Menu
SkillsMP has collected 15 skills from stacklok/mecatl. Open a skill to review its source and details.
Showing 15 of 15 collected skills.
Cut a tagged release of mecatl — dispatch the Create Release PR workflow, review and merge the release PR, then verify the tag and the artifacts it publishes (ko images + Helm chart to GHCR, plus a GitHub Release with signed archives and a Homebrew formula…
Configure, write, or tune the mecatl learning: settings policy, including learning.mode, sensitivity, reflection budgets, and validated/evaluated activation. NOT for running /reflect, reviewing proposals or memories, drafting skills, model routing,…
Authors or updates Mecatl's public user documentation. Use when a change affects user-docs/, the Docusaurus site content, or a user-facing behavior that needs documentation. It follows the repository's lightweight authoring contract.
Route contributors through mecatl's human-reviewed development spine: contract PR, approved baseline, autonomous TDD implementation, final code-review PR. A router, not an executor. Use for onboarding or workflow questions.
Implement an approved mecatl acceptance plan with run-local decomposition, isolated TDD workers, aggregate gates, strict AC tracing, panel review, and an Implementation PR. Split work requires a merged approved plan and recorded baseline. Combined work…
Writes tests in mecatl (hexagonal / strict DDD, two Go modules) following the invariant-first discipline. Picks the right layer, the right naming convention, and the right fake pattern (offline reference adapters — mockllm / memfs / memstore — plus the shared…
Turn Bounded or Architectural work into a concise scenario-first acceptance plan with exact interfaces and a decision-record outcome, then hand off at the selected Split or Combined checkpoint. Stops before implementation or orchestration. NOT for Spike,…
Designs and writes a mecatl model router configuration (the `models:` subtree of ~/.config/mecatl/settings.yaml) tailored to the operator's preferences. Asks about priorities (cost vs capability, open vs proprietary, provider, multimodal) then searches the…
Review completed non-trivial code across four independent axes: Spec, Standards, Test adequacy, and installed Domain specialists. Use proactively after implementation, modification, refactoring, bug fixes, feature work, or when asked to review/audit/check a…
Interpret the mecatl perf MCP server's output to diagnose latency, goroutine leaks, GC pressure, allocation churn, and memory growth in a running mecatl harness. Use when connected to the mecatl perf MCP server (the perf:// resources or the query_metric /…
Profile-driven performance optimization of mecatl using the offline benchmark + scenario harness. Use when optimizing allocations or latency, reducing allocs/op or memory, profiling a Go benchmark, pinpointing a hotspot with pprof, proving a win with…
Use when asked to greet someone with the ceremonial mecatl greeting. Loads the exact greeting format.
Use when asked for this repository's registered fact or codeword. Loads the canonical answer format.
Write Conventional-Commits messages for this repo, with the required Co-Authored-By trailer.
Write idiomatic table-driven Go tests that stay offline and follow this repo's conventions.