⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
assistive-ux
Use when adding, reviewing, designing, testing, or managing Assistive UX moments in Berd, including discover, suggest, and autoApply guidance, adaptive settings, behavior signals, retirement rules, or changes under src/shared/assistive-ux.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
Berd
Berd is an open-source desktop app for working with AI agents. It is built with
Tauri 2 and React 19 and talks to the upstream Goose backend through the ACP
WebSocket served by a goose serve sidecar.
The repository builds a general-purpose public distribution. Organizations can also create enterprise distributions by supplying managed provider settings, private resources, and release infrastructure through the repository's distribution seams without adding private material to the public source tree.
Getting started
just setup
just dev
just setup installs pnpm dependencies, builds the vendored @aaif/goose-sdk,
and prepares the Goose backend pinned by goose-backend.lock.json in your
platform cache directory. just dev reuses that stamped pinned binary and fails
if the lockfile commit no longer matches the cached build.
If you already have an upstream Goose binary you want to test, set
GOOSE_BIN=/path/to/goose before running just dev; that is an explicit local
override and bypasses the managed pinned checkout.
To bump the default Goose backend, update the lockfile in a PR:
scripts/update-goose-backend-lock.sh main # or a tag/branch/sha
just goose-sync # fetch/build the new pinned commit
Bundling and distributions
Tauri bundles the Goose backend as an external sidecar. By default, just bundle
stages the pinned managed Goose binary from goose-backend.lock.json and then
runs pnpm tauri build:
just bundle
You can stage an explicit local binary with
GOOSE_BIN=/path/to/goose just stage-sidecar. Staging creates
src-tauri/binaries/goosed-<rust-host-triple>, matching the
"externalBin": ["binaries/goosed"] entry in src-tauri/tauri.conf.json.
The public build is self-contained and does not require private package registries or enterprise credentials. Enterprise distributors may overlay private agents, runtime configuration, optional companion tools, update channels, and signing or publishing infrastructure in their own private build orchestration.
Optional companion CLI
Berd includes a distribution seam for bundling an optional companion CLI as an app resource. The public app does not require a private CLI package; enterprise distributors can provide and package their own implementation while retaining the normal Berd build and validation flow.
Public Agent Skills
Berd publishes portable Agent Skills under skills/. These
can be installed independently of the Berd app and are separate from the
contributor workflows under .agents/skills/ and the starter skills bundled
under distro/skills/.
The first published skill, buzz-handoff, brings
Buzz channel or thread context into a private agent conversation and can send an
explicitly approved reply through the public Buzz CLI.
Adding an experiment
Experiments are user-local preferences for unstable UI or workflow behavior.
Untouched experiments follow the global auto-enable setting, which defaults on
in dev builds and off in production builds. Use
.agents/skills/experimental-features/SKILL.md for the current workflow,
registry contract, storage rules, Tauri guardrails, and test coverage.
Participating
Berd is built by a small team at Block, in the open. You can read the source, build it, and fork it freely — but we don't accept pull requests from outside authorized repository collaborators, and outside PRs are closed automatically.
The way to participate is to open a well-formed issue. A bug report we can reproduce is worth more to us than a patch, because it's the part we can't do ourselves. CONTRIBUTING.md spells out exactly what each kind of issue needs; the issue forms require it.
Filing one? Hand this to your coding agent:
Read https://raw.githubusercontent.com/block/berd/main/CONTRIBUTING.md
and help me file a Berd issue. Interview me for anything the guide
requires that I haven't given you, and tell me if what I'm reporting
is actually two separate issues.
Please also review the Code of Conduct and Security Policy. Never report a security vulnerability as a public issue.
Useful commands
just check— Biome, design-system, i18n, contract, and type checksjust test— unit and component testsjust tauri-check— Rust type check with sidecars disabledjust clippy— Rust lint with warnings deniedjust bundle— stage the pinned Goose backend and runpnpm tauri build
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
.agents/skills/assistive-ux/SKILL.md2.8 KBupstream ↗
--- name: assistive-ux description: Use when adding, reviewing, designing, testing, or managing Assistive UX moments in Berd, including discover, suggest, and autoApply guidance, adaptive settings, behavior signals, retirement rules, or changes under src/shared/assistive-ux. --- # Assistive UX Use this skill for Berd product intelligence moments that teach, suggest, or adapt settings based on user behavior. Before changing code, read `docs/assistive-ux.md`. Treat that doc as the source of product intent and architecture. ## Core Rule Keep assistive state separate from user settings: ```text User settings answer: what should the product do? Assistive UX answers: what has the app shown, observed, accepted, retired, or applied? ``` Do not store guidance lifecycle state inside a feature setting. Do not use assistive state as the source of truth for product behavior. ## Types - `discover`: teaches that a control, setting, or capability exists. It should not change settings. - `suggest`: notices a repeated behavior and asks before changing a setting. - `autoApply`: changes a reversible local setting only after strong evidence, then explains the change and offers undo. Use `autoApply` conservatively. Never auto-apply changes involving secrets, credentials, permissions, destructive actions, provider setup, billing-like behavior, or hard-to-reverse choices. ## Implementation Workflow 1. Define or update the rule in `src/shared/assistive-ux/registry.ts`. 2. Keep lifecycle reads and writes in `src/shared/assistive-ux/runtime.ts` and `src/shared/assistive-ux/state.ts`. 3. Render the moment from the relevant feature surface. 4. Retire the moment when the user accepts it, dismisses it, sees it enough times, or manually changes the related setting. 5. If the moment changes a setting, call the setting's public setter and provide an undo path when the change is automatic. 6. Keep stored signals coarse. Do not store chat text, file paths, provider secrets, credentials, or message contents. ## UX Checklist Before shipping, confirm: - The moment appears close to the behavior it helps with. - The copy explains the next action without selling the feature. - The primary workflow still has visual priority. - The moment has a clear retirement path. - Repeated exposure is capped. - Manual setting changes stop or reset related guidance. - The behavior works in light and dark themes. ## Testing Add focused tests for: - fresh eligibility - shown-count updates - max-show expiration - acceptance or dismissal retirement - related setting-change retirement - invalid localStorage fallback - any feature surface that renders or applies the moment For broad behavior, add Playwright coverage only when the flow benefits from real app navigation or persistence across reloads.README.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/block-berd-agents-skills-assistive-ux.md