Claude Skill

craft-prompt

Advanced surface, separate from Foreman's core roadmap job — a standalone prompt builder for work that has no roadmap entry behind it. Guides you through assembling a self-contained spawned-session prompt following Foreman's template — asks which optional sections to include, gat

LLM Mart · 0 points · 10 views 63 listing impressions 0 install-command copies
Download V-Songbird-foreman-skills_craft-prompt-aae700b.zip · 35 KB

Install

skills CLI npx skills add https://github.com/V-Songbird/foreman/tree/main/skills/craft-prompt
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install v-songbird-foreman@llmmart
Git git clone https://github.com/V-Songbird/foreman.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole v-songbird/foreman collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

foreman:craft-prompt — interactive prompt builder

Foreman runs in Claude Code, Codex and Antigravity. Every step applies to every host unless it names one. Read the shared runtime first: it covers plugin paths, JSON payloads, questions and authorization for every host.

Advanced tool, separate from Foreman's core job. An ordinary implementation request does not call for a prompt-crafting interview: it goes through the foreman entrance, which builds its own handoff out of the roadmap entry. This skill is for the case with no roadmap entry behind it: a standalone prompt, asked for explicitly. Write for a destination with no memory of this conversation — every field must be filled so it can act cold.

Ask each call's questions together — AskUserQuestion in Claude Code; in Codex, the picker in questions.md, within its limits. With no usable question tool, ask one self-contained plain-text question. Ask directly: never say Foreman requires the question or cite a skill as the reason. Text supplied with the request (in Claude Code, the skill's args) seeds the task description; skip a question only when the user's own words already answer it.

Each step below lives in its own file beside this one. Read it when the interview reaches that step and follow it; a step this file skips is never read.


Call 1 — task type, optional sections, starting point, and flavor

Read call-1.md (${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/call-1.md) and follow it.


Ground the file options (one read-only pass, before Call 2)

Read ground-files.md (${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/ground-files.md) and follow it.


Call 2 — required fields (batch all 4)

Read call-2.md (${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/call-2.md) and follow it.


Call 3 — verification (conditional)

Skip this call only if the task type is pure research/investigation with no code changes.

Otherwise read call-3.md (${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/call-3.md) and follow it.


Call 4-N — optional section details

When Call 1 Q2 selected any optional section, or Call 1 Q4 answered Yes, read call-4.md (${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/call-4.md) and follow it.


When an answer is "I don't know"

When any answer comes back as a don't-know, or Call 2 Q3 comes back as I can only name the area or names no file, read dont-know.md (${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/dont-know.md) and follow it.


Resolve the named files (craft-time, once)

Read resolve-files.md (${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/resolve-files.md) and follow it.


Call 5 — how to run it

Honor a destination the user already stated. Otherwise read destination-question.md (${CLAUDE_PLUGIN_ROOT}/skills/roadmap/destination-question.md) now and do exactly what it says. Call 3 already gathered the verification, so the count is known here — it never removes an option, it decides which one carries a caution. Foreman never asks which model runs the work and never sets one: a background agent inherits this session's model, and a pasted prompt runs wherever the user pastes it.


Assemble the handoff — one call to craft-handoff.js

Read assemble.md (${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/assemble.md) and follow it.


Deliver

Read deliver.md (${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/deliver.md) and follow it.

Files (foreman)
  • agents
    • openai.yaml 275 B
      Loading…
  • assets
    • icon.png 21.1 KB · in bundle
    • icon.svg 511 B · in bundle
  • assemble.md 6.1 KB
    Loading…
  • call-1.md 3.9 KB
    Loading…
  • call-2.md 2.2 KB
    Loading…
  • call-3.md 3.2 KB
    Loading…
  • call-4.md 2.9 KB
    Loading…
  • deliver.md 1002 B
    Loading…
  • dont-know.md 1.3 KB
    Loading…
  • ground-files.md 2.2 KB
    Loading…
  • resolve-files.md 1.4 KB
    Loading…
  • SKILL.md 4.3 KB
    ---
    name: craft-prompt
    description: "Advanced surface, separate from Foreman's core roadmap job: builds or refines a self-contained prompt for a fresh session, in Foreman's template, for work with no roadmap entry behind it. Use on an explicit prompt-crafting request."
    when_to_use: "Trigger only on an explicit request to build or refine a standalone prompt: \"craft a prompt\", \"build a prompt\", \"write me a prompt\", \"refine this prompt\", \"foreman prompt\", or /foreman:craft-prompt. Wanting work built, tracked or handed to a background Agent is roadmap work for the `foreman` entrance."
    argument-hint: "<task description — optional seed>"
    allowed-tools: AskUserQuestion, TaskCreate, TaskUpdate, Agent, Read, Write, Bash, PowerShell
    ---
    
