@bongos/core 1.20.9 → 1.20.10

package/.claude/skills/builder-redteam/SKILL.md

@@ -2,6 +2,12 @@
 name: builder-redteam
 description: >-
   File a red-team or vulnerability report — severity, target, repro, expected vs actual — for the Archon view. Metic+ only; Xenos get a polite refusal. Triggers: "/builder-redteam", "I found a security issue", "redteam report", "file a vuln", or describing a flaw in the system's own walls.
+plain: >-
+  Files a private report about a security weakness you found, for the project's leads to see.
+reach-for: >-
+  When you notice a way someone could get around the project's protections.
+cost: >-
+  Free. It files one report; nothing is fixed or changed automatically.
 ---
 
 You are filing a vulnerability report on the Example project. The reporter is a trusted builder who has found a flaw — in Bongos, the game server, the chat broadcast, the deploy chain, the auth model — and wants the red-team bounty surface to pick it up.

package/.claude/skills/builder-release/SKILL.md

@@ -2,6 +2,12 @@
 name: builder-release
 description: >-
   Cancel an active claim without shipping: the task returns to 'ready' and no credits are awarded. Triggers: "/builder-release N", "cancel my claim", "I'm dropping this task", "give it back".
+plain: >-
+  Gives a task back without finishing it, so someone else can pick it up.
+reach-for: >-
+  When you decide not to carry on with a task you reserved.
+cost: >-
+  Free. The task goes back on the list and no credit is paid for it.
 ---
 
 **Script skill (authoritative).** The core action is `node scripts/gds/release.js <task-id> --reason "..."`. Once the task id and reason are determined, run it and print its output verbatim — do not editorialize the result. If the release is refused, the output closes with an `[otb-plain]` card; for a builder whose interaction profile is not `engineer`, tell them what that card says instead of pasting the refusal (the rule is spelled out in `/builder-claim`).

package/.claude/skills/builder-sequence/SKILL.md

@@ -2,6 +2,12 @@
 name: builder-sequence
 description: >-
   Walk a dependency chain from one kickoff — claim, build, ship, repeat; --goal N scopes it to one goal. One claim at a time, always fully shipped before the next. Triggers: "/builder-sequence N", "work the chain from task N", "continue goal N", "let's tackle goal N", "run goal N end to end".
+plain: >-
+  Works through a chain of related tasks in order, finishing each one completely before starting the next.
+reach-for: >-
+  When a goal is a line of tasks and you want them done one after another.
+cost: >-
+  Each finished task gets a paid quality review, usually a few dollars charged to the project, and each one is merged into the live code.
 ---
 
 You are running a **chain**: several dependency-linked tasks, one after another, from a single kickoff. Two-thirds of the open backlog sits behind a predecessor, and shipping a task auto-promotes its dependents `backlog`→`ready` — but nothing picks the newly-unblocked task up. That gap is what this skill closes.

package/.claude/skills/builder-setup/SKILL.md

@@ -2,6 +2,12 @@
 name: builder-setup
 description: >-
   One-time builder setup: authenticates against GitHub and stores a CLI session token. If a session exists for another account, asks which to use. Triggers: "/builder-setup", "set up builder", "register me", "set up Bongos", or any /builder-* failing with "no Bongos session".
+plain: >-
+  Connects your assistant to the project for the first time, using your GitHub account to sign in.
+reach-for: >-
+  The first time you work on the project from a computer.
+cost: >-
+  Free. It saves a sign-in on your computer.
 ---
 
 You are running the one-time setup that registers this Claude Code installation as a builder on the Example Bongos.

package/.claude/skills/builder-ship/SKILL.md

@@ -2,6 +2,12 @@
 name: builder-ship
 description: >-
   Mark the claimed task shipped: awards credits, writes a session log, frees the claim. Asks for handoff notes and a value summary if not given. Triggers: "/builder-ship", "I'm done", "ship it", "mark this complete".
+plain: >-
+  Hands in finished work: it gets reviewed, merged into the project, and you are credited for it.
+reach-for: >-
+  When the task you are on is finished and tested.
+cost: >-
+  Every ship runs a paid quality review, usually a few dollars charged to the project. When it passes, your work is merged into the live code.
 ---
 
 You are shipping a task on behalf of the current builder. Shipping is the moment that converts in-flight work into permanent project history + credits.

package/.claude/skills/builder-stage/SKILL.md

@@ -2,6 +2,12 @@
 name: builder-stage
 description: >-
   Stage the working tree on the builder's own live preview to see a change in a browser BEFORE shipping. Own-scoped and machine-local. Triggers: "/builder-stage", "stage my work", "let me see it before shipping", "preview this change".
+plain: >-
+  Puts your unfinished change on your own private preview site, so you can see it in a browser before handing it in.
+reach-for: >-
+  When you want to look at a change in a real browser before shipping it.
+cost: >-
+  Free. It only changes your own preview; the real site is untouched.
 ---
 
