strategy-pipeline
Phase 11 procedure — capabilities → set_strategy_inputs → plan → apply → approve, plus 3-path blocker resolution (ask / build / defer).
Skill by petr-royce
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/elophanto-strategy-pipeline
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: data
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/strategy-pipeline
What's inside
- Skill name
strategy-pipeline- Description
- Phase 11 procedure — capabilities → set_strategy_inputs → plan → apply → approve, plus 3-path blocker resolution (ask / build / defer). Covers WHOLE business surface via injected OPERATIONAL CONTEXT, not just what_we_sell.
- License
- MIT
- Metadata
- phase: 11 · author: petr-royce · version: 1.1.0
- Instructions
- 95 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Strategy pipeline (Phase 11)
Called by [[drive-business]] PATH B, or directly when the operator asks to plan an existing productized company.
## Triggers
- company_plan
- company_capabilities
- company_plan_apply
- set up strategy
- capability audit
- 30 day plan
- marketing plan
- blockers
- strategy inputs
## Pipeline (5 tools, in order)
### 1. `company_capabilities(<slug>)`
Audit vault + tools + skills. Writes `capabilities.md`. Returns structured map.
### 2. Research, propose recommendations, then capture inputs
Do NOT ask the operator blank questions. The agent has the research tools to ground every field. Operator's job is approve / modify / override, not fill blanks.
**Research first** (parallel where possible):
- `browser_navigate(<url>)` + `browser_extract` (homepage, /about, /pricing, /hire, /faq)
- `web_search('<domain> competitors')` and `web_search('<industry> alternatives 2026')`
- `company_report(<slug>)` — ledger gaps, pipeline state
- `file_read companies/<slug>/company.yaml` — declared channels, KPIs
**Propose each field with one-line rationale** in chat as a table:
| Field | Recommended | Rationale |
|---|---|---|
| `target_audience` | <derived from homepage + /hire positioning> | <evidence> |
| `competitors` | <3-5 from web_search> | <industry/category> |
| `current_challenges` | <from ledger gaps + funnel friction> | <evidence> |
| `unique_selling_points` | <from homepage value props> | <what only this does> |
| `primary_goals` | <3-5 from list below> | <inferred from product type> |
| `strategy_mode` | <one of: standard / unconventional / guerrilla / brand-awareness / controversial> | <from brand tone> |
| `focus` | <full / seo / geo / content / paid / social / email / brand> | <from active channels> |
| `budget_type` + `_amount` + `_period` | suggest `organic / 0 / monthly` if no signal | operator-decided |
| `risk_tolerance` | suggest 50 (balanced) unless brand tone suggests higher | operator-decided |
| `timeline_hint` | suggest based on stage (e.g. "first paid customer in 30d") | operator-decided |
Valid `primary_goals`: Brand Awareness, Lead Gen, Sales Growth, Retention, Thought Leadership, Community Building, Content Authority, Market Disruption, Competitive Advantage, AI Search Visibility.
Add: *"Approve all, or tell me which to change."*
**After operator confirms/modifies**: `company_set_strategy_inputs(slug, …)` — MODERATE. Uses the operator-approved values.
### 3. `company_plan(<slug>, override_strategy_mode=…, override_focus=…)`
Deterministically prepends OPERATIONAL CONTEXT (active schedules + last-7d ledger + prospect funnel + missions) so the strategy covers EVERY surface, not just `what_we_sell`. Writes `strategy/proposed/<timestamp>.yaml`.
### 4. `company_plan_apply(<slug>)` — MODERATE
Atomically:
- Detects blockers (5 types — see below)
- Mission + N goals (tactic_meta packed in plan_json) + schedules (from `timeline.month1/2/3` via `execution_priority`)
- Writes `voice_proposed.yaml` from `creativeDirections.hookTemplates`
- Writes `blockers.yaml`
- Promotes proposed → active, archives prior
### 5. `company_plan_approve(<slug>, note="…")` — MODERATE
Operator finalize. Touches the strategy mission so arbiter ranks high.
## Blocker resolution (3 paths)
Each blocker in `blockers.yaml` has `resolution_proposal`:
- **`ask`**: operator must act (credentials, business decisions). Surface in chat with `build_hint`.
- **`build`**: `from_buildable_blockers` arbiter candidate invokes `self_create_plugin` (`build_method`) or `skill_promote`. CRITICAL permission gates each build. In chat mode, only attempt if operator explicitly OKs.
