dev

Plugin dev from marketplace red-skills in reddb-io/red-skills. Commands read from the repo's manifest — 6 days ago.

Skills (54)

• adr-editor

  Proposal-driven reverse grill for the active `.red/adr/` collection. Ranks active ADR clusters, recommends where to start, confronts one cluster with current implementation evidence, and applies maintainer-approved dispositions through the full ADR verb set. Use to review, curate, reorganise, fix, o

• afk

  Autonomous loop that drains the `ready-for-agent` queue on the issue tracker. Registers the project with the `redskilled` daemon at a runner and a target width, arms the drain, and observes; the daemon admits each Worker, which claims an issue, works it in its own workspace, validates, lands, and cl

• ask-red

  Ask which RedSkills flow fits the current situation. Use when the operator asks what to do now, which command to run, or how to route a task through RedSkills.

• audit-skills

  Read-only skill-quality auditor. Scores every shipped SKILL.md against the RedSkills house style (mechanical checks + an LLM judge on the dev review engine), overlays best-effort telemetry, and prints a worst-first scorecard. Use when the user invokes `/audit-skills`, asks which skills are weakest,

• code-review

  Two-axis code review of the diff between HEAD and a fixed point — Standards (does the code follow this repo's documented coding standards and the Fowler smell baseline?) and Spec (does it implement what the issue/Spec asked for?). Runs both reviews as parallel sub-agents. Use when the user wants to

• context

  Build and refresh the project context stack before non-trivial work — domain glossary, ADRs, LLM Wiki, Memory graph, graph-aware zoom-out, and self-improvement signals. Use when the user asks to "get context", "manage context", onboard to a repo, prepare a large change, or improve agent memory/self-

• curate

  Interactive Skill curator. Reads `memory curate skills --json`, groups Curatable-skill candidates by category (`stale`, `abandoned`, `frequently-failing`, `archive`), asks for explicit approval, archives the approved set recoverably with the approving category recorded in the manifest, and reverses

• daily-review

  Generates a RedSkills operational review for a requested period. Default period is yesterday midnight to now (one day); pass `--period week` for a six-day window. Opens with the drain-end Attention audit, then covers delivered work, local AFK workers, cycle times, HITL/blocker challenges, and — for

• dashboard

  Shows a RedSkills operational dashboard with issue, Spec, AFK worker, flow, and DORA-proxy metrics from GitHub plus local AFK state. Use when the user invokes `/dashboard`, asks for RedSkills process metrics, workers running, open Specs/issues, cycle time, or DORA metrics.

• diagnose

  Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

• go

  Middle tier of the dispatch spectrum — `/goal` → `/go` → `/afk`. Use for genuinely untracked, ad-hoc, one-off demands only; anything that is or should be a tracked issue belongs to `/afk`. Mints a disposable issue, spins a dedicated worker, and brings back a PR. Add `--scout "<question>"` for a read

• ground-truth

  Adversarial self-verification discipline — never report a state-changing action as successful until you re-derive the claim from a fresh red-browser ground-truth snapshot. Runs inside /verify, /code-review, and the frontend skills. Use when about to assert a form submit, write, navigation, fix, or r

• guard-process-birth

  Keeps Worker process birth behind the host-scoped redskilled daemon. Use when changing per-project runtime source under apps/plugin-dev/src.

• guard-serialization

  Keeps default structured data on TOON snapshots, TOONL streams, and TOON wire frames. Use when changing JavaScript or TypeScript source under apps or packages that reads, writes, or transports structured data.

• hitl

  Resolve one ready-for-human issue by extracting the pending human decision, recording the maintainer answer as Human guidance, and moving the issue back to ready-for-agent when it becomes delegable. Use when the queue has ready-for-human issues, when a blocked issue needs a decision from you, or to

• how

  Explain how a subsystem works — "how does X work", code walkthroughs before changing something, placement and layering questions ("where should this live", "is this the right layer") — and, on request, critique its architecture with an independent panel. Use /context for the project context stack, /

• implement

  Implement a Spec or set of issues interactively — guided, human-driven counterpart to the autonomous /afk fleet.

• improve-codebase-architecture

  Find deepening opportunities in a codebase, informed by the domain language in .red/CONTEXT.md and the decisions in .red/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

• manager

  Operator liaison that carries one effort from raw intent through the existing owner workflows. `$dev:manager <intent>` starts an effort and persists it in the operator-scoped portfolio; `status` renders its brief; `checkpoint export`/`import` carries the portfolio to another host. Use when the user

• model-tier-policy

  Use when choosing or explaining the RedSkills dev model tier for validation, simple code, complex code, design, or AFK execution across Claude Code and Codex.

• prototype

  Prototype — throwaway code that answers one design question before committing to it. Use when the question is about state or logic behaviour (→ interactive terminal explorer) or about how something should look (→ several UI variations on one route, toggled by a URL param).

• red-doctor

  Adoption/process doctor — reports how fully a repo has adopted the RedSkills engineering stack. Read-only by default; `--fix` applies the canonical fix for every finding, gated per hard-to-reverse change. The recurring counterpart to the one-time `/red-setup`. Use when asked "red doctor", "check ado

• red-gains

  Shows the detailed rsp usage-gains report from the shared RedDB telemetry store. Use when the user invokes `/red-gains`, asks whether rsp is paying for itself, wants token-savings trends, latency percentiles, throughput heatmaps, degradation history, or which wrapped command saves the most tokens.