 You are staging a builder's in-progress work on **their own** sandbox — the live game preview running on their own machine — so they can see the change in a browser, suggest fixes, and only then decide to ship it to the main game (ADR 0046).

package/.claude/skills/builder-start/SKILL.md

@@ -2,6 +2,12 @@
 name: builder-start
 description: >-
   List what the builder can claim right now, filtered for parallel-safety against every active claim. Triggers: "what can I work on", "/builder-start", "show me tasks", "what's claimable", or the start of a session.
+plain: >-
+  Shows the tasks you can pick up right now without getting in anyone else's way.
+reach-for: >-
+  At the start of a working session, or whenever you wonder what to do next.
+cost: >-
+  Free, and it changes nothing. It only reads the task list.
 ---
 
 **Script skill (authoritative).** The core action is `node scripts/gds/start.js [--widget]`. Run it and render its output verbatim — do not rebuild the table, reorder rows, or add a recap. The card is the summary.

package/.claude/skills/collab-review/SKILL.md

@@ -2,6 +2,12 @@
 name: collab-review
 description: >-
   Walk what other builders have asked of YOU — help requests and task recommendations addressed to you — verifying each against the live record before acting, and bringing back one decision at a time. The answering half of /ask-for-help. Triggers: "/collab-review", "what have people asked me", "answer my asks", "work my collab queue", or a pasted "Copy for Session Start" prompt.
+plain: >-
+  Goes through the requests other people have sent you, such as asks for help or suggested tasks, and brings you one decision at a time.
+reach-for: >-
+  When you want to answer what people have asked of you.
+cost: >-
+  Free. It only acts on a request once you have decided what to do with it.
 ---
 
 **Route skill (authoritative).** The queue is `GET /api/bongos/help-requests/for-me` and `GET /api/bongos/task-recommendations/for-me`. Read them first, work them oldest first, and report each decision as it lands — do not narrate the API.

package/.claude/skills/design/SKILL.md

@@ -2,6 +2,12 @@
 name: design
 description: >-
   The UI design session — the playbook for ui-discipline work: layouts, pages, components, design systems, the hall, status and landing surfaces. World-first: the branding pack and DESIGN.md come before any taste rule. Triggers: "/design", "design this page", "let's work on the UI", or a claimed ui task.
+plain: >-
+  The guided way to design or change how a page or screen looks, starting from the project's own style.
+reach-for: >-
+  When you are working on the layout or look of a page.
+cost: >-
+  Uses your session. You see the changes on a preview before anything goes live.
 ---
 
 You are running a **UI design session**. Two things make it different from the Engineer pack (`docs/packs/engineer.md`): the work is judged **by looking at it** (so every step ends in a rendered screen, not a paragraph), and it is done **inside a world that is not yours** — the instance's, which you read first and never override. The `ui-design` module's [CLAUDE.md](../../../modules/ui-design/CLAUDE.md) is the reference; this file is the loop.

package/.claude/skills/design-sync/SKILL.md

@@ -2,6 +2,12 @@
 name: design-sync
 description: >-
   Export the repo design system into Claude Design, then land its generated UI code back as a task. Triggers: "/design-sync", "sync design", "export tokens to Claude Design", "import to Claude Design", "push design system".
+plain: >-
+  Sends the project's design style to Claude Design, then brings the screens designed there back into the project as a task.
+reach-for: >-
+  When you want to design screens in Claude Design using the project's own style.
+cost: >-
+  Uses your session. Bringing a design back creates a task; it does not change the live site by itself.
 ---
 
 You are helping the builder run the Claude Design sync loop: export the repo's design tokens and surfaces into Claude Design so any prototype starts from real values, not guesses.

package/.claude/skills/feedback/SKILL.md

@@ -2,6 +2,12 @@
 name: feedback
 description: >-
   Pull the latest Bongos feedback bundle into this session — the walkthrough transcript and screenshots, by absolute path. Local and read-only. Triggers: "/feedback", "pull in my latest feedback", "load my bongos feedback", "I just recorded a walkthrough", "grab the latest feedback bundle", "act on my screen recording".
+plain: >-
+  Loads your most recent recorded walkthrough, what you said and the screenshots, into this conversation.
+reach-for: >-
+  Right after you have recorded feedback on the project and want your assistant to act on it.
+cost: >-
+  Free, and it changes nothing. It only reads files on your computer.
 ---
 
 You are pulling in the **latest Bongos feedback bundle** — a self-contained capture the user just recorded with the Bongos desktop app (BV1.R13 / [ADR 0087](../../../docs/adr/0087-bongos-app-architecture-and-handoff-contract.md)). The app turns a spoken screen walkthrough into a model-agnostic `prompt.md` (a timestamped transcript + an ask) plus a handful of screenshots, all under `~/CloudBongos/feedback/`. This skill loads that bundle so you can act on it directly — no copy-paste, no clipboard-image fiddling.

