All authors

Claude Skills by abrooks89
github.com/abrooks8928 skills1 installs6 views
- InstallThe guided onboarding for agentflow — sets up a fresh machine AND orients the user on running the fleet. Interviews for the environment + first project profile, writes the typed config, provisions the Python/PyYAML/autodoc venv, installs the hooks, makes the venv the box's default python, hard-fails on missing required config, then walks the user through launching and operating the seven loops. The single hands-on guide (install + first use). Triggers on "set up agentflow", "install agentflow...Votes: 0GitHub stars: 3
- BrainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.Votes: 0GitHub stars: 3
- Executing PlansUse when you have a written implementation plan to execute in a separate session with review checkpointsVotes: 0GitHub stars: 3
- Requesting Code ReviewUse when completing tasks, implementing major features, or before merging to verify work meets requirementsVotes: 0GitHub stars: 3
- Subagent Driven DevelopmentUse when executing implementation plans with independent tasks in the current sessionVotes: 0GitHub stars: 3
- Systematic DebuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesVotes: 0GitHub stars: 3
- Writing PlansUse when you have a spec or requirements for a multi-step task, before touching codeVotes: 0GitHub stars: 3
- Asking QuestionsUse when about to ask the user a weighted decision or a choose-between-options question via AskUserQuestion, buttons, or any pick-one/pick-many UI. Especially when tired, moving fast, batching several questions, or tempted to "just fire the buttons."Votes: 0GitHub stars: 3
- AuditorPost-build intent-feedback loop — the fourth agentflow loop, run AFTER the builders. Each wake reviews the last N done epics, fans out one read-only subagent per epic to judge whether the epic's INTENT (its use cases, not its task list) was actually accomplished — verifying live per verification.strategy — and files DRAFTED gap/enhancement epics for the human to approve on their dev-manager pass. Every wake it also runs the fixed-issue pass: it checks each ask of an open issue a merged change...Votes: 0GitHub stars: 3
- Autodoc InitGenerate a full code-documentation wiki from a source repo using an ultracode workflow. Clones the repo, scaffolds the autodoc structure, fans out parallel agents to map every endpoint, page, component, service, process, vendor, runbook, data-model, decision (ADR), flow, and job, synthesizes dependency-ordered guided tours, then builds the index/overview. Triggers on: /autodoc-init, autodoc init, build the code wiki, document the whole repo, generate autodoc, map the codebase into autodoc.Votes: 0GitHub stars: 3
- Autodoc UpdateIncrementally refresh the autodoc code wiki from new commits. Pulls the source repo, diffs against the last-documented commit, maps changed files to the pages that document them, and runs an ultracode workflow to update affected pages, add pages for new entities, and flag deletions. Triggers on: /autodoc-update, autodoc update, refresh the code wiki, update autodoc from commits, sync autodoc.Votes: 0GitHub stars: 3
- BacklogUse when the user wants to defer something for later without losing it — "put a pin in that", "save for later", "defer that", "park this", "come back to it later", "stash that idea", "queue it up", or any equivalent. Creates a placeholder epic spec at `<data_root>/projects/<name>/design/specs/YYYY-MM-DD-<slug>.md` so it appears immediately in the planning queue (surfaced by the disk epic-survey) and is ready to be expanded via `/project <spec-path>` later.Votes: 0GitHub stars: 3
- Choose NextUse when the user wants to pick the next epic to work on from the status dashboard's queue — "/choose-next", "suggest something to do", "pick an epic", "what should I work on next", "give me 3 options". Surveys every queued epic (speccing, drafted, approved-for-autonomous, planning) on the dashboard, computes which are blocked (deps not yet done) vs ready, and proposes three deliberately diverse options (quick win + strategic-unblocker + drift-recovery). On selection, invokes `/project <spec-...Votes: 0GitHub stars: 3
- Dev ManagerUse when <person.name> wants to run the fleet's human session — the question hub and interactive refinement loop. Pumps open registry Question rows (halted > waiting > advisory) and answers or asks them, drives specs from `drafted` to `approved-for-autonomous` by locking requirements decisions and brainstorming the meaty ones, and owns the `## Blockers` rows the auditor escalates to it. It has NO unattended mode: the liveness sweep, malformed-row repair and the cull belong to the steward, and...Votes: 0GitHub stars: 3
- Graph QueryAnswer questions about a documented codebase from the autodoc graph store — one routed graph query (local entity traversal or global community-report search) instead of reading pages by hand. Every claim cites a file:line span. Triggers on: /graph-query, graph query, ask the code wiki, query the autodoc graph, where is X implemented, what calls X, how does the system fit together (against an autodoc corpus).Votes: 0GitHub stars: 3
- Jr Dev 1Second parallel builder for the fleet. Use when a second concurrent session should build epics alongside a running /lead-dev — claims ONLY from the registry `## Queue` rows lead-dev publishes to the `jr-dev-1` lane, never selects its own work. Launch ONCE with `/jr-dev-1 [--project <name>]` (the argument picks the active project and beats the session's injected default); do NOT wrap in /loop; do NOT launch when no primary loop is active (nothing will feed the lane). Opt-in: only runs when the...Votes: 0GitHub stars: 3
