All authors
Claude Skills by thrum-team
github.com/thrum-team160 skills0 installs0 views
- Setting Up Account UsageUse when the user wants to see account usage, quota, usage limits, rate limits or their plan usage, when thrum team shows no Accounts section or the line Usage not enabled on daemon, when account usage says not_installed, version_mismatch or unavailable, or when setting up quota-axi for the daemon and choosing which runtimes it reads.Votes: 0GitHub stars: 2
- Snapshot ProtocolUse when composing a restart snapshot or continuation - snapshot structure, worktree resolution, write rules.Votes: 0GitHub stars: 2
- Stamp ProtocolUse when stamping a plan, prompt, or snapshot - Authored-against format, derivation commands, never-type rule.Votes: 0GitHub stars: 2
- State MigrationUse when your agent-local thrum state is empty AND you have an existing State.md file in your agent directory - this is a ONE-TIME conditional onboarding that fires only on that exact combination. Do NOT use if thrum state already has entries (nothing to migrate) or if you have no State.md (brand-new agent, nothing to migrate). Triggers on - first session after the thrum state redesign lands, `thrum state list` returning empty while State.md exists on disk, being asked to migrate your persona...Votes: 0GitHub stars: 2
- StewardUse when running as a Steward - a persistent watcher that carries questions between several projects' coordinators (and brainstormers) and the project owner, sends them to the owner's inbox, and carries the owner's answers back with project and sender context. Never decides content.Votes: 0GitHub stars: 2
- Thrum MemoryUse when capturing, reading or querying structured memories (session summaries, architectural decisions, restart snapshots, agent rules) via the thrum memory CLI - writing a role-rule, looking up rules at session start, recalling a topic, or checking what a memory should say before you write it.Votes: 0GitHub stars: 2
- ThrumMulti-agent coordination via messaging, groups, and shared context. Use when agents need to communicate, delegate work, or coordinate across worktrees.Votes: 0GitHub stars: 2
- Trace Spec To PlanUse before converting a plan into epics/beads/worktrees, and whenever you need to know whether a plan actually implements its spec. Walks EVERY requirement in the spec forward into the plan, one item at a time, and reports PLANNED / NAME-ONLY / ABSENT / PARTIAL. Distinct from verify-against-source, which reads the ARTIFACT and asks 'does this honor its source' — this reads the SPEC and asks 'where did this land'. Triggers - about to run project-setup, about to create epics or beads, plan revi...Votes: 0GitHub stars: 2
- Transcript SearchUse when you need to search past sessions, find what we decided about a topic, recall an earlier conversation, find where an agent discussed something, search agent history or transcripts, or work out which session mentioned a word, error or command. Covers thrum transcript search, show and reindex - count first, narrow, search with a small limit, read one window, delegate broad questions to a cheap sub-agent.Votes: 0GitHub stars: 2
- Update QueueUse to reconcile your own thrum queue against ground truth - 'update my queue', 'audit my queue', 'my queue is stale', 'reconcile the queue', 'clean up done bundles', or at any session start / lull when you are about to conclude nothing is pending. Verifies each live bundle against git + beads + merge state, drops rot, adds missing committed work. Any role. A repeatable subset of a full multi-agent reconcile - scoped to YOUR queue only.Votes: 0GitHub stars: 2
- Using MonitorsUSING thrum monitor to schedule reminders, periodic script checks and pane nudges; use when asked to set up a monitor or verify one deliveredVotes: 0GitHub stars: 2
- Using The DashboardUse when you want to present an interactive board to the human user (status, options, NEEDs with A/B/C picks), or when you see a dashboard mention and wonder what is actually usable today. Carries the CLI surface, the write/read discipline, and the live-vs-coming honesty table.Votes: 0GitHub stars: 2