package/.claude/skills/figma-design-sync/SKILL.md

@@ -2,6 +2,12 @@
 name: figma-design-sync
 description: >-
   Round-trip the UI design system with Figma — push tokens and surfaces, then land a designer's edit back as code. Not otb-figma-sync, which is pixel-art tiles only. Triggers: "sync design to Figma", "push tokens to Figma", "pull my Figma edit into code", "figma round-trip".
+plain: >-
+  Keeps the project's design style and a Figma file in step: sends the style to Figma, and turns a designer's edit there back into the project.
+reach-for: >-
+  When a designer works in Figma and their changes should reach the project.
+cost: >-
+  Uses your session and your Figma access. Bringing an edit back changes the project's files.
 ---
 
 You are helping the builder run the Figma round-trip loop for the `ui` discipline's design surfaces: push the repo's current tokens/surfaces into Figma so a designer always starts from real state, then bring a designer's Figma edit back into the repo as committed-ready code.

package/.claude/skills/fix-task/SKILL.md

@@ -1,6 +1,12 @@
 ---
 name: fix-task
 description: Claim, fix, verify, and ship a single Bongos task by id — the standard cloud-bongos task loop. Use when asked to "claim/fix/ship task NNNN".
+plain: >-
+  Does one task from start to finish: reserves it, fixes it, checks it and hands it in.
+reach-for: >-
+  When you are asked to do a specific task by its number.
+cost: >-
+  Handing it in runs a paid quality review, usually a few dollars charged to the project, and merges the work into the live code.
 ---
 
 You are running the standard task loop for cloud-bongos: read a task, verify its premise, claim it, fix it test-first, then ship it. This skill chains the pieces `/builder-claim` and `/builder-ship` already own — it does not re-derive their mechanics.

package/.claude/skills/goal-create/SKILL.md

@@ -2,6 +2,12 @@
 name: goal-create
 description: >-
   Plan and create ONE goal — the module-scoped workspace between a version and its criteria — drafting its done-when criteria and seed tasks. Metic+ only. Triggers: "/goal-create", "create a goal", "what goal should this live in", or a task created with no goal.
+plain: >-
+  Helps you set up a new goal: what it is for, how you will know it is done, and the first tasks to get there.
+reach-for: >-
+  When new work does not fit any existing goal.
+cost: >-
+  Free. It creates the goal and its first tasks once you agree to them.
 ---
 
 You are running the **goal-create** session for this Cloud Bongos instance. You produce **one goal**: a title, a scope wall, two to four done-when criteria, and a handful of seed tasks — written to Bongos in one sitting.

package/.claude/skills/goal-review/SKILL.md

@@ -2,6 +2,12 @@
 name: goal-review
 description: >-
   Decide criteria a UAT can't close: work abandoned or unlinked. Metic+. Triggers: "/goal-review".
+plain: >-
+  Helps you decide what to do with a goal's done-when checks that can no longer be tested, because their work was dropped or never linked.
+reach-for: >-
+  When a goal is stuck on checks nobody can finish.
+cost: >-
+  Free. It only closes or changes a check when you decide to.
 ---
 
 You are running the **goal-review** session: the residue of the criterion close. It mirrors `/idea-triage`, for the *closing* end of the work hierarchy (ADR 0086 §6).

package/.claude/skills/goal-uat/SKILL.md

@@ -2,6 +2,12 @@
 name: goal-uat
 description: >-
   Test criteria awaiting UAT on the live site, then sign off. Metic+. Triggers: "/goal-uat", "what's awaiting UAT".
+plain: >-
+  Walks you through trying a finished goal on the live site, so a person can confirm it really works before it is signed off.
+reach-for: >-
+  When work is waiting for someone to try it for real.
+cost: >-
+  Free. Your sign-off is recorded; nothing else changes.
 ---
 
 You are running the **goal-uat** session: the closing step of a goal. A criterion no longer closes because its linked tasks shipped ([ADR 0351](../../../docs/adr/0351-a-criterion-closes-on-a-uat.md), task 1004392). Once its work has shipped it reads **Awaiting UAT**, and it closes only when a person who did **not** ship that work does what the criterion describes **on the live site** and signs it off.

package/.claude/skills/grade-audit/SKILL.md

@@ -2,6 +2,12 @@
 name: grade-audit
 description: >-
   Accountability sweep over recent grades: override ledger, dropped findings on passing grades, false-pass spot-check, outage roll-up. Queues follow-ups only — never confirms, flips a status, or re-grades. Triggers: "/grade-audit", "audit recent grades", "what shipped past the grader".
+plain: >-
+  Looks back over recent quality reviews for anything that slipped through: overrides, ignored findings, or passes that look wrong.
+reach-for: >-
+  Now and then, to check that the quality reviews are being trusted properly.
+cost: >-
+  Free. It only files follow-up tasks; it never changes a review or a task's status.
 ---
 
