demo
Record a demo of a feature working — video, GIF, or annotated terminal transcript — using the repo's verification skill.
Skill by baranbingol1
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/baranbingol1-demo
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/demo
What's inside
- Skill name
demo- Description
- Record a demo of a feature working — video, GIF, or annotated terminal transcript — using the repo's verification skill. Use when the user says show me it working, make a demo, or record this, and after landing a feature the user asked to see.
- License
- MIT
- Instructions
- 30 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# demo
Produce a watchable proof: drive a real feature on the real app and record it. A demo is
[prove-it-works](../prove-it-works/SKILL.md) made visible — the recording exercises the
actual user path, never a staged or mocked one.
## Process
1. **Reuse the verify machinery.** The repo's `verify-<app>` skill (from
[verify-setup](../verify-setup/SKILL.md)) owns Launch, Doctor, and Drive; a demo is a
Drive with recording on. No verify skill in the repo: offer to run verify-setup
first — it's the same work minus the recording, and the repo keeps the skill.
2. **Pick the recording medium by surface:**
- Web/desktop UI: screen or tab recording via the browser/driver tooling (video or
GIF). Capture the interaction, not a slideshow of end states.
- CLI/TUI: a terminal recording or transcript with the invocations and their real
output, trimmed to the signal.
- API/service: a narrated request/response sequence — the commands run and the
actual responses, plus the observable side effect (row inserted, file written).
3. **Script the walkthrough before recording:** the feature's map file (features/) names
the entry path and the observable end state; the demo follows the map, start to
proven end state, including the side-effect check. One take that shows the whole
path beats three fragments.
4. **Run it**: doctor first, drive with recording on, stop at the proven end state,
cleanup per the verify skill — the recording is evidence and survives cleanup, saved
to a named location.
5. **Deliver**: hand over the file with one line per step of what it shows. Working a
bd ticket: attach the demo location to the ticket's evidence note.From baranbingol1/bbstack, MIT.
More from baranbingol1/bbstack
- 0.529score
implement
baranbingol1
Implement a piece of work from a spec, bd ticket, or direct request.
SkillBFreshness: BClaude Code +9 - 0.524score
diagnose
baranbingol1
Diagnosis loop for bugs and performance regressions.
SkillBFreshness: BClaude Code +9 - 0.521score
autoresearch
baranbingol1
Autonomous experiment loop that optimizes one measurable metric: try an idea, measure, keep wins, revert losses, repeat until a stop predicate is met.
SkillBFreshness: BClaude Code +9 - 0.521score
lazy-ladder
baranbingol1
Apply when implementing anything: writing, adding, refactoring, or fixing code, and when choosing libraries or dependencies.
SkillBFreshness: BClaude Code +9 - 0.518score
bb
baranbingol1
Route a request to the right bbstack skill — the one name to remember.
SkillBFreshness: BClaude Code +9 - 0.518score
eval
baranbingol1
Blind-test how a skill or prompt change affects agent behavior before promoting it.
SkillBFreshness: BClaude Code +9 - 0.516score
guard-the-context-window
baranbingol1
Apply during long-running work — implementation runs, orchestration, wiki generation, verification sweeps — when context is filling up: large outputs, long…
SkillBFreshness: BClaude Code +9 - 0.499score
domain-modeling
baranbingol1
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9 - 0.499score
grilling
baranbingol1
Grill the user relentlessly about a plan, decision, or idea.
SkillBFreshness: BClaude Code +9 - 0.498score
explain-diff-html
baranbingol1
Use when the user asks for a rich explanation of a code change, diff, branch, or PR.
SkillBFreshness: BClaude Code +9 - 0.496score
encode-lessons-in-structure
baranbingol1
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.
SkillBFreshness: BClaude Code +9 - 0.496score
boundary-discipline
baranbingol1
Apply when wiring validation, error handling, or framework adapters.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 28, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/baranbingol1/bbstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from baranbingol1
- 0.529score
implement
baranbingol1
Implement a piece of work from a spec, bd ticket, or direct request.
SkillBFreshness: BClaude Code +9 - 0.524score
diagnose
baranbingol1
Diagnosis loop for bugs and performance regressions.
SkillBFreshness: BClaude Code +9 - 0.521score
autoresearch
baranbingol1
Autonomous experiment loop that optimizes one measurable metric: try an idea, measure, keep wins, revert losses, repeat until a stop predicate is met.
SkillBFreshness: BClaude Code +9 - 0.521score
lazy-ladder
baranbingol1
Apply when implementing anything: writing, adding, refactoring, or fixing code, and when choosing libraries or dependencies.
SkillBFreshness: BClaude Code +9 - 0.518score
bb
baranbingol1
Route a request to the right bbstack skill — the one name to remember.
SkillBFreshness: BClaude Code +9 - 0.518score
eval
baranbingol1
Blind-test how a skill or prompt change affects agent behavior before promoting it.
SkillBFreshness: BClaude Code +9
Cite this page
demo skill. Agent Mart. https://agentmart.dev/skills/baranbingol1-demo (last updated 2026-10-24)