skill-strategy

Strategy Skill

Thin wrapper that routes GTM strategy research requests to the strategy-agent.

IMPORTANT: This skill implements the skill-internal postflight pattern. After the subagent returns, this skill handles all postflight operations (status update, artifact linking, git commit) before returning.

Context Pointers

Reference (do not load eagerly):

• Path: .opencode/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

• User explicitly runs /strategy command with task number
• User runs /research on a founder task with task_type: "strategy"

Implicit Invocation (during task implementation)

When an implementing agent encounters any of these patterns:

Plan step language patterns:

• "Develop GTM strategy"
• "Create go-to-market plan"
• "Define positioning"
• "Channel strategy"
• "Launch planning"

Target mentions:

• "go-to-market"
• "GTM strategy"
• "positioning statement"
• "launch plan"
• "channel prioritization"

When NOT to trigger

Do not invoke for:

• Market sizing (use skill-market)
• Competitive analysis (use skill-analyze)
• General business research (use skill-researcher)
• Product roadmap (not GTM)

---

Execution Flow

Stage 1: Input Validation

Validate required inputs:

• task_number - Must be provided and exist in state.json
• topic - Optional, string context hint
• mode - Optional, one of: LAUNCH, SCALE, PIVOT, EXPAND

# Lookup task
task_data=$(jq -r --argjson num "$task_number" \
  '.active_projects[] | select(.project_number == $num)' \
  specs/state.json)

# Validate exists
if [ -z "$task_data" ]; then
  return error "Task $task_number not found"
fi

# Extract fields
task_type=$(echo "$task_data" | jq -r '.task_type // "founder"')
status=$(echo "$task_data" | jq -r '.status')
project_name=$(echo "$task_data" | jq -r '.project_name')
description=$(echo "$task_data" | jq -r '.description // ""')

# Extract pre-gathered forcing_data (if present)
forcing_data=$(echo "$task_data" | jq -r '.forcing_data // null')
pre_gathered_mode=$(echo "$forcing_data" | jq -r '.mode // null' 2>/dev/null)

# Validate mode if provided
if [ -n "$mode" ]; then
  case "$mode" in
    LAUNCH|SCALE|PIVOT|EXPAND) ;;
    *) return error "Invalid mode: $mode. Must be LAUNCH, SCALE, PIVOT, or EXPAND" ;;
  esac
fi

---

Stage 2: Preflight Status Update

Update task status to "researching" BEFORE invoking subagent.

Update state.json:

jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
   --arg status "researching" \
   --arg sid "$session_id" \
  '(.active_projects[] | select(.project_number == '$task_number')) |= . + {
    status: $status,
    last_updated: $ts,
    session_id: $sid
  }' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json

Update TODO.md: Use Edit tool to change status marker to [RESEARCHING].

---

Stage 3: Create Postflight Marker

padded_num=$(printf "%03d" "$task_number")
mkdir -p "specs/${padded_num}_${project_name}"

cat > "specs/${padded_num}_${project_name}/.postflight-pending" << EOF
{
  "session_id": "${session_id}",
  "skill": "skill-strategy",
  "task_number": ${task_number},
  "operation": "research",
  "reason": "Postflight pending: status update, artifact linking, git commit",
  "created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)"
}
EOF

---

Stage 4: Prepare Delegation Context

Include pre-gathered forcing_data when available:

{
  "task_context": {
    "task_number": N,
    "project_name": "{project_name}",
    "description": "{description}",
    "task_type": "founder",
    "task_type": "strategy"
  },
  "forcing_data": {
    "mode": "{pre_gathered_mode}",
    "target_customer": "{pre_gathered_target}",
    "value_prop": "{pre_gathered_value_prop}",
    "differentiator": "{pre_gathered_differentiator}",
    "channel_hypothesis": "{pre_gathered_channel}",
    "launch_context": "{pre_gathered_launch}",
    "gathered_at": "{timestamp}"
  },
  "topic": "optional context hint",
  "mode": "LAUNCH|SCALE|PIVOT|EXPAND or use forcing_data.mode",
  "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json",
  "metadata": {
    "session_id": "sess_{timestamp}_{random}",
    "delegation_depth": 1,
    "delegation_path": ["orchestrator", "strategy", "skill-strategy"]
  }
}

Note: If forcing_data is present from STAGE 0 of /strategy command, pass it to the agent. The agent will use pre-gathered data and only ask follow-up questions for missing details.

---

Stage 5: Invoke Agent

CRITICAL: You MUST use the Task tool to spawn the agent.