 You are auditing the last week of grades for accountability gaps: work that shipped past a failing grade unaccounted for, real findings that rode passing grades into production and evaporated, and passes the panel structurally could not have judged. You **describe and queue**. You never confirm, flip, re-grade, or add a gate — every follow-up lands as a queued idea or a handoff to another skill.

package/.claude/skills/grade-recover/SKILL.md

@@ -2,6 +2,12 @@
 name: grade-recover
 description: >-
   Diagnose why a ship parked at completed — grader outage, fabricated fail, or genuine quality fail — and run the right recovery. Adds no gate to the ship path. Triggers: "/grade-recover N", "my grade failed", "grader unavailable", or a ship that landed at completed.
+plain: >-
+  Works out why a quality review held your work back, whether the reviewer broke, got it wrong, or found a real problem, and takes the right next step.
+reach-for: >-
+  When your work failed its review or is stuck waiting for one.
+cost: >-
+  A fresh review is paid, usually a few dollars charged to the project, and is only run after the real cause is fixed.
 ---
 
 You are recovering a task whose ship parked at `completed` because of its grade. Your job is to diagnose WHICH of three distinct shapes did it — they look similar in a terminal scrollback and need opposite responses — then run the right recovery. You never add a new approval step: everything here is a documented, existing path (ADR 0162).

package/.claude/skills/grader-health/SKILL.md

@@ -2,6 +2,12 @@
 name: grader-health
 description: >-
   Read-only health check over recent grades — outage runs, pass-rate drift, cost anomalies, stale model pins. Changes nothing. --probe runs a live paid calibration (Metic+). Triggers: "/grader-health", "check the grader", "is the grader healthy", "grader health check", "why are grades failing lately".
+plain: >-
+  Checks whether the automatic quality reviewer is working well: failures, odd pass rates, or unusual costs.
+reach-for: >-
+  When reviews seem to be failing strangely, or you want a health check.
+cost: >-
+  Free and read-only. An optional live test of the reviewer costs a small amount.
 ---
 
 You are running a health check over the grading panel. Everything here is **read-only**: you read live surfaces, compare against known baselines, and emit findings + exact remediation commands. You never confirm, flip, or re-grade anything yourself — the builder (or /grade-recover) acts on what you report.

package/.claude/skills/idea-triage/SKILL.md

@@ -2,6 +2,12 @@
 name: idea-triage
 description: >-
   Daily walk of the idea_inbox, which holds only HOMELESS work — anything naming a goal became a task at filing time. Promote, discard or merge each open idea. Metic+ only. Triggers: "/idea-triage", "triage ideas", "review the inbox", "walk the idea inbox", or a scheduled daily run.
+plain: >-
+  Goes through the ideas that have no home yet and decides what happens to each: turn it into work, drop it, or merge it with another.
+reach-for: >-
+  Once a day, or when the idea inbox is filling up.
+cost: >-
+  Uses your session. An idea only changes when you decide what to do with it.
 ---
 
 You are running the daily idea-triage session for Example. Open ideas in the Bongos `idea_inbox` table get walked one-at-a-time and verdicted, so the inbox doesn't accumulate stale entries.

package/.claude/skills/merge-mode/SKILL.md

@@ -3,6 +3,12 @@ name: merge-mode
 description: >-
   Manual fallback for the auto-merge in /builder-ship: walks every task at status='confirmed' through merge, smoke and deploy. Triggers: "/merge-mode", "merge the queue", "land confirmed tasks", "land the queue", "do a merge run", or a /builder-ship that reported the auto-merge bailed.
 requires: [main-checkout, push-credential, gh, droplet-ssh]
+plain: >-
+  The manual backup for finishing hand-ins: it takes approved work that did not merge by itself and puts it live.
+reach-for: >-
+  Only when a hand-in reports that the automatic merge could not finish.
+cost: >-
+  Changes the live code and the live site. It needs special access that most computers here do not have.
 ---
 
 You are running the manual merge-mode session for Example. **`/merge-mode` is a rare last resort, not a routine sweep — and not something to push on other builders.** The server lands merges on its own: `/builder-ship` chains into auto-merge, green PRs auto-merge, a 5-min reconciler flips `confirmed → shipped`, and the [ADR 0082](../../../docs/adr/0082-server-side-merge-conflict-auto-resolution.md) resolver self-heals generated-file conflicts. **Before running this skill, confirm the task is genuinely stuck** — still at `confirmed` more than ~5 minutes after its ship because of a conflict or regression the server couldn't auto-resolve. If you haven't waited for the sweep yet, stop and wait. This skill is for the strand that survives all of that — usually a cross-branch / non-generated-file conflict, a smoke regression, or a `--no-merge` ship.

