olafkfreund

Read, write, search and reorganise notes in the local Obsidian vaults. Use for anything touching ~/Documents/R3_vault, ~/Documents/Synechron or ~/Documents/My_Obsidian_Vault/Privat — finding notes, adding or editing content, renaming/moving notes without breaking links, and daily notes. Triggers on "my notes", "my vault", "Obsidian", "write this up in my notes", or a request to look something up in personal documentation.

Manage DNS records for the user's GoDaddy-registered domains. Add/upsert, delete, list, look up specific records, verify a stored record matches an expected value, and check public DNS resolution via dig. Triggers on `/dns`, requests to add/change/check A, AAAA, CNAME, MX, TXT, NS, SRV records on the user's domains, debugging DNS propagation, or auditing what's set at GoDaddy vs what's resolving in the wild.

Operate Google Workspace from the terminal via the `gog` CLI (gogcli). Use for checking and replying to Gmail, managing Google Tasks, reading and creating Calendar events, Google Chat (spaces/DMs/messages), Meet spaces, Contacts, Drive/Docs/Sheets, and more. Triggers on `/gog`, `/gog mail`, `/gog tasks`, `/gog events`, `/gog chat`, `/gog meet`, or any request to check/read/reply/send email, list or add tasks, see today's agenda, or message someone on Chat for the user's Google account.

Agenix Skill

cargo2nix Skill

COSMIC Desktop Environment Skill

DankMaterialShell (DMS) Skill

Devenv Skill

Teach an AI coding assistant how to work in the TFactory codebase — the autonomous test-generation + execution platform. Covers the 4-agent pipeline, the LLM-provider abstraction (never call anthropic directly), the workspace layout, branching model, how to run the suite, and the non-negotiable conventions (i18n, no-automatic-pushes, dry-run side-effects).

Close the AIFactory ↔ TFactory loop hands-off. After TFactory tests a feature and finds problems, this drives one bounded cycle — hand the correction back to AIFactory, wait for its QA Fixer, re-test in TFactory — and stops when the run passes, the same tests keep failing (no progress), or a correction-cycle cap is hit (→ stuck for a human). One cycle per invocation; drive it with /loop for a fully autonomous test → fix → re-test loop. Epic

When TFactory's tests find problems in a feature, hand a correction back to AIFactory for revision. Reads the correction request TFactory's Triager already prepared (findings/handback_request.{md,json}), previews the target AIFactory spec, and on confirmation sends it so AIFactory's QA Fixer writes the fix on the original spec. The reverse direction of /handover-to-tfactory — together they close the AIFactory ↔ TFactory loop (epic

Hand a finished feature off to TFactory for autonomous polyglot test generation — from AIFactory, Claude Code, or any tool (via the MCP control plane, or a markdown/Gherkin/EARS acceptance-criteria file ingested with spec_sources.py). Records the task, snapshots the spec, and drives the full Planner → Gen-Functional → Executor → Evaluator → Triager pipeline across the v0.2 5-lane spine (unit / browser / api / integration / mutation) to produce a triage report + (optionally) commit tests to the feature branch + post a PR comment. Pair with /tfactory-watch under /loop to poll the task home and verify coverage — the full round-trip.

From an AIFactory project, receive a correction hand-back from TFactory (sister project). When TFactory's tests found problems, this previews the prepared correction and applies it to the original spec via AIFactory's QA Fixer (writes QA_FIX_REQUEST.md + runs the fixer). The reverse of /handover-to-tfactory.

From an AIFactory project, hand a finished spec off to TFactory (sister project) for autonomous test generation. Records the task with TFactory's MCP server; once TFactory Tasks 5-8 land, this also drives the planner→generator→executor→evaluator→triager pipeline.

Run a read-only cloud infrastructure assessment — discover an AWS/Azure/GCP account's resources, detect misconfigurations with Prowler (CIS/OCSF), build a service-topology diagram, and emit a verdict (reject/flag/accept). Follows the access → discover → diagram → assess flow and writes the report into findings/. Use for cloud security posture, misconfiguration audits, or "what's in this account".