    # foreman:craft-prompt — interactive prompt builder
    
    Foreman runs in Claude Code, Codex and Antigravity. Every step applies to every host unless it names one. Read [the shared runtime](../foreman/runtime.md) first: it covers plugin paths, JSON payloads, questions and authorization for every host.
    
    Advanced tool, separate from Foreman's core job. An ordinary
    implementation request does not call for a prompt-crafting interview: it
    goes through [the `foreman` entrance](../foreman/SKILL.md), which builds
    its own handoff out of the roadmap entry. This skill is for the case with
    no roadmap entry behind it: a standalone prompt, asked for explicitly.
    Write for a destination with no memory of this conversation — every field
    must be filled so it can act cold.
    
    Ask each call's questions together — `AskUserQuestion` in Claude Code; in
    Codex, the picker in [questions.md](../foreman/questions.md), within its
    limits. With no usable question tool, ask one self-contained plain-text
    question. Ask directly: never say Foreman requires the question or cite a
    skill as the reason. Text supplied with the request (in Claude Code, the
    skill's args) seeds the task description; skip a question only when the
    user's own words already answer it.
    
    Each step below lives in its own file beside this one. Read it when the
    interview reaches that step and follow it; a step this file skips is never
    read.
    
    ---
    
    ## Call 1 — task type, optional sections, starting point, and flavor
    
    Read [call-1.md](call-1.md) (`${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/call-1.md`) and follow it.
    
    ---
    
    ## Ground the file options (one read-only pass, before Call 2)
    
    Read [ground-files.md](ground-files.md) (`${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/ground-files.md`) and follow it.
    
    ---
    
    ## Call 2 — required fields (batch all 4)
    
    Read [call-2.md](call-2.md) (`${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/call-2.md`) and follow it.
    
    ---
    
    ## Call 3 — verification (conditional)
    
    Skip this call only if the task type is pure research/investigation with no code changes.
    
    Otherwise read [call-3.md](call-3.md) (`${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/call-3.md`) and follow it.
    
    ---
    
    ## Call 4-N — optional section details
    
    When Call 1 Q2 selected any optional section, or Call 1 Q4 answered `Yes`,
    read [call-4.md](call-4.md) (`${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/call-4.md`) and follow it.
    
    ---
    
    ## When an answer is "I don't know"
    
    When any answer comes back as a don't-know, or Call 2 Q3 comes back as
    `I can only name the area` or names no file, read [dont-know.md](dont-know.md) (`${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/dont-know.md`) and follow it.
    
    ---
    
    ## Resolve the named files (craft-time, once)
    
    Read [resolve-files.md](resolve-files.md) (`${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/resolve-files.md`) and follow it.
    
    ---
    
    ## Call 5 — how to run it
    
    Honor a destination the user already stated. Otherwise read
    [destination-question.md](../roadmap/destination-question.md)
    (`${CLAUDE_PLUGIN_ROOT}/skills/roadmap/destination-question.md`) now and
    do exactly what it says. Call 3 already gathered the verification, so the
    count is known here — it never removes an option, it decides which one
    carries a caution. Foreman never asks which model runs the work and never
    sets one: a background agent inherits this session's model, and a pasted
    prompt runs wherever the user pastes it.
    
    ---
    
    ## Assemble the handoff — one call to craft-handoff.js
    
    Read [assemble.md](assemble.md) (`${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/assemble.md`) and follow it.
    
    ---
    
    ## Deliver
    
    Read [deliver.md](deliver.md) (`${CLAUDE_PLUGIN_ROOT}/skills/craft-prompt/deliver.md`) and follow it.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.