- Using The QueueUse to track your committed work or see who is doing what - 'what is on my plate', 'promote a backlog bead', 'assign work', 'nothing pending'. Also run it before concluding you are done, to reconcile committed work against the queue.Votes: 0GitHub stars: 2
- Using Thrum StateUse when reading or writing thrum state - your session-start state, next actions, a fleet fact like deploy state or topology, or a stale-row freshness ping. Confirm each row is measured, not guessed, before you write it.Votes: 0GitHub stars: 2
- Using Tmux SshUse when about to ssh to a host, run a command on a VM or remote box, start a long test or build on another machine, inspect a remote log, or recover after an ssh connection dropped or a remote command timed out. Use tmux-ssh for remote commands, saved-watch resume, and concurrent observation.Votes: 0GitHub stars: 2
- Verify Against PlanUse after implementation is complete to verify the code covers every requirement from the plan / design spec - runs alongside code-review as the second pass in the Code Review Protocol. Takes an optional design= input so requirements that only the design doc states are checked too. Outputs structured findings - missing scope, unmet acceptance criteria, silent deviations from the spec, newly-introduced surprises.Votes: 0GitHub stars: 2
- Verify Against SourceUse when verifying that a prose artifact (brainstorm, design spec, plan, or implementation prompt) honors its input/source artifact(s) - the prose counterpart to verify-against-plan. Runs as the conformance axis of the planning-skill review loop. Outputs structured findings - missing scope, silent deviations from the source, scope creep, misunderstandings.Votes: 0GitHub stars: 2
- Watcher ArchetypeUse when running as a watcher agent on a scheduled wake - the read-only, wake-run-exit detection loop (scan, then triage plus fix-sketch, then emit, then report, then job done). Loads the deterministic run-cycle discipline and the domain skill-pack plug-in contract for security/lint/deps/etc. watchers built on the v0.11 watcher substrate.Votes: 0GitHub stars: 2
- Writing Durable MarkdownUse when creating or editing ANY markdown file - CLAUDE.md, a role preamble, a SKILL.md, a runbook, project state, State.md, a spec, a plan, a README, or docs. Fires on adding a rule, writing a note, correcting a wrong claim, recording a lesson, or documenting an incident. Enforces state-the-rule-and-stop, because narrative in a loaded file costs tokens at every wake and leaves contradictions nobody can untangle.Votes: 0GitHub stars: 2
- Adversarial CritiqueStress-test a mid-implementation design fork by dispatching sub-agents that argue opposing options across three structured rounds. Produces a defended pick with invariants and acceptance criteria — not a "both approaches work" summary. The artifact left on disk is an audit trail: if the decision proves wrong later, future readers can see exactly why it was made and what was considered.Votes: 0GitHub stars: 2
- Agent Messaging Protocol- Communicate directly with the intended party whenever possible. - Treat the original message as the authoritative source. - Forward a pointer to the original message instead of retyping or paraphrasing its body. - Include the original author, original message ID, intended recipient, and requested action. - Attach `message:<original-message-id>` as a message reference when supported. - Read the original message before acting: `thrum message get <message-id> --json`. - Reply against the orVotes: 0GitHub stars: 2
- Brainstorm Queue AwareYou are a brainstormer running the normal `brainstorming` skill, and your briefing names a `steward: @<name>` (or otherwise tells you a Brainstorm Steward is managing your slot in a queue of parallel brainstorms). That one fact is the whole trigger. If no steward was named, ignore this skill entirely and run `brainstorming` exactly as documented — ask the human directly, the ordinary way.Votes: 0GitHub stars: 2
- Brainstorm StewardYou are the **Brainstorm Steward** — a persistent watcher whose roster is a set of remote brainstormer agents rather than implementers or coordinators. Your job is to keep the owner from having to hold N brainstorm threads open at once: you multiplex every brainstormer's pending question into a single queue in your own pane, relay the owner's answer back to the right brainstormer, and hand off the mechanical parts (launch, dual-review approval) to coordinators. The brainstormer then runs its ownVotes: 0GitHub stars: 2
