first-ask
Interactive task-refinement workflow that clarifies scope, deliverables, and constraints before carrying out the task.
Skill by MarieLynneBlock
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/marielynneblock-first-ask
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
Use cases: productivity
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/first-ask
What's inside
- Skill name
first-ask- Description
- Interactive task-refinement workflow that clarifies scope, deliverables, and constraints before carrying out the task. Uses Joyride input tools when available.
- License
- unknown
- Metadata
- skill-author: Marie-Lynne Block
- Instructions
- 32 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from MarieLynneBlock/arcanum-artifex
- 0.564score
markdown-link-auditor
MarieLynneBlock
Audit Markdown links, images, and local anchors for broken relative references.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
asset-frontmatter-check
MarieLynneBlock
Validate YAML frontmatter of Copilot customisation assets in this lab (SKILL.md, WORKFLOW.md, *.agent.md, *.instructions.md, *.prompt.md).
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
asset-self-containment-check
MarieLynneBlock
Check that a Copilot customisation asset (skill, workflow, agent, instruction, or prompt folder) stays standalone and copyable, with no runtime dependency on…
SkillBFreshness: B★ 4Claude Code +9 - 0.524score
eval-driven-dev
MarieLynneBlock
Build an automated evaluation pipeline that tests a Python LLM application end-to-end with pixie test — real code paths, real LLM calls, instrumented external…
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
noob-mode
MarieLynneBlock
Plain-English response style for non-technical Copilot CLI users.
SkillCFreshness: C★ 4Claude Code +9 - 0.514score
mcp-cli
MarieLynneBlock
Interface for MCP (Model Context Protocol) servers via CLI.
SkillCFreshness: C★ 4Claude Code +9 - 0.514score
agentic-eval
MarieLynneBlock
Use when designing and implementing evaluation loops for AI agents, including reflection, evaluator-optimiser patterns, rubric scoring, LLM-as-judge review…
SkillCFreshness: C★ 4Claude Code +9 - 0.514score
ai-ready
MarieLynneBlock
Guide users to review and install the external ai-ready skill from its upstream repository.
SkillCFreshness: C★ 4Claude Code +9 - 0.514score
foundry-agent-sync
MarieLynneBlock
Create and synchronise prompt-based AI agents directly within Azure AI Foundry via REST API, from a local JSON manifest.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
agent-owasp-compliance
MarieLynneBlock
Assess tool-using and multi-agent AI systems against OWASP ASI-style controls, mapping evidence to prompt injection, tool governance, agency, escalation…
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
agent-supply-chain
MarieLynneBlock
Review, generate, and verify supply-chain integrity controls for AI agent tools, plugins, MCP servers, skills, prompts, and custom agents, including SHA-256…
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
generate-custom-instructions-from-codebase
MarieLynneBlock
Generate GitHub Copilot migration instructions by comparing two project versions and extracting conventions for framework upgrades, refactoring, dependency…
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 10, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from MarieLynneBlock
- 0.564score
asset-frontmatter-check
MarieLynneBlock
Validate YAML frontmatter of Copilot customisation assets in this lab (SKILL.md, WORKFLOW.md, *.agent.md, *.instructions.md, *.prompt.md).
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
markdown-link-auditor
MarieLynneBlock
Audit Markdown links, images, and local anchors for broken relative references.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
asset-self-containment-check
MarieLynneBlock
Check that a Copilot customisation asset (skill, workflow, agent, instruction, or prompt folder) stays standalone and copyable, with no runtime dependency on…
SkillBFreshness: B★ 4Claude Code +9 - 0.524score
eval-driven-dev
MarieLynneBlock
Build an automated evaluation pipeline that tests a Python LLM application end-to-end with pixie test — real code paths, real LLM calls, instrumented external…
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
noob-mode
MarieLynneBlock
Plain-English response style for non-technical Copilot CLI users.
SkillCFreshness: C★ 4Claude Code +9 - 0.514score
agentic-eval
MarieLynneBlock
Use when designing and implementing evaluation loops for AI agents, including reflection, evaluator-optimiser patterns, rubric scoring, LLM-as-judge review…
SkillCFreshness: C★ 4Claude Code +9
Cite this page
first-ask skill. Agent Mart. https://agentmart.dev/skills/marielynneblock-first-ask (last updated 2026-10-24)