srnnkls
21 verified skills
review
Unified review dispatcher. Auto-detects review type from argument or presents selection menu. Routes to code review, PR review, or scope review.
development
scope
Unified scope lifecycle. Auto-detects operation from argument or presents selection menu. Routes to create, review, update, done, or list.
tools
git
Modern git workflows plus dispatched operations (rebase strategy analysis). Use when managing branches, structuring commits, choosing development strategies, or planning a rebase.
development
peer
External code-review harness (`peer` zsh tool): canonical model registry, idle-stall watchdog, and self-parallelising fan-out to codex/gemini. Use when dispatching external (non-Claude) reviewers from the review or implement pipelines — call `peer run`/`peer <harness>` instead of `codex exec`/`gcloud`+Vertex directly.
tools
implement
Scope execution pipeline and implementation methodology. Use for executing scopes (TDD three-phase pipeline), verifying completion, debugging, or building features from requirements.
development
continue
Resume interrupted work from context. Use when continuing after session break, context limit, or interruption.
tools
code
Code domain. Composes with implement, review, and test skills for code-specific operations.
development
doc
General reference documents by domain. Use when creating architecture docs, strategy documents, specs, or guides.
documentation
dispatch
Intent router. Auto-detects execution mode from context and routes to the appropriate skill.
tools
gestalt
Query code intelligence with gestalt. Use when finding callers/callees, tracing references, running CozoScript queries, or generating repo maps.
development
issue
GitHub issue operations. Use when creating PRs from issues, viewing issue details, or linking issues to branches.
data-ai
loop
Autonomous implementation loop over a focus topic. Reads active scopes, enumerates tasks as todos, then iterates the TDD pipeline (tester→implementer→reviewer) until all tasks are complete. Use when autonomously implementing all pending work for a scope or topic without manual step-by-step oversight.
testing
loqui
Access language-specific coding guidelines from loqui. Use when implementing code and needing patterns, style guidance, or best practices for Python, Go, Rust, or Bash.
development
skill
Create new Claude Code skills following project patterns and best practices. Use when building new skills, extracting reusable capabilities, or converting commands to skills.
development
dotfiles
Manage dotfiles using dotter (symlink manager and templater). Use when deploying, adding, removing, or organizing configuration files in ~/dotfiles.
devops
debate
Start structured red vs. blue team debates via subagents. Use when exploring a topic from multiple adversarial perspectives.
data-ai
validate
Unified validation dispatcher. Auto-detects validation type from argument or presents selection menu. Routes to test, implement (verify), or hooks-test.
testing
adversarial
Push into adversarial focus mode — surface orthogonal observations, run three rounds of named adversarial analysis (pre-mortem, devil's advocate, falsification), drop narration. Use when work is experimental, when a solution "looks correct," or when pattern-matching might be masking the real problem.
development
bash
Ultra-concise bash command patterns. Use when constructing shell commands or one-liners.
testing
test
Test-driven development methodology (RED-GREEN-REFACTOR). Use when implementing features, fixing bugs, or changing behavior - write failing test first, then minimal code to pass.
development
clarify
Resolve ambiguities interactively with tracked changes. Works with scope, code review, and other skills.
development