- Brainstormer Dashboard NeedsWhen your steward or coordinator runs a dashboard board for the human (the steward-console pattern), your NEED travels as an **action-pick widget** the human answers by clicking. This is a thin overlay on `using-the-dashboard` (invoke it first for the CLI contract and the honesty table) and on the queue-aware pattern you already run — same discipline, new surface: the question leaves your hands as a structured pick, and the answer comes back as a routed ANSWER message, exactly as before.Votes: 0GitHub stars: 2
- Brainstormer Staying CurrentKeep a long-lived brainstorm branch current without landing it into the merge target. Every git write in this skill (commit, merge, revert, push) stays with you — never delegate a git write to a subagent. Every `fetch` also stays with you, the acting agent, per Preserve and Bind freshness below. If you delegate the read-only merge-base/status analysis, load `choosing-subagent-models` first and fence the subagent to `show`, `log`, `diff`, `grep`, `rev-parse`, `merge-base`, `status` — the same reaVotes: 0GitHub stars: 2
- Choosing Subagent Models**Every subagent you dispatch for an answer must WRITE ITS RESULT TO A FILE (e.g. `/tmp/<task>.md`); its reply to you is only a summary. Put this in the prompt.**Votes: 0GitHub stars: 2
- Closing Findings While WarmAn implementer mid-fix notices a sibling defect, or a reviewer flags a finding during a review cycle. The cheap move is to write it down and move on: file a bead, note "P2 fast-follow" in the report, close out DONE. That paper trail looks like closure but frequently isn't — the bead never gets created, the context that made the fix cheap (the file open, the failure mode fresh in mind) is gone by the time anyone looks at it again, and "tracked" quietly becomes "dropped."Votes: 0GitHub stars: 2
- Configure RolesGenerate role-based preamble templates customized to your project environment. Templates auto-apply when agents register via `thrum quickstart`.Votes: 0GitHub stars: 2
- Conversation Only ContextYour context is the session's scarcest resource. It buys conversation with the operator, messaging, queue and state — nothing else. Every investigation, verification, root-cause, code read, doc summary and VM job goes to a named persistent subagent that writes its result to a file.Votes: 0GitHub stars: 2
- Coordinator Assessing Agent Completion`thrum tmux connect` tells you which agents are **alive**. Nothing tells you which are **alive but done**. This is that second question.Votes: 0GitHub stars: 2
- Coordinator Branch Split On Block- A merge gate (`coordinator-hotpath-merge-gate` or `coordinator-philosophy-merge-gate`) — or dual review — **BLOCKS on one identifiable concern** of a branch, while the branch also carries one or more genuinely independent, unrelated concerns that are clean. - The clean concern(s) are ready to land on their own merits and gain nothing from waiting on the blocked concern's fix. - The branch lives on a **live multi-writer shared branch** — other coordinators/agents are also pushing, so Votes: 0GitHub stars: 2
- Coordinator Dashboard Human LoopYou own boards the HUMAN reads — the reference shape is the Brainstorm Steward console: ① NEED queue (unified, oldest-first, each an action-pick) ② roster health ③ owner decisions (pending + recently-resolved) ④ pipeline status. Surface basics live in `using-the-dashboard` — invoke it for the CLI shapes and the live-vs-coming honesty table. THIS skill carries the loop mandate.Votes: 0GitHub stars: 2
- Coordinator Deploying A Node> This runbook covers EVERY deploy to a single node, migrating or not. Most > sections apply to every deploy; only migration-weight and store-corruption > specifics are bump-only.Votes: 0GitHub stars: 2
- Coordinator Dispatching Work**Why:** Manual `tmux send-keys 'claude'` followed by `$thrum:thrum-prime` skips identity registration and produces silent CWD drift. The `thrum tmux launch <name>` flow registers the agent against the worktree path correctly and gives the daemon a real PID to track.Votes: 0GitHub stars: 2
