技能 Founder 规划
- 作者仓库星标 435
- 作者仓库 nvim
Founder Plan Skill
Routes founder-specific planning requests to the founder-plan-agent, enabling interactive forcing questions workflow for market sizing, competitive analysis, and GTM strategy planning.
Context Pointers
Reference (do not load eagerly):
- Path:
.claude/context/formats/subagent-return.md - Purpose: Return validation
- Load at: Subagent execution only
Note: This skill is a thin wrapper. Context is loaded by the delegated agent, not this skill.
Trigger Conditions
This skill activates when:
Direct Invocation
/plancommand on a task withlanguage: founder- Extension routing lookup finds
routing.plan.founder
Task-Type-Based Routing
- Task type is "founder"
/plan {N}where task {N} has language="founder"
When NOT to trigger
Do not invoke for:
- Tasks with other language types (general, meta, neovim, etc.)
- Quick mode operations (
--quickflag) - Tasks already in [PLANNED] or [COMPLETED] status
Execution
1. Input Validation
Validate inputs from delegation context:
task_number- Required, integerresearch_path- Optional, path to existing research reportssession_id- Required, string
# Validate task_number is present
if [ -z "$task_number" ]; then
return error "task_number is required"
fi
# Validate session_id is present
if [ -z "$session_id" ]; then
return error "session_id is required"
fi
2. Preflight Status Update
Update task status to "planning" in state.json:
jq --argjson num "$task_number" \
--arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
'(.active_projects[] | select(.project_number == $num)) += {
status: "planning",
last_updated: $ts
}' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
Update TODO.md status marker to [PLANNING].
3. Create Postflight Marker
Create marker file to signal postflight operations needed:
padded_num=$(printf "%03d" "$task_number")
project_name=$(jq -r --argjson num "$task_number" \
'.active_projects[] | select(.project_number == $num) | .project_name' \
specs/state.json)
task_dir="specs/${padded_num}_${project_name}"
mkdir -p "$task_dir"
cat > "$task_dir/.postflight-pending" << EOF
{
"session_id": "${session_id}",
"skill": "skill-founder-plan",
"task_number": ${task_number},
"operation": "plan",
"reason": "Postflight pending: status update, artifact linking, git commit",
"created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)"
}
EOF
4. Context Preparation
Extract task_type from state.json (null-safe):
# Extract task_type from state.json (null-safe)
task_type=$(jq -r --argjson num "$task_number" \
'.active_projects[] | select(.project_number == $num) | .task_type // null' \
specs/state.json)
Prepare delegation context for agent:
{
"task_context": {
"task_number": 234,
"project_name": "market_sizing_fintech_payments",
"description": "Market sizing: fintech payments",
"task_type": "founder",
"task_type": "market"
},
"research_path": "specs/234_market_sizing_fintech_payments/reports/01_context.md",
"metadata_file_path": "specs/234_market_sizing_fintech_payments/.return-meta.json",
"metadata": {
"session_id": "sess_{timestamp}_{random}",
"delegation_depth": 2,
"delegation_path": ["orchestrator", "plan", "skill-founder-plan"]
}
}
5. Invoke Agent
CRITICAL: You MUST use the Agent tool to spawn the agent.
Required Tool Invocation:
Tool: Agent (NOT Skill, NOT Plan)
Parameters:
- subagent_type: "founder-plan-agent"
- prompt: [Include task_context, research_path, metadata_file_path, metadata]
- description: "Create founder analysis plan with forcing questions"
The agent will:
- Load existing context (research reports if any)
- Conduct interactive forcing questions to gather data
- Generate plan artifact with gathered context stored
- Write metadata file for postflight consumption
- Return brief text summary
5b. Self-Execution Fallback
CRITICAL: If you performed the work above WITHOUT using the Agent tool (i.e., you read files,
wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a
.return-meta.json file now before proceeding to postflight. Use the schema from
return-metadata-file.md with the appropriate status value for this operation.
If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata.
Postflight (ALWAYS EXECUTE)
The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 5b). Do NOT skip these stages for any reason.
6. Read Metadata File
Read the metadata file:
metadata_file="specs/${padded_num}_${project_name}/.return-meta.json"
metadata=$(cat "$metadata_file")
status=$(echo "$metadata" | jq -r '.status')
7. Postflight Status Update
If agent succeeded (status == "planned"):
# Update state.json
jq --argjson num "$task_number" \
--arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
'(.active_projects[] | select(.project_number == $num)) += {
status: "planned",
last_updated: $ts
}' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
# Link artifact in state.json
plan_path=$(echo "$metadata" | jq -r '.artifacts[0].path')
plan_summary=$(echo "$metadata" | jq -r '.artifacts[0].summary')
jq --argjson num "$task_number" \
--arg path "$plan_path" \
--arg summary "$plan_summary" \
'(.active_projects[] | select(.project_number == $num)).artifacts += [{
type: "plan",
path: $path,
summary: $summary
}]' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
Update TODO.md status marker to [PLANNED] and link plan artifact per @.claude/context/patterns/artifact-linking-todo.md with field_name=**Plan**, next_field=**Description**.