package/.claude/skills/new-project/SKILL.md

@@ -2,6 +2,12 @@
 name: new-project
 description: >-
   Runbook from zero to a live, owned STANDALONE instance: name, address, scaffold, provision, OAuth app, first sign-in, verify, brand. Triggers: "/new-project", "stand up a new instance", "start a new project".
+plain: >-
+  Takes you step by step from nothing to a brand-new project website of your own.
+reach-for: >-
+  When you want to start a separate project on the platform.
+cost: >-
+  Creates real things: a website, a database and a GitHub sign-in. You need a web address, which you buy yourself.
 ---
 
 You are guiding a new owner from **zero to a live, owned Cloud Bongos instance**. This skill is the **canonical step sequence** (goal 35). The `bongos onboard` CLI and the hall wizard are just other front-ends over these same steps — keep them in lockstep by keeping the sequence here.

package/.claude/skills/otb-character-review/SKILL.md

@@ -2,6 +2,12 @@
 name: otb-character-review
 description: >-
   Score a multi-frame character ANIMATION against the painterly criteria, with a verdict per frame and for the sequence. Sibling of otb-design-review, which scores one tile. Triggers: "review this animation", "is this animation consistent", "rate these frames".
+plain: >-
+  Scores a short character animation frame by frame against the project's art rules, and says whether it holds together.
+reach-for: >-
+  When you have animation frames and want to know whether they are good enough.
+cost: >-
+  Uses your session. It only gives a verdict; it changes nothing.
 ---
 
 You are reviewing a painterly **character animation** — a `character_anim` family: many frames of the *same* character in *different* poses (e.g. the Bongo Buddha idle-breathing cycle). This is the animation sibling of `otb-design-review` (which scores one pixel-art tile). Do NOT judge it as pixel art — there is no palette to match, no FireRed reference, no 32×32 grid.

package/.claude/skills/otb-design-review/SKILL.md

@@ -2,6 +2,12 @@
 name: otb-design-review
 description: >-
   Score a pixel-art tile against the Example rubric: per-criterion scores, a critique, a pass/retry/escalate verdict and a fix_hint. Triggers: "review this tile", "score X", "rate Y", or asking how a generated asset stacks up.
+plain: >-
+  Scores a single pixel-art tile against the project's art rules and says whether to keep it, redo it, or pass it up.
+reach-for: >-
+  When you want to know how a generated piece of art measures up.
+cost: >-
+  Uses your session. It only gives a verdict; it changes nothing.
 ---
 
 You are scoring a generated tile against the Example quality rubric. Do NOT critique freelance — use the rubric in `modules/art-pipeline/template/rubric.json`.

package/.claude/skills/otb-feedback-capture/SKILL.md

@@ -2,6 +2,12 @@
 name: otb-feedback-capture
 description: >-
   Turn verbal design feedback into a durable dated rule in the Example style guide. Triggers: directional notes such as "trees too modern", "saturation too high", "containers should look weathered".
+plain: >-
+  Turns a spoken comment about the art, such as 'the trees look too modern', into a lasting rule in the project's style guide.
+reach-for: >-
+  When you give direction about how the art should look.
+cost: >-
+  Free. It adds a dated rule to the style guide.
 ---
 
 You are turning a one-time piece of feedback into a permanent guardrail. The whole point of this skill is that **Lars should not have to repeat himself**. If he tells you trees should be more gnarled, every future tree generation should bake that in.

package/.claude/skills/otb-figma-sync/SKILL.md

@@ -2,6 +2,12 @@
 name: otb-figma-sync
 description: >-
   Push generated tiles into the Example Figma file as a review canvas. Hard-coded to one file ID; refuses any other. The repo stays the source of truth. Triggers: "sync to Figma", "show me the tilesheet in Figma", "update the design file".
+plain: >-
+  Puts the generated art tiles into the project's Figma file so people can review them there.
+reach-for: >-
+  When you want to see the tiles side by side in Figma.
+cost: >-
+  Uses your Figma access. It only updates that one Figma file; the project's files stay the real copy.
 ---
 
 **Script skill (authoritative).** The core action is the `use_figma` MCP tool call. Execute it with the determined parameters and do not paraphrase or reformat the Figma response — relay the frame name and link verbatim.

package/.claude/skills/otb-tile-generate/SKILL.md

@@ -2,6 +2,12 @@
 name: otb-tile-generate
 description: >-
   Generate pixel-art tiles for the Example world through the generate, review and retry orchestrator. Always reuses the locked palette and rubric. Triggers: "generate a tile", "make a sprite for X", "regenerate Y", or asking for new world art.
+plain: >-
+  Makes new pixel-art tiles for the game world, checking each one against the project's art rules and retrying the weak ones.
+reach-for: >-
+  When the world needs a new piece of art.
+cost: >-
+  Paid: every image it generates costs money and is logged, and it stops when the spending limit is near.
 ---
 
 You are operating the Example pixel-art generation pipeline. The user has asked you to produce one or more tiles. Do NOT freelance — use the existing pipeline.