Required Tool Invocation:

Tool: Task (NOT Skill)
Parameters:
  - subagent_type: "strategy-agent"
  - prompt: [Include task_context, forcing_data, topic, mode, metadata_file_path, metadata]
  - description: "GTM strategy research with positioning and channels"

The agent will:

• Use pre-gathered forcing_data if available (skip already-answered questions)
• Present mode selection only if not pre-selected
• Use forcing questions for positioning context (building on pre-gathered data)
• Gather channel data with evidence
• Collect launch timing and metrics data
• Create research report at specs/{NNN}_{SLUG}/reports/
• Write metadata file
• Return brief text summary

---

Stage 5b: Self-Execution Fallback

CRITICAL: If you performed the work above WITHOUT using the Task 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 Task 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.

Stage 6: Read Metadata File

padded_num=$(printf "%03d" "$task_number")
metadata_file="specs/${padded_num}_${project_name}/.return-meta.json"

if [ -f "$metadata_file" ] && jq empty "$metadata_file" 2>/dev/null; then
    status=$(jq -r '.status' "$metadata_file")
    artifact_path=$(jq -r '.artifacts[0].path // ""' "$metadata_file")
    artifact_type=$(jq -r '.artifacts[0].type // ""' "$metadata_file")
    artifact_summary=$(jq -r '.artifacts[0].summary // ""' "$metadata_file")
else
    status="failed"
fi

---

Stage 7: Update Task Status (Postflight)

If status is "researched", update state.json and TODO.md.

Update state.json:

jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
   --arg status "researched" \
  '(.active_projects[] | select(.project_number == '$task_number')) |= . + {
    status: $status,
    last_updated: $ts
  }' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json

Update TODO.md: Use Edit tool to change status marker to [RESEARCHED].

---

Stage 8: Link Artifacts

Add artifact to state.json with summary.

IMPORTANT: Use two-step jq pattern to avoid escaping issues.

if [ -n "$artifact_path" ]; then
    # Step 1: Filter out existing research artifacts (use "| not" pattern)
    jq '(.active_projects[] | select(.project_number == '$task_number')).artifacts =
        [(.active_projects[] | select(.project_number == '$task_number')).artifacts // [] | .[] | select(.type == "research" | not)]' \
      specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json

    # Step 2: Add new research artifact
    jq --arg path "$artifact_path" \
       --arg type "$artifact_type" \
       --arg summary "$artifact_summary" \
      '(.active_projects[] | select(.project_number == '$task_number')).artifacts += [{"path": $path, "type": $type, "summary": $summary}]' \
      specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
fi

Update TODO.md: Link artifact using count-aware format.

Apply the four-case Edit logic from @.opencode/context/patterns/artifact-linking-todo.md with field_name=**Research**, next_field=**Plan**.

---

Stage 9: Git Commit

git add -A
git commit -m "task ${task_number}: complete research

Session: ${session_id}

---

Stage 10: Cleanup

rm -f "specs/${padded_num}_${project_name}/.postflight-pending"
rm -f "specs/${padded_num}_${project_name}/.postflight-loop-guard"
rm -f "specs/${padded_num}_${project_name}/.return-meta.json"

---

Stage 11: Return Brief Summary

GTM strategy research completed for task {N}:
- Mode: {mode}, {questions_asked} forcing questions completed
- Target: {brief target customer}
- Key benefit: {brief benefit}
- Top channels: {list}
- Launch recommendation: {type}
- Pre-gathered data used: {yes/no}
- Research report: specs/{NNN}_{SLUG}/reports/01_{short-slug}.md
- Status updated to [RESEARCHED]
- Changes committed
- Next: Run /plan {N} to create implementation plan

---

Return Format

Brief text summary (NOT JSON).

Expected successful return:

GTM strategy research completed for task 234:
- Mode: LAUNCH, 10 forcing questions completed
- Target: VP Engineering at Series A-C SaaS, 50-200 employees
- Key benefit: Cut deploy time by 80%
- Top channels: Hacker News, DevOps meetups, Twitter
- Launch recommendation: Beta (2K waitlist with 40% engagement)
- Pre-gathered data used: yes (5 questions from STAGE 0)
- Research report: specs/234_gtm_strategy_b2b_saas/reports/01_gtm-strategy.md
- Status updated to [RESEARCHED]
- Changes committed with session sess_1736700000_abc123
- Next: Run /plan 234 to create implementation plan

---

Error Handling

Input Validation Errors

Return immediately if task not found.

Metadata File Missing

Keep status as "researching" for resume.

User Abandonment

Return partial status with progress made.

Git Commit Failure

Non-blocking: Log failure but continue.