specai-grill-me
Interview the user to resolve feature and architecture decisions before planning.
Skill by ArceApps-dev
Chalk Labs
Need help deploying specai-grill-me?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/arceapps-dev-specai-grill-me
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/specai-grill-me
What's inside
- Skill name
specai-grill-me- Description
- Interview the user to resolve feature and architecture decisions before planning.
- License
- MIT
- Instructions
- 32 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Grill-me ## Required Skills - `specai-bootstrap` Ground the request in the repository, then ask one design question at a time until no relevant design, implementation, or technology choice remains unresolved. Do not leave grill-me with an open decision that could change scope, behavior, architecture, or technology. ### Gate G1 Before exit, record grounding evidence and settle all relevant decisions; do not exit with an open decision. ## Ground first Identify domain terms, inspect relevant code/configuration/APIs, and record the searched terms, inspected sources, and facts. Before asking anything, check whether the repository can answer it. If repository inspection is unavailable, report the blocker; do not guess. ## Interview - Ask exactly one unresolved user decision per turn, with only the repository facts needed for context. - Keep business behavior, data/state, integrations, security, UX, constraints, and edge cases in view. - Probe vague answers and explain material trade-offs. Do not ask about facts the codebase establishes. - Business and product decisions belong here; technical details already settled by the approved design do not. Before each turn, make sure it contains one decision question. When none remain, stop asking and return a concise record of agreed behavior, decisions, constraints, and remaining non-decision notes. Do not start planning until all relevant choices are resolved. ### Gate G2 — Response check Each response that asks the user a question must contain exactly one focused, unresolved decision question. When none remain, ask no question and return the concise decision record. Do not generate code during the interview. Load domain modeling only when a domain term or durable architectural trade-off needs recording; use the PRD/planning skills for their phases.
From ArceApps-dev/specai, MIT.
More from ArceApps-dev/specai
- 0.528score
specai-bootstrap
ArceApps SpecAI
Use when establishing SpecAI skill discovery, language, and shared workflow contracts.
SkillBFreshness: BClaude Code +9 - 0.524score
specai-anti-bloat
ArceApps SpecAI
Use when reviewing a diff for overengineering, auditing repository complexity, or listing // td: debt; also handles /specai-review, /specai-audit, and…
SkillBFreshness: BClaude Code +9 - 0.524score
specai-adr
ArceApps SpecAI
Use when una decisión arquitectónica duradera y transversal requiere conservar su rationale sin duplicar la especificación normativa.
SkillBFreshness: BClaude Code +9 - 0.521score
specai-judgment-day
ArceApps SpecAI
Use before creating a PR when adversarial dual-blind review is needed.
SkillBFreshness: BClaude Code +9 - 0.521score
specai-backlog
ArceApps SpecAI
Use cuando el usuario invoque /specai-backlog, consulte planes pendientes o seleccione una feature del backlog para decidir si implementarla.
SkillBFreshness: BClaude Code +9 - 0.519score
specai-finishing-a-development-branch
ArceApps SpecAI
Use when finishing an accepted SpecAI feature through /specai-finish after global verification and recorded user acceptance.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-living-documents
ArceApps SpecAI
Keep the six feature documents concise and current during implementation.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-agent-clarification
ArceApps-dev
Surface unresolved technical constraints during grounded design clarification.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-antigravity-bridge
ArceApps SpecAI
Use when Antigravity's plan mode would create a second plan alongside an active SpecAI feature.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-dispatching-parallel-agents
ArceApps SpecAI
Use when at least two independent tasks may run concurrently.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-documentation
ArceApps SpecAI
Use when creating or updating concise feature or project documentation.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-iteration
ArceApps SpecAI
Use when the user reports an issue or requests a change after implementation or acceptance.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 22, 2026 (1 month ago)
- Last release
- Aug 10, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ArceApps-dev/specai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ArceApps-dev
- 0.518score
specai-agent-clarification
ArceApps-dev
Surface unresolved technical constraints during grounded design clarification.
SkillBFreshness: BClaude Code +9 - 0.513score
specai-assumptions-consolidation
ArceApps-dev
Summarize design agreements and traceable technical assumptions before planning.
SkillBFreshness: BClaude Code +9 - 0.513score
specai-improve-codebase-architecture
ArceApps-dev
Audit architectural friction and produce a concise visual report.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get specai-grill-me running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
specai-grill-me skill. Agent Mart. https://agentmart.dev/skills/arceapps-dev-specai-grill-me (last updated 2026-10-24)