meridian
Adds persistent project context, session handoff, and workflow enforcement to Claude Code, with skills for planning, error auditing, observability audits, and generating documentation for context routing.
6 skills187
@markmdevPlugins
1@markmdevSkills
6add-frontmatter
Scan all .md files in the project and add or fix YAML frontmatter (summary + read_when) so they can be discovered by context…
@markmdevcreate-docs
Create or update .meridian/docs/ knowledge files for a module or directory. Produces reference docs with frontmatter for context…
@markmdeverror-audit
Audit code for silent error swallowing, fallbacks to degraded alternatives, backwards compatibility shims, and UI that fails to…
@markmdevobservability-audit
Audit code for observability gaps — debug logs left in, errors caught without being logged, missing context on log entries,…
@markmdevplanning
Interview-driven planning methodology that produces implementation-ready plans. Always use this skill INSTEAD of EnterPlanMode —…
@markmdevux-states-audit
Audit UI code for missing loading states, empty states, and error states. Every async operation and data-driven UI must handle…
@markmdevAgents
8architect
AgentReviews architecture — either existing code or proposed plans. Use during planning to validate approach, or after changes to…
@markmdevcode-health-reviewer
AgentFinds dead code, pattern drift, over-engineering, and refactoring opportunities. Use after completing large tasks, at the end of…
@markmdevcode-reviewer
AgentDeep code review that finds real bugs — logic errors, data flow issues, pattern inconsistencies. Returns structured findings to…
@markmdevdocs-researcher
AgentUse BEFORE writing code that uses an external API, library, or tool not already documented in `.meridian/api-docs/`. Researches…
@markmdevexplore
AgentUse for broad codebase research when you don't know where to look, need to understand "how does X work?", or want comprehensive…
@markmdevimplement
AgentUse when you have a detailed, unambiguous implementation spec (e.g., "add export for function X in file Y"). Executes the spec,…
@markmdevpebble-scaffolder
AgentDocuments planned work in Pebble before implementation. Creates appropriate structure (epic, task, or bug fix) based on scope.
@markmdevplan-reviewer
AgentValidate a plan before implementation. Use before exiting Plan mode. Pass the plan file path and any additional context files.…
@markmdevCommands
3coderabbit-review
CommandHandle CodeRabbit AI review cycles after creating a PR
@markmdevwork-until
CommandStart a work-until loop that keeps you working on a task until completion
@markmdevIs this you? Claim your profilePut a plugin at the top of Plugins, from $9