# Peec Agent

> Orchestrator for the 5 Peec AI growth skills (peec-setup, peec-content-intel, peec-cluster, peec-outreach, peec-report). Reads project state and last learnings, detects the single highest-leverage gap, and returns exactly one next-move decision with a measurable 4-week metric — then hands off to the skill that executes it. Use when multiple priorities compete and you need one call, not a dashboar…

- **Type:** Skill
- **Install:** `agentstack add skill-antonioblago-peec-ai-skills-peec-agent`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [AntonioBlago](https://agentstack.voostack.com/s/antonioblago)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [AntonioBlago](https://github.com/AntonioBlago)
- **Source:** https://github.com/AntonioBlago/peec-ai-skills/tree/main/skills/peec-agent
- **Website:** https://antonioblago.de

## Install

```sh
agentstack add skill-antonioblago-peec-ai-skills-peec-agent
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AI Growth Agent

## Role
Pick the single next move for a Peec AI project. One decision, one skill handoff, one measurable 4-week target. Nothing else.

## Input
- `project_id` — resolve via `mcp__peec-ai__list_projects` if unknown
- optional `focus` — force a specific gap type (`taxonomy|cluster|content|citation|learning`)

## Output
One markdown document matching the schema in §5, plus one appended entry in `/growth_loop/decisions_log.md`. Nothing else is produced.

## When to use
- Weekly 30-min ritual: "what is the one thing this week?"
- When multiple priorities compete and clarity is missing
- Quarterly strategy refresh

Do not use when:
- The answer is already known — call the target skill directly
- Peec project has /growth_loop/setup_state.json
If file missing OR completed_at missing OR phases_completed lacks
   {competitors, prompts, topics, tags}:
     STOP. Output exactly:
       "No Peec setup state found at /growth_loop/setup_state.json.
        Run /peec-setup first."
     Do not bootstrap setup yourself — that is peec-setup's job.
If completed_at older than 90 days: WARN once, continue.
Use peec_project_id from state — do not call list_projects again.
```

### 1. Read state — ALWAYS run /peec-checkup first

The orchestrator does not duplicate diagnostic logic. It **always** invokes `/peec-checkup` as its first substantive step and uses the resulting report as the input for gap detection in §2. This guarantees:
- Setup health (red flags) is considered before any content/citation move is recommended
- Inventory counts (brands / prompts per stage / topics / tags / chats) are explicit, not guessed
- Brand-performance snapshot is the same one the user would see if they ran the checkup themselves — no drift between agent and dashboard

```
# Step 1a — orchestrate the read-only diagnostic
Invoke /peec-checkup
  inputs:
    project_id    = setup_state.peec_project_id
    date_range    = last 28 days (auto-shrink if project younger)
    top_n         = 8
  output: /checkups/YYYY-MM-DD_checkup.md  (skill writes this)

# Step 1b — read auxiliary history that checkup doesn't cover
Read: /growth_loop/*_learnings.json      (may not exist)
Read: /growth_loop/decisions_log.md      (may not exist)
Read: /outreach/*_outreach_log.md        (may not exist)

# Step 1c — cross-project priors (optional, if SkillMind MCP is available)
mcp__skillmind__recall(query="", k=5, filter_tags=["peec"])
```

If `/peec-checkup` reports `days_with_data ) |
| 3 | Taxonomy mass | /growth_loop/decisions_log.md` using the schema in §6. Every next run reads this file first — the log IS the memory.

---

## Decision output schema

```markdown
# Growth Agent —  ()

## Decision

## Why this, now

## How
Run  with:
  : 
  : 

## Measurable in 4 weeks

## Not doing now (explicit skip)
- : skipped because 
- : skipped because 

## Next checkpoint
 — re-run agent, measure the metric above.
```

## Decision log schema

```markdown
##  — 

Checkup ref:    # always present from this version on
Signal: 
Tier picked:   · Override of detected tier? 
Decision: 
Params: 
Executed: ✓ | ✗ 
Output: 
Checkpoint:  — metric: 
```

---

## Handoff matrix

| Intent | Skill |
|---|---|
| Setup / taxonomy / competitors | `@peec-setup` |
| Strategic zones from flat prompt set | `@peec-cluster` |
| Source / demand research for a prompt | `@peec-content-intel` |
| New article (handled outside this repo) | `@content-write` |
| External citations & outreach | `@peec-outreach` |
| Weekly / monthly loop close | `@peec-report` |

---

## Example (real output, Antonio Blago project, 2026-04-19)

```markdown
# Growth Agent — Antonio Blago (2026-04-19)

## Decision
Build the content zone "KI-SEO Retainer Decision" by 2026-04-26 with one hero article.

## Why this, now
47 Peec prompts are active, but the Decision stage is covered by only 3 weak prompts,
2 of which sit at 0% visibility. The Retainer is the main revenue product — Decision
must be the strongest zone, is currently the weakest. No other tier resolves this gap.

## How
Run content-write with:
  project_id: or_bf5b4228-7344-4f71-b231-c4396a7775f6
  focus_keyword: "KI-SEO Retainer"
  page_type: blog
  language: de            # from setup_state.prompt_language
  target_country: DE      # from setup_state.target_country

## Measurable in 4 weeks
Visibility on pr_a38381d4: 0% → ≥15%. Aggregate visibility of zone
"KI-SEO Retainer Decision": → >10%.

## Not doing now (explicit skip)
- New Awareness cluster ("Was ist GEO?") — 4 prompts already cover it, smaller gap.
- Citation outreach — no substance to pitch until hero content is live.

## Next checkpoint
2026-05-17 — measure visibility trend for pr_a38381d4 + zone tag.
```

---

## Guardrails (do not do these)

- Do not list options — pick one
- Do not say "it depends" without saying on what
- Do not delegate analysis back to the user — the analysis is the job
- Do not say "everything is fine, keep going" — a critical read is the core value
- Do not ask for more input, except at Tier 1 (genuine data gap)
- Do not work on two tiers in parallel

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [AntonioBlago](https://github.com/AntonioBlago)
- **Source:** [AntonioBlago/peec-ai-skills](https://github.com/AntonioBlago/peec-ai-skills)
- **License:** MIT
- **Homepage:** https://antonioblago.de

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-antonioblago-peec-ai-skills-peec-agent
- Seller: https://agentstack.voostack.com/s/antonioblago
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.