s8-playbook

Plugin s8-playbook from marketplace solution8 in solution8-com/s8-agentic-playbook. Commands read from the repo's manifest — 1 month ago.

Skills (26)

• diagnosing-bugs

  Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

• grill-me

  A relentless interview to sharpen a plan or design. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrase.

• handoff

  Compact the current conversation into a handoff document a fresh session can pick up from. Use at the end of a working session, when the context nears its edge, or when the user asks to wrap up or hand over - on a repo with code, where the tracker and the git history already hold the state. On a doc

• implement

  Implement a piece of work based on a spec or set of tickets. Use when work arrives from /pickup-issue, or when the user asks to implement or build something already specced in a ticket.

• improve-codebase-architecture

  Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

• onboarding

  Set the playbook up alongside a person's existing Claude setup, then show them where to start. Use immediately after the plugin is installed, when someone says they have just installed it, or when they ask how it fits with the skills, CLAUDE.md or habits they already have.

• orchestrate

  Build a whole spec, or a set of issues, with parallel builder agents on one integration branch, then verify, review and hand over one pull request. Use when the user says "orchestrate", "build these issues", "implement this spec" or "run the spec", or names several issues to build together. For one

• pickup-issue

  Load one issue's context and set up its workspace, then hand to /implement. Use when the user names an issue to work on ("pick up #12", "let's do issue 40", "start on the auth one"), or points at an issue URL and wants work to begin.

• pr

  Use when writing a PR body.

• prototype

  Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

• research

  Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

• retro

  Conduct a retrospective on a coding session.

• review-suite

  Run selected review passes — over-engineering, dead-code, duplication, security, authz-coverage, docs-drift, error-handling, standards — as parallel subagents over a diff, branch, or whole codebase, merged into one severity-coded HTML triage report with gh-issue export. Use when the user asks for an

• setup-repo

  Set up a project repo - create it or adopt an existing one, then wire what the project actually needs. Use when standing up a new project, or bringing an existing one under the playbook.

• start

  Pick up an existing project cold by reading its state docs before doing anything else. Use at the beginning of a working session, when the user says "start", "continue", "where were we", or "pick up where we left off", or whenever you are dropped into a repo with no context from a previous session.

• suggest

  Point someone at the skill that fits what they are doing. Use when they are unsure what to reach for ("what do I use for...", "is there a skill for this"), or describe a piece of work without naming a skill.

• tdd

  Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

• to-issues

  Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

• to-questionnaire

  Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

• to-spec

  Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

• update-docs

  Save session progress to the ledger, refresh any project docs the work drifted from, and write the handoff for the next session. Use at the end of a working session, when a milestone lands, when the context nears the smart-zone edge, or when the user asks to wrap up or update the docs - on a docs, t

• verify-feature

  Live runtime verification of a diff - drive the real app through UI flows, hit the endpoints, inspect the database, and prove behavioral side effects, compiled into one self-contained HTML evidence report with screenshots. Use whenever the user wants a feature verified, tested end-to-end, or proven

• wait-what

  Re-pitch the last message when it did not land. Use when the user signals they did not follow what was just said — "wait, what?", "huh?", "i don't get it", "you lost me", "kan du sige det igen".

• 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 that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can pe

• writing-for-agents

  Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Similar plugins