• red-setup

  The one authorized creator of a repo's `.red/` directory and the only way to enable RedSkills plugins (dev, memory, brain) in a project (ADR 0067). RedSkills hooks are installed globally on every agent but stay fully inert in any directory without a `.red/config.yaml` whose `plugins.<name>.enabled:

• red-statusline

  Install or inspect the RedSkills statusline for the active host. RedSkills renders one statusline from the `redskilled` daemon; Claude Code wires it through `.claude/settings.json` as a command-backed statusLine, while Codex configures the built-in `tui.status_line` footer and the dev plugin's Sessi

• redskilled

  Operates the per-machine redskilled daemon through its published status, provisioning, policy, and lifecycle surfaces, and writes a self-serve debug dossier for the Worker(s) that touched one issue. Use when the operator needs to inspect, provision, configure, restart, or confirm the host-scoped exe

• report-bug

  Interview the user about a bug they hit, then file a structured `type:bug needs-triage` issue on the project tracker. Pulls seed material from the conversation context when invoked with no arguments, or from the argument when one is provided. Use when the user says "report a bug", "open a bug", "thi

• resolving-merge-conflicts

  Guided merge-conflict resolution loop. Inspect state → find each side's intent → resolve every hunk preserving both intents → run the project's checks. Never abort. Use when a merge, rebase, or cherry-pick leaves conflict markers in tracked files.

• retake

  Pick one issue back up — reconstruct where it stands (linked PRs, branches, worktrees, uncommitted or unpushed work, HITL state, active blocker), report that state, then execute the one right action — a plain requeue into `ready-for-agent`, an `--adopt-branch` landing through the no-agent gate, or a

• start

  Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (.red/CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

• tdd

  Test-driven development with a red → green loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green", wants integration tests, or asks for test-first development.

• to-spec

  Turn the current conversation context into a Spec and publish it to the project issue tracker. Use when user wants to create a Spec from the current context.

• to-tickets

  Break a plan or Spec into independently-grabbable Tickets on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into Tickets, create implementation Tickets, or break down work into Tickets.

• triage

  Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

• verify

  Verify that a code change does what it's supposed to by driving a live app with the CDP driver and checking ground-truth snapshots. Use when asked to verify a PR, confirm a fix works, test a change manually, or validate that a feature is visible/functional before closing an issue.

• wayfinder

  Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

• wizard

  Generate an interactive Bash wizard for steps only a human can perform. Use for credentials, CI secrets, third-party dashboards, provisioning, migrations, or cutovers that require human action.

• zoom-out

  Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

• browser-review

  Open a generated HTML artifact for live human review — the human annotates an exact element and character range, the agent polls that feedback and iterates. A layout-audit gate blocks "done" on a broken render. Use when you want surgical element-level annotation instead of "screenshot + describe in

• writing-beats

  Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to

• writing-fragments

  Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fra

• writing-shape

  Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a roug

• research

  Performs deep official-source research on a technical topic and saves a structured Markdown report under `.red/researches/<YYYY-MM-DD>-<slug>.md`. Use when the user invokes `/research`, asks for official documentation, primary-source research, repository/wiki documentation, specs, or high-depth sour

• branch-lock

  Lock the agent to a branch and block it from switching away. Sets up self-contained pre-tool hooks that block the agent's git checkout/switch to any other branch while a lock is active, and gives you a /branch-lock command to set, change, and clear the lock. Use when you want the agent pinned to one

• git-guardrails-claude-code

  Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

• migrate-to-shoehorn

  Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

• setup-pre-commit

  Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

• ff

  Reframes the user's message into one chosen framing through a two-step interaction — first asks which framing to rewrite into, then generates that single rewrite and asks whether to dispatch (execute) it. Use when the user invokes `/ff`, says fast-forward, asks to rewrite their own message, or wants

• handoff

  Compact the current conversation into a handoff document for another agent to pick up.

• reflect

  Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, reflect on a design, or mentions "reflect".

• to-questionnaire

  Turn knowledge the user cannot supply into a Markdown questionnaire for the person who can. Use only when the user invokes this skill.

• unslop

  Cut AI tells from a piece of writing and give it a human voice. Use when the user invokes this skill on a draft, a doc, a PR body, or any prose surface.

• what

  Re-pitch the last reply so it stands on its own, in plain human language. Use only when the user invokes this skill.

• writing-for-agents

  Designs and revises documents that agents read, including skills, always-loaded instructions, and disclosed references. Use when creating or editing a SKILL.md, AGENTS.md, CLAUDE.md, agent-facing instructions, or documentation reached through a context pointer.

Subagents (3)

• complex-code

  Use for complex code changes: cross-module behavior, architectural decisions, risky migrations, security-sensitive paths, or simple-code escalations after failed validation.

• simple-code

  Use for simple, well-specified, single-scope code changes where the expected files and behavior are clear and the blast radius is small.

• validate

  Use for validation-only work: fuzzy or semantic checks, contract review, fixture/schema sanity checks, and AFK task classification before code execution.

MCP servers (1)

• rs_dev

  runs: red-skills-redskilled-mcp

Similar plugins