package/.claude/skills/planning-session/SKILL.md

@@ -3,6 +3,12 @@ name: planning-session
 description: >-
   Structured planning for a version — scope criteria, a written spec, an owner interview on every non-obvious decision, then the seeded task list. Metic+ only. Triggers: "/planning-session", "open a planning session", "let's plan V[N]", "plan the next version", "scope a new version".
 requires: [droplet-ssh]
+plain: >-
+  A structured planning conversation for the next version: what it must achieve, a written plan, and the owner's call on every open question.
+reach-for: >-
+  When it is time to decide what the next version of the project should contain.
+cost: >-
+  Uses your session. It creates the version's plan and tasks once they are agreed.
 ---
 
 You are running a planning session for Bongos. The goal is to leave the session with: (a) a clear set of done-when criteria for a version, (b) a **written spec** (`docs/specs/<ver>-<goal-slug>.md`) that an in-depth interview refines until every non-obvious decision is resolved, (c) a ranked task list **seeded from that spec** that lives in the Bongos database, and (d) a durable record of the session for the audit trail.

package/.claude/skills/priority-session/SKILL.md

@@ -2,6 +2,12 @@
 name: priority-session
 description: >-
   A trusted builder answers a few plain questions; the answers reweight the idea_inbox and suggest what to claim next. Metic+ only. Triggers: "/priority-session", "run a priority session", "what should I work on next", "reprioritize the inbox", "what feels most important right now", "help me decide what to claim".
+plain: >-
+  Asks you a few simple questions about what matters most, then re-ranks the ideas and suggests what to work on next.
+reach-for: >-
+  When you are not sure what is most important to do next.
+cost: >-
+  Free. It re-orders the idea list from your answers.
 ---
 
 You are running a **priority session** for Bongos. Where a **planning session** sets a *version's* scope (criteria + a fresh ranked task list), a priority session works the *present tense*: it takes the open `idea_inbox` exactly as it stands and reweights it against how the builder actually feels about the work right now — what's stuck, what would unblock the most people, what they're excited to build. The session ends with a **weighted ranking of the open ideas** and a single **"what should I claim next?"** suggestion, and it writes a durable session-log entry so the reweighting is on the audit trail.

package/.claude/skills/read-session-export/SKILL.md

@@ -2,6 +2,12 @@
 name: read-session-export
 description: >-
   Read a Claude Code /export zip — conversation, thinking, tool calls — to answer questions about a past session. READS an existing export, never creates one. Triggers: a dropped session-export-*.zip, "read/summarize this session", "what happened in this session", "what was I/you thinking", "/read-session-export".
+plain: >-
+  Reads a saved copy of a past conversation with your assistant and answers questions about what happened in it.
+reach-for: >-
+  When you have a saved conversation file and want to know what went on.
+cost: >-
+  Free, and it changes nothing. It only reads the file you give it.
 ---
 
 The user already has the zip — Claude Code's built-in `/export` made it. Read it with the reader rather than by hand: it prints a compact transcript (prompts + thinking + replies + one-line tool calls) to stdout and skips the megabytes of debug logs.

package/.claude/skills/recall/SKILL.md

@@ -2,6 +2,12 @@
 name: recall
 description: >-
   One-call project-knowledge search over repo docs and DB prose. Read-only, rank-scoped. Use instead of grepping the tree. Triggers: "/recall", "recall …", "what do we know about X", "have we done X before", "did a past session hit X", "search the docs/ADRs for X", "is there an ADR about X".
+plain: >-
+  Searches everything the project already knows, its documents and past decisions, in one go.
+reach-for: >-
+  Before solving a problem, to check whether it has been solved before.
+cost: >-
+  Free, and it changes nothing. It only searches.
 ---
 
 You are answering "what do we already know about X?" — the GDS-V4 one-call-recall capability ([ADR 0060](../../../docs/adr/0060-gds-retrieval-layer.md)). Before this existed, recall meant grepping the repo + eyeballing session logs + hoping you remembered the right ADR. Now one call searches the indexed corpus (every repo markdown + nightly-indexed DB prose: task descriptions, learnings, session-log summaries, recent shipped-task summaries) with full-text + typo-tolerant fuzzy matching fused by RRF, and returns the most relevant sections with their breadcrumb (file > heading > subheading).

package/.claude/skills/scan-before-install/SKILL.md

@@ -2,6 +2,12 @@
 name: scan-before-install
 description: >-
   Vet a third-party GitHub repo or Claude plugin BEFORE installing: quarantined fetch, deterministic floor, subagent panel over a scrubbed mirror, arithmetic verdict, evidence-gated landings. The scanner never installs. Triggers: "/scan-before-install", "is this plugin safe to install", "vet this GitHub repo".
+plain: >-
+  Checks an outside add-on or code project for safety problems before you install it.
+reach-for: >-
+  Before adding anything to the project that someone else wrote.
+cost: >-
+  Uses your session, more than most because several reviewers read the code. It never installs anything itself.
 ---
 