Draft, preview, and publish a post to the TFactory GitHub Pages blog (docs/_posts/). Writes a well-structured Jekyll post in the TFactory voice, drops it into the Gruvbox-themed Pages site, previews it with the nix-Chrome screenshot harness, and (on request) commits + syncs dev→main. Use to write or refresh TFactory blog posts.

Draft, preview, and publish a post to the PFactory GitHub Pages blog (docs/_posts/). Writes a well-structured Jekyll post in the PFactory voice, drops it into the Gruvbox-themed Pages site, previews it with the nix-Chrome screenshot harness, and (on request) commits + syncs dev→main. Use to write or refresh PFactory blog posts.

Hand a plan or request to PFactory for governed planning. Ingests it (markdown / Gherkin / EARS / pdf / docx, inline or a file), runs the pipeline (enrich with live cloud + Backstage context, decompose into an epic + child issues, feasibility, the review lenses, the hard readiness gate), and returns a cited review a human can approve. Nothing reaches GitHub or AIFactory until the gates pass and a human approves.

Poll one PFactory planning session through the pipeline and report where it stands — board column, gate result, blocking findings, and the readiness checks that still fail. One check per invocation, so it can be driven with /loop. Read-only; it never approves, waives, or emits.

From an AIFactory project, hand a finished spec off to PFactory (sister project) for autonomous test generation. Records the task with PFactory's MCP server; once PFactory Tasks 5-8 land, this also drives the planner→generator→executor→evaluator→triager pipeline.

Run a read-only cloud infrastructure assessment — discover an AWS/Azure/GCP account's resources, detect misconfigurations with Prowler (CIS/OCSF), build a service-topology diagram, and emit a verdict (reject/flag/accept). Follows the access → discover → diagram → assess flow and writes the report into findings/. Use for cloud security posture, misconfiguration audits, or "what's in this account".

From an AIFactory project, receive a correction hand-back from PFactory (sister project). When PFactory's tests found problems, this previews the prepared correction and applies it to the original spec via AIFactory's QA Fixer (writes QA_FIX_REQUEST.md + runs the fixer). The reverse of /handover-to-pfactory.

Best practices and guidelines for developing applications and applets for the COSMIC Desktop Environment.

Best practices for using NixOS, Flakes, and direnv for reproducible development environments.

Guidelines, idioms, and best practices for writing high-quality Rust code.

A Phase 0 fixture skill used to verify that skill-pool's installer correctly symlinks skills into Claude Code's discovery path. Invoke when the user asks about the "skill pool test skill" or wants to confirm the installer works.

Operate Fides — the compliance, provenance & evidence-tracking system — from the `fides` CLI, the API, and CI/CD pipelines. Use when recording build provenance (trails, artifacts, attestations), gating deploys on policy/compliance, running the change gate + segregation-of-duties approvals, adopting control frameworks (SOC 2, ISO 27001, NIST 800-53, PCI-DSS, DORA, PSD2, SOX, SLSA), verifying supply-chain provenance (cosign/Sigstore signatures, SLSA in-toto, SBOM), snapshotting runtimes (docker/k8s/ecs/lambda), verifying tamper-evidence chains, the continuous control-test timeline, wiring integrations (ServiceNow — including consuming ServiceNow's MCP server and grounding Now Assist — Slack, Git providers, webhooks), managing service accounts/users, reading DORA metrics, or configuring/deploying the Fides server and its MCP server. Triggers on "fides", "compliance gate", "attestation", "provenance", "change gate", "SBOM evidence", "policy gate", "control coverage", "verify-image", "control timeline", "serviceno

Generates governed, structured cross-currency collateral valuations and multi-jurisdiction rate audits for LCH Group members using the MCP API Gateway facade.

Draft, stage, and publish a post to the freundcloud Jekyll blog (this repo, deployed to www.freundcloud.com via GitHub Pages). Triggers on "/blog", "write a blog post", "draft a post", "publish a post", "promote a draft", or any request to add/list posts for this site.

Draft, preview, and publish a Ravn devlog post to the GitHub Pages site. Use for the /blog command or whenever the user wants to write, edit, or ship a blog/devlog entry for the ravn-agents project. Covers voice, front matter, file naming, what to write about, local preview, and the publish flow.