Index of every page on this site: llms.txt
All skills
block avatar

/berd-help

@77422a9
by Block Open Sourceblock/berd1.1k stars
137
Run it yourself

Help with Berd the desktop app: how-to, troubleshooting, settings, agents, skills, automations, projects, sessions, providers, connections, feedback, or berdctl. Use for app questions, not harness-specific behavior.

  • 11 files
  • 20.4 KB
  • Updated 3 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/block/berd/berd-help

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈57 tokens for metadata: the name and description. ≈1.3k when used: this file. ≈3.9k more on demand in 10 files.

Description uses 2.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈227 characters, or 2.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Berd help

Use this skill to help users operate, troubleshoot, and script Berd — the desktop app — from a normal chat. Topics below point to references/ files; read the one relevant to the user's question rather than guessing, and read more than one if the question spans topics.

First Principles

  • Before giving exact product instructions, try to verify the behavior from available evidence. If source code is available, inspect it first. If source code is not available, use visible app state, screenshots, error messages, Doctor output, or berdctl --help output.
  • Do not invent UI paths, menu names, frontmatter fields, feature existence, fallback workflows, or berdctl commands/flags. If you cannot verify the exact path, say that and ask for a screenshot, selected project/source access, or the specific screen the user is on. For berdctl, verify against --help rather than recalling flags from memory.
  • Treat the current app behavior as the source of truth. Prefer evidence from visible UI, runtime state, error messages, Doctor output, local files, berdctl --help, and available source over memory or stale documentation.
  • Give practical steps the user can try now. Keep the answer short unless the problem needs a deeper diagnosis.
  • Do not claim access to private GitHub source unless it is actually available in the current environment.
  • Berd changes fast. Prefer naming where to look (a file, a command's --help, a visible settings section) over naming specific section names, labels, flags, or IDs in this skill's own prose — those are exactly the details most likely to move. When a reference file below does name something specific, treat it as a hint of where to look, not a guarantee it still matches current behavior; verify before repeating it to the user.

Scope

This skill is about Berd the app — not about any one harness running inside a session (goose, claude-acp, codex-acp, copilot-acp, amp-acp, cursor-agent). A question about the app around the harness (where a setting lives, how a session started, how to export a chat, how to file a Berd bug) is in scope. A question about a specific harness's own behavior, output, or errors is not — treat that as harness-specific and say so rather than guessing at harness internals.

What To Check

For how-to questions:

  • Identify the feature area from the Topics list below and read that reference file.
  • If source is available, search for the feature's UI, command, hook, tests, or i18n strings before answering.
  • Use the app's current state when available: selected agent, project, model, provider, active session, attached files, visible errors, or screenshots.
  • Explain the shortest path to the action, then mention important constraints or gotchas. If a berdctl command does the same thing faster or more reliably than a click path, offer it — see references/berdctl.md.

For troubleshooting:

  • Ask for the exact error, screenshot, provider/model, project path, or Doctor result when the symptoms are ambiguous.
  • Suggest low-risk checks first: rerun, reconnect, verify settings, check selected model/provider, restart the app, or run Doctor when relevant.
  • Separate likely causes from confirmed causes.
  • If the problem looks like a real app bug rather than user error, see references/reporting-problems.md instead of guessing at a fix.

Topics

Read the matching reference file for a specific question. Read more than one when a question spans topics (for example, an automation failure that might be a provider problem needs both):

  • references/berdctl.md — the berdctl CLI, when to prefer it over UI steps
  • references/agents.md — agents/personas
  • references/skills.md — skills, source kinds, precedence
  • references/automations.md — automations
  • references/projects.md — projects and workspaces
  • references/sessions.md — sessions ("chat"), the right rail, files, worktrees, terminal
  • references/ai-providers.md — provider connections and error causes
  • references/connections-and-extensions.md — connections vs. extensions
  • references/settings.md — settings structure and gotchas
  • references/reporting-problems.md — filing feedback or a bug

Working With Bundled Builder Skills

  • If the user wants to create, edit, or inspect an agent/persona, use or recommend the agent-builder skill.
  • If the user wants to create, edit, or inspect a reusable skill, use or recommend the skill-builder skill.
  • Do not duplicate those workflows inside this skill or its references. This skill helps users understand, troubleshoot, and drive the app around them.

Source Of Truth

When source code is available, use it to verify behavior — the reference files above may lag actual behavior since Berd changes fast. Good places to inspect include UI feature folders, Tauri commands, distro bundled skills, settings views, berdctl command modules (src/features/berdctl/commands/impl/), and tests. If source code is not available, rely on current app context and --help output, and be transparent about uncertainty.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 77422a9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 3 months ago
metadata
{
  "berdBundled": true
}

README badge

README badge for block/berd/berd-help