 You are scanning a third-party artifact someone wants to install. The engine lives in `modules/security/artifact-scan/` — this skill is the orchestration wrapper: it runs the pipeline, spawns the panel, and lands one of three offers. Every load-bearing decision below is an owner decision; do not soften any of them.

package/.claude/skills/session-handoff/SKILL.md

@@ -2,6 +2,12 @@
 name: session-handoff
 description: >-
   Emit a paste-ready next-steps prompt so a FRESH session starts with curated context. Read-only. Triggers: "/session-handoff", "hand off to a fresh session", "give me a handoff prompt", "wrap up context for next time", "write the next-steps prompt", "I want to continue this in a new session", "context is getting heavy, prep a fresh start".
+plain: >-
+  Writes a ready-to-paste note so a fresh conversation can pick up exactly where this one left off.
+reach-for: >-
+  When this conversation is getting long and you want to continue in a new one.
+cost: >-
+  Free, and it changes nothing. It only writes the note for you to copy.
 ---
 
 You are producing a **handoff prompt**: a single, self-contained block of text the builder will **copy and paste as the first message of a brand-new session** to continue this work with a clean, light context.

package/.claude/skills/ship-check/SKILL.md

@@ -2,6 +2,12 @@
 name: ship-check
 description: >-
   Run every freshness and fitness check ship.js will run, and get the healing command for each stale file. Triggers: "/ship-check", "am I ready to ship", "what will ship trip on", "check before I ship", "is anything stale".
+plain: >-
+  Runs the same checks a hand-in will run, and tells you how to fix anything that would fail.
+reach-for: >-
+  Before handing in work, to avoid a failed attempt.
+cost: >-
+  Free. It only checks; fixing is up to you.
 ---
 
 # /ship-check — the pre-ship table

package/.claude/skills/status/SKILL.md

@@ -2,6 +2,12 @@
 name: status
 description: >-
   Roll up a version or criterion in one call — its gating tasks, their live statuses, and what is blocking. Read-only. Answers "what's the status of X" and "what's left for criterion Cn". Triggers: "/status", "what's left for C8", "status of GDS-V3", "how far along is the memory criterion", "what tasks remain to complete X".
+plain: >-
+  Shows how far along a version or goal is: what is finished, what is left, and what is holding it up.
+reach-for: >-
+  When you want to know how much is left before something is done.
+cost: >-
+  Free, and it changes nothing. It only reads.
 ---
 
 You are answering a project-status question. Before this skill existed, doing so meant ~10 sequential Bongos calls (grep the seed file for which tasks map to a criterion, eyeball a "Gates R55–R63" sentence, then re-query each task's status). The structured criterion↔task link (`task_criteria`, migration 055) + the `/status` CLI collapse that to one call. See ADR 0025 and task #435.

package/.claude/skills/strand-fix/SKILL.md

@@ -3,6 +3,12 @@ name: strand-fix
 description: >-
   Land ONE stranded ship — a task parked at confirmed that the reconciler gave up on. Also the fix for a claim refused 409 REBASE_REQUIRED. Triggers: "/strand-fix N", "task N is stranded", "land the strand", "my claim says REBASE_REQUIRED".
 requires: [gh]
+plain: >-
+  Rescues one piece of approved work that got stuck on its way into the project, and gets it merged.
+reach-for: >-
+  When work is approved but never reached the live code, or a task refuses to start because older work is stuck.
+cost: >-
+  Uses your session. It gets the stuck work merged into the live code.
 ---
 
 You are landing one stranded task. The reconciler is not coming back for it — a strand produces no signal of its own, so nothing happens until someone walks it.

package/.claude/skills/tweak/SKILL.md

@@ -2,6 +2,12 @@
 name: tweak
 description: >-
   Apply the next submitted page tweak: claim the round, apply every line, render the page before and after, attach the renders and ship it to wait for the artist. Metic+. Triggers: "/tweak", "apply the next page tweak", "work the tweak queue".
+plain: >-
+  Applies the next set of change requests someone made to a page, and shows before and after pictures for the artist to approve.
+reach-for: >-
+  When page change requests are waiting to be done.
+cost: >-
+  Handing it in runs a paid quality review, usually a few dollars charged to the project. The change waits for the artist's approval.
 ---
 
 You are applying ONE page an artist rewrote in the studio (Tweak Mode, ADR 0341). The artist wrote the words; your job is to transcribe them faithfully, show the artist the result, and park it. **You never land it.** The artist approves the applied page first (ADR 0341 D7), and nothing here arms a merge.

package/.claude/skills/worktree-clean/SKILL.md

@@ -2,6 +2,12 @@
 name: worktree-clean
 description: >-
   Remove per-claim worktrees whose work landed, and sweep the husks a locked remove leaves, via junction-safe worktree.js — never raw git worktree remove, which follows the node_modules junction. Triggers: "/worktree-clean", "prune stale worktrees", "worktree husks".
+plain: >-
+  Tidies away old workspace folders on your computer whose work has already been merged.
+reach-for: >-
+  When your computer is collecting old workspaces.
+cost: >-
+  Free. It deletes only workspaces whose work is already safe in the project.
 ---
 