- Jr Dev 2Third parallel builder for the fleet. Use when a THIRD concurrent session should build epics alongside a running /lead-dev (and /jr-dev-1) — claims ONLY from the registry `## Queue` rows lead-dev publishes to the `jr-dev-2` lane, never selects its own work. Launch ONCE with `/jr-dev-2 [--project <name>]` — `--project` picks the active project on the slash command and beats the session's injected default; it is a project selector, never a work target. Do NOT wrap in /loop; do NOT launch when n...Votes: 0GitHub stars: 3
- Jr Dev 3Fourth (INTERIM) parallel builder for the fleet. Use when a FOURTH concurrent session should build epics alongside a running /lead-dev (and /jr-dev-1, /jr-dev-2) — claims ONLY from the registry `## Queue` rows lead-dev publishes to the `jr-dev-3` lane, never selects its own work. Launch ONCE with `/jr-dev-3 [--project <name>]` — `--project` picks the active project on the slash command and beats the session's injected default; it is a project selector, never a work target. Do NOT wrap in /loo...Votes: 0GitHub stars: 3
- Lead DevAutonomous staging-pump loop for the configured project. Selects work, drives it through /project to staging with ultracode multi-agent orchestration, and gate-verifies via role-based Playwright subagents. Self-paced via ScheduleWakeup (one epic per wake, state-file handoff across context resets). Launch ONCE with `/lead-dev [--project <name>] [target]` — `--project` picks the fleet on the slash command itself and is forwarded on every self-wake; do NOT wrap in /loop.Votes: 0GitHub stars: 3
- OrchestratorUse when given a multi-day epic spec to execute autonomously across phases of tasks with parallel subagent dispatch, regression auto-fix, and status board persistence. Triggers on `/orchestrator <plan-or-spec-path>` or when user describes a multi-day epic and wants minimum approvals after plan approval.Votes: 0GitHub stars: 3
- Polish ModeDeep polish pass — act as product manager + architect over the live product to GENERATE graded, already-decided work when the backlog runs dry or the user says "polish" / "polish mode". Produces filed issues, drafted epic specs, and backlog-pinned forks for the dev-manager — it does not build the work it finds.Votes: 0GitHub stars: 3
- ProjectWorkflow-aware meta-command for the epic-launch pipeline (brainstorm → plan → orchestrator). Detects what was handed in and resumes from the right point. Use when invoked as `/project [arg]` or when the user says "spin up an epic for X", "kick off a project on Y", "let's project this", "take this from spec to epic", "scaffold a new epic on X", "run /project on this plan/spec", or otherwise asks to push a topic / spec / plan into autonomous execution. Routes by input — empty/topic → fresh full...Votes: 0GitHub stars: 3
- RefineYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.Votes: 0GitHub stars: 3
- ReportThe fleet status report — one predictable template that answers "what is going on", collected in ONE data pass and rendered three ways: an artifact (the full visual report, where Mermaid renders natively), a permanent vault page (which makes the next report a diff instead of a guess), and an ASCII-only Ntfy push (blocked-first, ending in the single next action). Three triggers, same output — automatically at the start of every dev-manager session, on a 24h ceiling when the last report is olde...Votes: 0GitHub stars: 3
- SolutionUse when about to produce an implementation plan that will be executed by the orchestrator. Wraps ../_vendored/writing-plans/SKILL.md to produce a plan with YAML frontmatter declaring phases, task DAG, and test commands. Triggers when invoked by the orchestrator OR when user explicitly requests an "epic plan" / plan-with-frontmatter.Votes: 0GitHub stars: 3
- StewardMaintenance steward for the configured project — a loop alongside the builders (lead-dev and every jr-dev lane), auditor (intent feedback) and dev-manager (the human's seat). Does NOT build epics. Sweeps what no builder's selection rule can reach because it is caused by time passing, not by work arriving — spec frontmatter that lags merged reality, stale lane claims, an orphaned deploy lock, deployed-vs-source drift, schema-vs-code drift, silently failing services, repo/vault debt, host proce...Votes: 0GitHub stars: 3
- Tdd LoopUse when implementing a feature or bugfix from a spec/ticket and you want the full red-green-refactor cycle run autonomously with subagent-driven debug and critic review, surfacing only when green+critic-approved or genuinely blocked. Triggers on "tdd loop", "implement this spec via tdd", "run the autonomous tdd cycle", or any request to ship a feature without per-step intervention.Votes: 0GitHub stars: 3
- Wiki SaveWrite ONE durable page into the project's `wiki/` pillar at the end of a firing that produced something durable — a lesson learned or a decision made. Fires at four phase boundaries: end-of-epic, park, halt, block. A lane duty for five seats — `lead-dev`, `jr-dev-1`, `jr-dev-2`, `jr-dev-3` and `dev-manager` — and a human command in any interactive seat (`/wiki-save [--project <name>] [what to save]`). Writes through `agentflow.wiki` — `write_page`, then `refresh_projection` — never by hand-ed...Votes: 0GitHub stars: 3