Agent skill

method:router

Routes `/method:router` requests to the best-fit method skill among the 7 methods. Not a method itself. Use for `/method:router` or `/method:router <args>` when choosing which method to start.

Stars 20
Forks 6

Install this agent skill to your Project

npx add-skill https://github.com/petekp/claude-code-setup/tree/main/skills/method-router

SKILL.md

Method Router

Routing only. This skill is not a method.

Workflow

  1. Treat /method:router <text> as the strongest signal.
  2. If args are empty, read the current thread and any referenced handoff, spec, PRD, bug report, or method directory.
  3. If still ambiguous, ask exactly one disambiguating question.

Route only when positive signals match and exclusions do not.

  • method:research-to-implementation Match: multi-file or cross-domain feature delivery, unclear approach, or research needed before build. Exclude: bug fixes, config changes, or already-clear tasks.
  • method:decision-pressure-loop Match: architecture or protocol choices with real downside, serious options, or reopen conditions needed before build. Exclude: code delivery, bug fixes, or settled decisions.
  • method:spec-hardening Match: an existing RFC, spec, PRD, or method schema that is promising but not yet safe to build from. Exclude: unformed ideas, bug fixes, or specs already implementation-ready.
  • method:flow-audit-and-repair Match: a broken, flaky, or unsafe existing flow, especially across boundaries, where repair must start from forensics and end in a verified fix. Exclude: feature ideation, greenfield implementation, or cases with no real broken flow to reproduce.
  • method:create Match: authoring a new method from a natural-language workflow and fitting it to the live method corpus. Exclude: editing an existing method, building a runtime engine, or wrapping a tiny one-off prompt in method structure.
  • method:autonomous-ratchet Match: overnight autonomous quality improvement, polish, ratcheting, or unattended codebase refinement with an evidence-backed closeout. Exclude: interactive work, greenfield features, architecture decisions, cleanup-only scope, or repos without build/test commands.
  • method:dry-run Match: dry-running, validating, tracing, or mechanically checking a method skill, especially after authoring or editing it. Exclude: architecture critique, feature design, or product judgment.

Route Order

Use a sequence only when an earlier phase must happen before a later one.

  • Broken existing flow: method:flow-audit-and-repair before any rebuild or expansion work.
  • Unsettled architecture or protocol choice: method:decision-pressure-loop before method:spec-hardening or method:research-to-implementation.
  • Draft exists but is not build-ready: method:spec-hardening before method:research-to-implementation.
  • New method authoring: method:create before method:dry-run.
  • If both method:decision-pressure-loop and method:spec-hardening match, start with method:decision-pressure-loop.
  • If none match, say so and do not force a route. This includes single-file changes, config edits, quick wiring, or trivial bug fixes.

Recommend

Recommend the best method or sequence in order. For each recommended step, give 1-2 sentences tied to the matched signals and exclusion checks. Briefly say why the closest alternatives do not fit. If nothing fits, say that directly and stop.

Invoke On Confirmation

If the user confirms, invoke only the first recommended method. Recompute once if new information changes the route.

Expand your agent's capabilities with these related and highly-rated skills.

petekp/claude-code-setup

ubiquitous-language

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

20 6
Explore
petekp/claude-code-setup

every-style-editor

This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.

20 6
Explore
petekp/claude-code-setup

manage-codex

Autonomous Codex batch orchestrator. Use for "/manage-codex", "manage codex", "use codex", "dispatch to codex", or long-running Codex work.

20 6
Explore
petekp/claude-code-setup

seo-audit

When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. For AI search optimization, see ai-seo.

20 6
Explore
petekp/claude-code-setup

capture-learning

Analyze recent conversation context and capture learnings to project knowledge files (for project-specific insights) or skills/commands/subagents (for cross-project patterns). Use when the user asks to "capture this learning", "update the docs with this", "remember this for next time", "document this issue", "add this to CLAUDE.md", "save this knowledge", or "update project knowledge". Also triggers after resolving build/setup issues, discovering non-obvious patterns, or completing debugging sessions with valuable insights.

20 6
Explore
petekp/claude-code-setup

agent-changelog

Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project evolution", or proactively after major milestones, architectural changes, or when stale/deprecated information is detected that could confuse coding agents.

20 6
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results