KingInYellows/yellow-plugins

create-agent-skills

Expert guidance for creating Claude Code skills and agents. Use when working with SKILL.md files, authoring new skills, creating slash commands, or designing agent workflows.

audit-review

Run 1-3 parallel quick-audit passes (code quality, security, error handling) over a diff and gate on findings. Use when smart-submit or gt-amend need to audit uncommitted changes before committing.

gt-stack-plan

Decompose a feature into stacked PRs, ordered by dependency (plan-only). Use when breaking a feature into reviewable stacked PRs.

audit-review

Run 1-3 parallel quick-audit passes (code quality, security, error handling) over a diff and gate on findings. Use when smart-submit or gt-amend need to audit uncommitted changes before committing.

gt-stack-plan

Decompose a feature into stacked PRs, ordered by dependency (plan-only). Use when breaking a feature into reviewable stacked PRs.

ci-diagnose

Diagnose a CI failure now — fetch the failed run, redact and match its logs against the F01-F12 pattern library, and report root cause with fixes. Use when a GitHub Actions run has failed and you want its root cause and a fix now (for the reference workflow…

ci-diagnose

Diagnose a CI failure now — fetch the failed run, redact and match its logs against the F01-F12 pattern library, and report root cause with fixes. Use when a GitHub Actions run has failed and you want its root cause and a fix now (for the reference workflow…

compound-lifecycle

Audit, refresh, and consolidate `docs/solutions/` to keep the institutional knowledge catalog from rotting. Use when a `docs/solutions/` sweep is needed or after `knowledge-compounder` flags an older entry as superseded.

debugging

Find root causes systematically before fixing — trace the causal chain and form hypotheses with predictions for uncertain links. Use when debugging errors, test failures, stack traces, or when stuck after failed fix attempts. For delegating a stuck…

ideation

Generate 3 grounded approaches to a soft problem, then hand the chosen one off to `brainstorm-orchestrator`. Use when the problem statement is still vague or `/flow:brainstorm` narrows too quickly.

optimize

Run a metric-driven optimization pass: parallel candidate variants scored against an LLM-as-judge analytic rubric. Use when comparing approaches against a measurable goal — anywhere 'better' can be expressed as a per-criterion rubric. For session-level…

session-history

Search prior sessions across Claude Code, Devin, and Codex for the same problem or topic. Use when the current session cannot see prior context — after agent compaction, session boundary, or when reconstructing a multi-session decision trail. This searches…

council-patterns

Canonical reference for yellow-council reviewer contracts, CLI invocation, redaction, and output-parsing conventions. Use when authoring or modifying claude-reviewer, gemini-reviewer, opencode-reviewer, or the /council command.

debt-conventions

Technical debt scoring framework and scanner patterns. Use when scanner agents need scoring rubrics, category definitions, safety rules, or output schemas.

pr-review-workflow

Internal reference for PR review workflow patterns. Use when agents or commands need shared conventions for adaptive selection, output format, or error handling.

test-skill

Skill fixture used to validate the skill-reference resolver in lint-plugins.sh.

github-stack-amend

Fold working-tree changes into the current branch commit and re-submit via gh stack. Use when user says "amend this" or "add this to the current PR" on the github stacked-PR provider.

github-stack-cleanup

Remove local stack tracking, and by default also remote-unstack every PR via the GitHub API. Use when user says "clean up my stack" or "untrack this stack" on the github stacked-PR provider.

github-stack-merge

Merge a stacked PR via gh stack merge. Use when the user says "merge my stack" or "land this PR" on the github stacked-PR provider and the target is fully reviewed and ready.

github-stack-nav

Check out a stack target — stack number, PR number, PR URL, or branch. Use when user says "go to PR 42" or "show my stack and let me pick" on the github stacked-PR provider.

github-stack-plan

Report the current GitHub-native stack structure (read-only). Use when checking what branches/PRs are in the stack before submitting or merging.