- **`defer`**: operator marked tactic out of scope. Note and move on.
## Surface coverage (CRITICAL)
The OPERATIONAL CONTEXT block lists every active surface (X growth, Pump.fun, email, prospect funnel, etc.). The resulting strategy MUST address each — not just `what_we_sell`. A single-surface strategy for a multi-surface business is a quality failure.
## Hard rules
- ❌ Don't skip `company_capabilities` — no operational context = narrow strategy.
- ❌ Don't skip operator approval of `strategy_inputs` — those calls aren't yours.
- ❌ Don't promote proposal to active via file_write — use `company_plan_apply`.
- ❌ Don't call `apply` + `approve` back-to-back without surfacing blockers between.
- ❌ Don't invoke `self_create_plugin` on a build blocker without explicit chat OK.
- ❌ Don't re-plan a company with an active strategy unless operator asks.
## Verify
- [ ] 5 steps ran in order
- [ ] `strategy/active/strategy.yaml` exists
- [ ] `blockers.yaml` surfaced to operator
- [ ] Voice seeded if hookTemplates populated
- [ ] Tactics span all surfaces from operational contextFrom elophanto/EloPhanto, MIT.
More from elophanto/EloPhanto
- 0.778score
metaplex
metaplex-foundation
Metaplex development on Solana — NFTs, tokens, compressed NFTs, candy machines, token launches.
SkillAFreshness: A★ 106Claude Code +9 - 0.778score
solana-dev
Solana Foundation
Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana…
SkillAFreshness: A★ 106Claude Code +9 - 0.777score
strategy-foundations
petr-royce
Marketing-strategy foundations distilled from the Phase 11 strategy generator.
SkillAFreshness: A★ 106Claude Code +9 - 0.777score
b2c-marketing-voice
petr-royce
Anti-slop principles for B2C social posts and outreach.
SkillAFreshness: A★ 106Claude Code +9 - 0.777score
12-principles-of-animation
raphael-salaja
Audit animation code against Disney's 12 principles adapted for web.
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
trust-ladder-workflow
petr-royce
Per-company trust state procedure (learning / trial / operating).
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
drive-business
petr-royce
Canonical workflow for "drive my business" / "operate this company".
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
voice-extraction-workflow
petr-royce
Produce a voice contract from operator-curated exemplars (Phase 10).
SkillAFreshness: A★ 106Claude Code +9 - 0.769score
integrating-jupiter
jupiter
Comprehensive guidance for integrating Jupiter APIs (Ultra Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio…
SkillAFreshness: A★ 106Claude Code +9 - 0.636score
pikastream-video-meeting
elophanto
Join a Google Meet or Zoom call as a video meeting agent via PikaStreaming.
SkillAFreshness: A★ 106Claude Code +9 - 0.636score
solana-kit-migration
elophanto
Helps developers understand when to use @solana/kit vs @solana/web3.js (v1), provides migration guidance, API mappings, and handles edge cases for Solana…
SkillAFreshness: A★ 106Claude Code +9 - 0.634score
plan-review-design
elophanto
Use when reviewing the UX/UI portion of a plan before implementation — rate each design dimension 0-10, explain what would make it a 10, and patch the plan to…
SkillAFreshness: A★ 106Claude Code +9
Signals
- Stars
- 106
- Forks
- 9
- Open issues
- 2
- Last commit (this folder)
- May 27, 2026 (5 months ago)
- Last release
- Oct 1, 2026 (29 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.1.0
- License
- MIT
- Repository
- github.com/elophanto/EloPhanto
- Website
- elophanto.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from petr-royce
- 0.777score
b2c-marketing-voice
petr-royce
Anti-slop principles for B2C social posts and outreach.
SkillAFreshness: A★ 106Claude Code +9 - 0.777score
strategy-foundations
petr-royce
Marketing-strategy foundations distilled from the Phase 11 strategy generator.
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
drive-business
petr-royce
Canonical workflow for "drive my business" / "operate this company".
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
voice-extraction-workflow
petr-royce
Produce a voice contract from operator-curated exemplars (Phase 10).
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
trust-ladder-workflow
petr-royce
Per-company trust state procedure (learning / trial / operating).
SkillAFreshness: A★ 106Claude Code +9
Cite this page
strategy-pipeline skill. Agent Mart. https://agentmart.dev/skills/elophanto-strategy-pipeline (last updated 2026-10-24)