fyrsmithlabs

Multi-agent consensus code review with adaptive budgets, complexity-aware agent selection, multiple consensus protocols (Approval/Veto, AAD, CI, Supermajority), cross-agent coverage tracking, context-folding isolation, and progressive summarization. Use when reviewing PRs, directories, or code changes.

Use when creating new repositories, reviewing existing repos for compliance, or enforcing repository naming, structure, documentation, and security standards. Applies to all fyrsmithlabs projects.

Use when releasing a new version of a fyrsmithlabs plugin. Automates version bumping across all manifests (plugin.json, marketplace.json, CLAUDE.md), validates counts match disk, runs plugin-validator, creates git tag and GitHub release. Say "release the plugin", "bump version", "create a release".

This skill should be used when the user asks to "test opa", "opa test", "test rego", "write rego tests", "policy coverage", "conftest verify", "mock opa", or mentions `_test.rego` files. Provides OPA testing framework guidance including unit tests, mocking, coverage, and Conftest patterns.

This skill should be used when the user asks about "opa cli", "opa eval", "opa build", "opa check", "opa fmt", "regal lint", "opa bundle", "opa bench", "opa run", or mentions OPA tooling, CI/CD pipeline integration for OPA, or Rego linting. Provides OPA CLI and ecosystem tooling reference.

This skill should be used when the user asks about "kubernetes policy", "gatekeeper", "constraint template", "terraform policy", "conftest", "terraform compliance", "docker policy", "dockerfile policy", "envoy authz", "envoy authorization", "service mesh policy", "cloud policy", "aws policy rego", "azure policy rego", "gcp policy rego", or mentions writing OPA policies for a specific platform. Provides platform-specific Rego patterns and input schemas.

This skill should be used when the user asks to "write rego", "rego syntax", "rego policy", "rego rule", "opa policy", mentions `.rego` files, asks about Rego built-in functions, comprehensions, or partial rules. Provides Rego v1 language reference and idiomatic patterns.

This skill should be used when the user asks to "migrate rego", "rego v1", "v0 to v1", "upgrade rego", "opa fmt --rego-v1", "rego breaking changes", "rego compatibility", mentions Rego version migration, or encounters v0 syntax errors in OPA 1.0+. Provides Rego v0 to v1 migration patterns and tooling.

This skill should be used to preserve or restore session state. It triggers when the user says "save my progress", "checkpoint this", "pick up where we left off", or "resume", before /clear, before a long-running task, or when context usage approaches ~70%. Covers checkpoint_save, checkpoint_list, and checkpoint_resume.

This skill should be used when starting a task to check for prior solutions, or when finishing one to record a learning. It triggers when the user says "have we solved this before", "remember this", "record what we learned", reuses a past approach, or captures a design decision worth surviving the session. Covers memory_search, memory_record, memory_feedback, and memory_outcome.

This skill should be used whenever an error, exception, failed build, failing test, stack trace, compiler/linter error, CI failure, or panic appears, or when the user asks "why is this failing" or "how do I fix this". Covers troubleshoot_diagnose, remediation_search, remediation_record, and remediation_feedback to match errors to past fixes and record new ones.

This skill should be used at the start of a coding or research session, or when the user says "what did we do before", "remember", "resume", mentions persistent or cross-session memory, or begins a non-trivial task that could reuse prior learnings. It establishes the contextd workflow — run semantic_search and memory_search before exploring code — and points to the cross-session-memory, checkpoint-workflow, and error-remediation skills.