 **Script skill (authoritative).** Two scripts do the work; this skill only sequences them and shows the list before anything is removed.

package/docs/module-api-changelog.md

@@ -2675,5 +2675,7 @@ is load-bearing: the script throws rather than guess if it is missing, and
         landed since 1.20.7 with no explicit bump. run 36669272909. (task 1002620)
   1.20.9 — CI auto-patch (publish-on-merge, ADR 0161): carrier for merges
         landed since 1.20.8 with no explicit bump. run 36669791458. (task 1002620)
+  1.20.10 — CI auto-patch (publish-on-merge, ADR 0161): carrier for merges
+        landed since 1.20.9 with no explicit bump. run 36670625760. (task 1002620)
 ---------------------------------------------------------------------------
 ```

package/modules/ui-design/skills/brandkit/SKILL.md

@@ -5,6 +5,12 @@ description: >-
   first, holds the logo standard and the five concept methods, and lands the system as the instance's own
   materials — the mark as SVG, the colours as the pack, the type as its faces. Triggers on "brand kit",
   "identity system", "logo system". Never generates a logo, wordmark or UI mockup.
+plain: >-
+  Builds the project's visual identity, its logo, colours and typefaces, as the project's own files.
+reach-for: >-
+  When the project needs a brand identity, or its identity needs pulling together.
+cost: >-
+  Uses your session. It adds brand files to the project and never generates a logo image.
 ---
 
 <!-- BEGIN PLATFORM PREAMBLE · ui-design module · one block, byte-identical in every skill the module ships (vendored or rebuilt in-house) so an upstream refresh is a three-way merge; the source is modules/ui-design/skills/PREAMBLE.md and tests/ui_design_skills.mjs fails on drift -->

package/modules/ui-design/skills/design-taste-frontend/SKILL.md

@@ -5,6 +5,12 @@ description: >-
   Says the design read in one line, sets three dials (variance, motion, density), locks one world for the
   whole page, and ends on a pre-flight the kit measures. Triggers on "design a landing page", "make this not
   look templated", "taste pass", "anti-slop". Not for dashboards or native mobile.
+plain: >-
+  The default way to give a landing page or marketing page a strong, considered look that does not feel like a template.
+reach-for: >-
+  When a landing or marketing page looks generic.
+cost: >-
+  Uses your session. It changes the page, and you check it on a preview.
 ---
 
 <!-- BEGIN PLATFORM PREAMBLE · ui-design module · one block, byte-identical in every skill the module ships (vendored or rebuilt in-house) so an upstream refresh is a three-way merge; the source is modules/ui-design/skills/PREAMBLE.md and tests/ui_design_skills.mjs fails on drift -->

package/modules/ui-design/skills/design-taste-frontend-v1/SKILL.md

@@ -5,6 +5,12 @@ description: >-
   gets exactly this behaviour while the default (design-taste-frontend) evolves separately. A fixed triple of
   dials, the layout bans, full interaction cycles, and a named vocabulary of premium patterns. Triggers on
   "design-taste-frontend-v1", "the fixed dials", "the pattern vocabulary".
+plain: >-
+  The earlier version of the landing-page style guide, kept so work that asked for it gets exactly the same results.
+reach-for: >-
+  Only when a task asks for this older version by name.
+cost: >-
+  Uses your session. It changes the page, and you check it on a preview.
 ---
 
 <!-- BEGIN PLATFORM PREAMBLE · ui-design module · one block, byte-identical in every skill the module ships (vendored or rebuilt in-house) so an upstream refresh is a three-way merge; the source is modules/ui-design/skills/PREAMBLE.md and tests/ui_design_skills.mjs fails on drift -->

package/modules/ui-design/skills/gpt-taste/SKILL.md

@@ -5,6 +5,12 @@ description: >-
   every other one. A written plan block before any markup, derived deterministically from the route; the
   four-stage attention-interest-desire-action structure; an ultra-wide hero; a dense tile grid with zero empty
   cells. Triggers on "it looks generic", "award-tier", "anti-default".
+plain: >-
+  A stricter style pass for a long, persuasive page that keeps coming out looking like every other one.
+reach-for: >-
+  When a scrolling sales or landing page still looks generic after a first try.
+cost: >-
+  Uses your session. It changes the page, and you check it on a preview.
 ---
 
 <!-- BEGIN PLATFORM PREAMBLE · ui-design module · one block, byte-identical in every skill the module ships (vendored or rebuilt in-house) so an upstream refresh is a three-way merge; the source is modules/ui-design/skills/PREAMBLE.md and tests/ui_design_skills.mjs fails on drift -->