8. Git Commit
git add -A
git commit -m "$(cat <<'EOF'
task {N}: create implementation plan
Session: {session_id}
EOF
)"
9. Cleanup and Return
Remove postflight markers and metadata:
rm -f "$task_dir/.postflight-pending"
rm -f "$task_dir/.postflight-loop-guard"
rm -f "$task_dir/.return-meta.json"
Return brief text summary to caller.
Return Format
Brief text summary (NOT JSON).
Expected successful return:
Founder plan created for task {N}:
- {questions_asked} forcing questions completed, {phase_count} phases planned
- Context gathered: {brief summary of key data points}
- Plan: specs/{NNN}_{SLUG}/plans/01_{short-slug}.md
- Status updated to [PLANNED]
- Changes committed with session {session_id}
- Next: Run /implement {N} to execute the plan and generate report
Error Handling
Session ID Missing
Return immediately with failed status.
Task Not Found
Return error with guidance to check task number.
Agent Errors
Pass through the agent's error return verbatim.
User Abandonment
Return partial status with progress made, keep status as "planning".
- 流狐分类
- 通用
- 作者声明 Agent
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 作者 / 版本 / 许可
- @benbrastmckie · 未声明 license
- 流狐 Token 估算
- 低消耗
- 流狐接入估算
- 需简单配置
- 是否需要外部 API Key
- 未发现要求
- 检测到的系统要求
- 未声明
- 底层运行要求
- 未声明
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 检测到的网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
作者没有在当前 SKILL.md 中定义固定输出样例。 Reference (do not load eagerly): Path: .claude/context/formats/subagent-return.md Purpose: Return validation
This skill activates when:
/plan command on a task with language: founder Extension routing lookup finds routing.plan.founder
Task type is "founder" /plan {N} where task {N} has language="founder"
Do not invoke for: Tasks with other language types (general, meta, neovim, etc.) Quick mode operations (--quick flag)
Execution
# Founder Plan Skill
Routes founder-specific planning requests to the `founder-plan-agent`, enabling interactive forcing questions workflow for market sizing, competitive analysis, and GTM strategy planning.
## Context Pointers
Reference (do not load eagerly):
- Path: `.claude/context/formats/subagent-return.md`
- Purpose: Return validation
- Load at: Subagent execution only
Note: This skill is a thin wrapper. Context is loaded by the delegated agent, not this skill.
## Trigger Conditions
This skill activates when:
### Direct Invocation
- `/plan` command on a task with `language: founder`
- Extension routing lookup finds `routing.plan.founder`
### Task-Type-Based Routing
- Task type is "founder"
- `/plan {N}` where task {N} has language="founder"
### When NOT to trigger
Do not invoke for:
- Tasks with other language types (general, meta, neovim, etc.)
- Quick mode operations (`--quick` flag)
- Tasks already in [PLANNED] or [COMPLETED] status
---
## Execution
### 1. Input Validation
Validate inputs from delegation context:
- `task_number` - Required, integer
- `research_path` - Optional, path to existing research reports
- `session_id` - Required, string
```bash
# Validate task_number is present
if [ -z "$task_number" ]; then
return error "task_number is required"
fi
# Validate session_id is present
if [ -z "$session_id" ]; then
return error "session_id is required"
fi
```
### 2. Preflight Status Update
Update task status to "planning" in state.json:
```bash
jq --argjson num "$task_number" \
--arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
'(.active_projects[] | select(.project_number == $num)) += {
status: "planning",
last_updated: $ts
}' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
```
… 作者原文负责流程事实;流狐只索引当前章节、要点、文件与命令。
章节 -> Context Pointers → Trigger Conditions → Direct Invocation → Task-Type-Based Routing → When NOT to trigger → Execution
要点 -> CRITICAL · Agent · Required Tool Invocation · Plan · Description
文件/命令 -> founder-plan-agent · .claude/context/formats/subagent-return.md · /plan · language: founder · routing.plan.founder · /plan {N} · --quick · tasknumber
内容 SHA-256 -> f88927c6dcda
原文结构
适用与边界
原文中的明确线索
founder-plan-agent、.claude/context/formats/subagent-return.md、/plan、language: founder、routing.plan.founder、/plan {N}、--quick、tasknumber