github-stack-setup

Check GitHub-native stacked-PR prerequisites — gh CLI, authentication, and the official github/gh-stack extension. Use when first installing the plugin, after gh auth changes, or when /stack:status reports PARTIAL_TOOLING for the github provider.

github-stack-status

Report GitHub-native stacked-PR tooling readiness and point to /stack:status (yellow-core) for the authoritative active-provider answer. Use when checking why gh stack tooling is unavailable or which stacked-PR provider is currently active.

github-stack-submit

Stage, commit, and submit uncommitted changes as a GitHub-native stacked PR. Use when user says "submit this" or "ship it" on the github stacked-PR provider and has uncommitted work to turn into a PR.

github-stack-sync

Sync the local stack with trunk via gh stack sync, optionally pruning merged branches. Use when user says "sync with main" or "pull latest" on the github stacked-PR provider.

gt-amend

Fold working-tree changes into the current branch commit, audit them, and re-submit via Graphite. Use when user says "amend this", "add this to the current PR", "fold this fix in", or has follow-up edits for an already-submitted branch. Not for starting new…

gt-cleanup

Scan local branches for staleness and divergence, then delete or reconcile them with safeguards. Use when user says "clean up my branches" or "which branches are stale". For deleting branches whose PRs merged — and for pulling trunk or restacking — use the…

gt-merge

Merge the current stack's pull requests, from trunk up to the current branch, via Graphite. Use when the user says "merge my stack" or "land these PRs" and the stack is fully reviewed and ready.

gt-nav

Visualize your Graphite stack and navigate between its branches. Use when user says "show my stack", "where am I in the stack", "go up/down a branch", or "checkout the top of the stack". Not for restacking, syncing, or cleanup — use the gt-sync or gt-cleanup…

gt-setup

Validate Graphite CLI prerequisites and configure settings for AI agent workflows. Use when first installing the plugin, after Graphite auth changes, or when gt commands fail.

gt-sync

Pull latest trunk, restack all tracked branches, and untrack branches whose PRs merged. Use when user says "sync with main", "rebase my stack", or "pull latest", after PRs merge, or when gt reports "needs restack". Not for deleting stale local-only branches —…

smart-submit

Stage, audit, commit, and submit uncommitted changes via Graphite, with parallel code-review agents. Use when user says "submit this", "ship it", or "commit and push", or has uncommitted work to turn into a PR. Requires uncommitted changes — a clean,…

stack-decomposition-format

Structured format contract for "## Stack Decomposition" sections in plan documents, shared by gt-stack-plan (producer) and flow:work (consumer). Use when writing or parsing a Stack Decomposition section.

stack-plan-style

Display guidance for presenting a stacked-PR plan — ordered branch tree with intent, commit type, and dependency notes. Use when gt-stack-plan presents a stack plan for user confirmation.

agent-browser-patterns

agent-browser usage patterns and conventions reference. Use when agents or commands need agent-browser context, ref-based workflow, session persistence, semantic locator fallbacks, or error handling patterns.

test-conventions

Testing conventions and configuration reference. Use when agents or commands need config schema, severity classification, report templates, or credential rules for browser testing.

ci-conventions

Shared CI conventions reference (not an executable action) — validation rules, failure patterns (F01-F12), error catalog, and security patterns. Consult when agents or commands need CI-specific validation or pattern-matching reference.

ci-lint-workflows

Lint GitHub Actions workflows for self-hosted runner issues (W01-W14). Use when checking workflows before pushing or finding common CI pitfalls; previews and confirms before applying any fix.

ci-runner-health

Check self-hosted runner health via SSH, with deep runner diagnostics folded in. Use when the user asks for runner status, whether a runner is healthy, or wants to verify infrastructure before diagnosing CI failures.

ci-setup-runner-targets

Configure runner pool targets, routing rules, and semantic metadata for CI workflow optimization (wizard, YAML import, or GitHub API discovery). Use when setting up runner-aware CI optimization or after changing your runner fleet.