- Coordinator Hotpath Merge Gate- **Queue every gate request on arrival** with `thrum queue add --title "gate <branch>@<short sha>"`, and reply to the requester with the bundle ID. A request that lives only in a message is lost at your next compaction. Without a Pro licence (`not entitled` / `requires a license`), skip this write and track it in the message thread instead. - **Reconcile your queue before starting a gate** (`thrum queue list`) and take the oldest pending item in the coordinator's order. Only an explVotes: 0GitHub stars: 2
- Coordinator Interacting With The OwnerCoordinators consume **40-50% of this box's total tokens** (owner's figure). The dominant cause is narrating agent traffic to the pane for a human who is not there — a stream of notification turns, each answered with a multi-paragraph pane report, spending about half a coordinator session talking to nobody.Votes: 0GitHub stars: 2
- Coordinator Managing State And Lifecycle**Why:** Project state captures session-level context (what shipped, what broke, what's next) and feeds the next session's priming. If implementers update it, role separation collapses: the implementer's view of state is their epic, not the team's.Votes: 0GitHub stars: 2
- Coordinator Merging Code**Check whether you are the merge king for THIS branch before running this sequence.** Do not assume — read it from config:Votes: 0GitHub stars: 2
- Coordinator Philosophy Merge Gate**Finish the gate you are in. Never restart mid-gate.** A finding that exists only in your context is one restart from gone.Votes: 0GitHub stars: 2
- Coordinator Plan Reconcile GateRun this gate when:Votes: 0GitHub stars: 2
- Coordinator Rolling Out To Nodes> This skill is the ORCHESTRATION layer. It does not replace > `coordinator-deploying-a-node` — it calls it, once per node.Votes: 0GitHub stars: 2
- Coordinator Running Autonomous Feature DevelopmentWhen idle and a qualifying backlog item exists, the coordinator drives the whole front half: scan, select, stand up a brainstormer, **drive the design Q&A on the questions it owns**, surface only the genuine judgment calls (batched), dual-review to a clean plan, and present the human a finished plan for go/no-go. On approval, execution routes through a **standing orchestrator**.Votes: 0GitHub stars: 2
- Coordinator Running Brainstorm CyclesA coordinator-orchestrated brainstorm is the right shape when:Votes: 0GitHub stars: 2
- Coordinator Running Review Cycles**Why:** Reviewers serve different purposes. `feature-dev:code-reviewer` catches security, error-handling, idiom, and dead-code issues. `verify-against-plan` catches missing scope, unmet acceptance criteria, and silent deviations from the plan. Running them sequentially doubles review-cycle latency for no reason — they're independent reads of the same diff.Votes: 0GitHub stars: 2
- Coordinator Single Responsibility Merge GateThis skill has been superseded by `coordinator-philosophy-merge-gate`, which subsumes single-responsibility as one lens (Lens 10, with sub-probes 10a/10b/10d) among the full `.thrum/philosophy.md` anti-pattern set.Votes: 0GitHub stars: 2
- Deviations ProtocolThis file is the canonical source-of-truth for the "Deviations from Source" block emitted by planning-loop artifacts (plans, implementation prompts). Invoke this skill to author the block, even when empty.Votes: 0GitHub stars: 2
- Diagnosing Fleet And Daemon**This is a LOOKUP TABLE, not a procedure.** You are here because something is broken and you need an answer in one command. Read the row you need and go.Votes: 0GitHub stars: 2
- Efficient Multi Agent ResearchWhen investigating N items (N > 6), reading everything into the main agent's context pollutes it and degrades decision-making. Instead, partition the work across parallel sub-agents that write findings to disk, then consolidate into a single report.Votes: 0GitHub stars: 2
- Fixing Documentation Errors**You found it, you can verify it, you fix it — in this turn.**Votes: 0GitHub stars: 2
- Generator Idempotency ProtocolThe modes are idempotent — running the skill repeatedly on a stable project should produce no file changes after the first run.Votes: 0GitHub stars: 2