restoring enforcement. Use when the user says "force merge", "expedite", "bypass review", "merge anyway", or gives a GitHub PR URL/number and asks to merge it despite it being blocked. Always re-enables any ruleset it disabled — never leaves protections off.
- ▌ Terraform Module Change · bmaltais bundleEnd-to-end workflow for making a change to an existing Terraform module resource: fetch provider docs, implement the change, write a pure-logic tftest fixture (no provider credentials needed), wire test discovery via Makefile, run the full validation cycle (terraform test → fmt → tflint), and update RELEASE_NOTES.md. Use when the user asks to add, update, or fix an argument on an existing Terraform resource, add a new behaviour to an existing resource block, ensure a resource re-syncs on upstream changes, or "update X to use the new Y argument". Trigger on phrases like "update this resource to use", "add X to my terraform resource", "ensure sync when", "how do I make terraform detect changes in", "update my tf code for provider version X", "write tests for this tf change". DO NOT use for: scaffolding new modules (use terraform-caf-azurerm-module), full provider version upgrades across a module (use eslz-module-upgrade), or pure validation runs without code changes (use terraform-validation-workflow).
- ▌ Azure Vm Quota Ticket Automation · bmaltais bundleExtract Azure VM quota requests from free text, clarify missing details, and use the bundled azqt CLI to map, audit, submit, and report requests. Use when the user shares a document, email, or chat log containing Azure VM quota asks (SKUs, vCPU/memory sizes, subscription IDs) and wants Azure Support quota-increase tickets extracted, clarified, and filed.
- ▌ Dox · bmaltaisFollow and maintain the DOX AGENTS.md contract hierarchy in this repo. Use before editing any file — walk root-to-target AGENTS.md chain first — and after any meaningful change to code, docs, or skill structure — update the nearest owning AGENTS.md and its Child DOX Index.
- ▌ Lxd · bmaltais bundleManage LXD containers — launch, configure users, networking, storage, and snapshots.
- ▌ Herdr · bmaltais bundleControl herdr from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDR_ENV=1).
- ▌ Graphify · bmaltais bundleUse for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
- ▌ Markdown · bmaltais bundleComprehensive Markdown best practices and formatting rules, aligned with markdownguide.org, markdownlint, and CommonMark spec 0.31.2. Use when writing or reviewing Markdown files. Trigger on phrases like "format this markdown", "markdown best practices", "fix my markdown", "lint markdown", "markdown style".
- ▌ Simplify · bmaltais bundleAutomated code review and simplification workflow that reviews git changes through three parallel analyses (code reuse, quality, efficiency) and applies high-confidence fixes. Use whenever users want to clean up code, simplify code, review changes before committing, check for duplicate logic, find N+1 patterns, improve code efficiency, refactor messy code, or reduce technical debt. Trigger on phrases like "simplify my code", "review my changes", "check for duplicates", "optimize this code", "clean up before commit", "any code smells?", "make this more efficient", or "reduce complexity". Always use this skill when the user mentions code review, refactoring, or wants to improve code quality.
- ▌ Artyfacts · bmaltais bundleManage your Artyfacts workspace — list, create, update, and search artifacts and sections via artyfacts-pp-cli. Invoke with /artyfacts <what you want to do>.
- ▌ Coder K3s · bmaltais bundleDeploy, configure, manage, and troubleshoot Coder self-hosted dev environments on a k3s Kubernetes cluster. Use when: installing Coder on k3s, creating or updating workspace templates, debugging 502 Bad Gateway errors, fixing code-server connectivity, managing Coder CLI authentication, pushing Terraform workspace templates, configuring PostgreSQL backend, debugging workspace pod failures, setting up per-user namespaces, or integrating Coder workspaces with LiteLLM / GPU nodes.
- ▌ Git Proxy · bmaltais bundleSafe git operations — commits, pushes, branches, merges, and rebases with safety constraints enforced.
- ▌ Implement · bmaltais bundleImplement a piece of work from a spec, tickets, or an agent brief — the middle step of triage → implement → review.
- ▌ To Issues · bmaltaisBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
- ▌ Wargaming · bmaltaisWargame a mission on paper into a move-by-move plan a cheaper executor model can follow end-to-end with zero questions. Use when the user says "wargame this/the mission", wants a plan battle-tested against failure before another model or session executes it, or asks for forks/abort conditions/a verification checklist to be worked out in advance.
- ▌ Audit Docs · bmaltaisAudit a codebase's documentation (README, SKILL.md, AGENTS.md, etc.) for gaps against the actual implementation. Finds undocumented commands, flags, config fields, and behaviors. Use when a feature has landed but docs weren't updated, after a session where docs drift was discovered, or as a pre-release check.
- ▌ Code Craft · bmaltais bundleConstruction discipline for code a human will maintain — deep modules, one home per fact, red-first tests, gates run before "done". Use when writing a new module, class, or non-trivial function, when refactoring, when the user asks for production-grade / clean / maintainable code, or when another skill needs the bar for what counts as finished code.
- ▌ Fable Mode · bmaltais bundleGates every non-trivial task through a five-stage working discipline extracted from Fable, and routes sub-agent work to the cheapest model that can pass verification. Use when the user says "fable mode", when a problem is hard or ambiguous, or when orchestrating sub-agents.