diff --git a/README.md b/README.md index 0b72fd3..b9df2aa 100644 --- a/README.md +++ b/README.md @@ -108,7 +108,7 @@ At the end it offers an interactive opt-in — **"Also initialize KiroCrew? (y/N What it installs: 1. `~/.kiro/agents/*.json` — the four agent specs (also valid KiroCrew templates) 2. `~/.kiro/prompts/*.md` — their system prompts -3. `~/.kiro/skills/` — workflow skills (incl. the `upgrade-guardian` skill) +3. `~/.kiro/skills/` — workflow skills (incl. the `potr-upgrade-guardian` skill) 4. `~/.kiro/hooks/` — safety-gate, barrel-export, etc. 5. `~/.kiro/steering/` — shared steering docs @@ -196,10 +196,10 @@ These agents are distributed by `dev init-kiro` for use across all BePower proje | Agent | Description | |-------|-------------| -| `bepower-setup` | Analyzes a project and generates optimal `.kiro/` configuration (steering, agent, prompt, skills) | -| `functional-analyst` | Interactive functional analysis — collects requirements through conversation, produces approval docs and technical briefs (Italian-first) | -| `upgrade-guardian` | Assesses the safety of a dependency/framework upgrade in an isolated worktree and returns a reasoned **LOW/MEDIUM/HIGH** risk verdict with real breaking-change analysis, project impact and verification | -| `rev-eng` | Reverse-engineers a target web app's internal API via Playwright and documents it for a TypeScript client | +| `potr-setup` | Analyzes a project and generates optimal `.kiro/` configuration (steering, agent, prompt, skills) | +| `potr-functional-analyst` | Interactive functional analysis — collects requirements through conversation, produces approval docs and technical briefs (Italian-first) | +| `potr-upgrade-guardian` | Assesses the safety of a dependency/framework upgrade in an isolated worktree and returns a reasoned **LOW/MEDIUM/HIGH** risk verdict with real breaking-change analysis, project impact and verification | +| `potr-rev-eng` | Reverse-engineers a target web app's internal API via Playwright and documents it for a TypeScript client | ## Using the Agents @@ -212,7 +212,7 @@ Pass the agent name to `kiro-cli chat`: ```bash # in the repo you want it to work on cd ~/projects/bepower/bep-cdk -kiro-cli chat --agent upgrade-guardian +kiro-cli chat --agent potr-upgrade-guardian ``` Then start the conversation by telling it what to assess, e.g.: @@ -223,7 +223,7 @@ The agent reads the project context (`README.md`, `AGENTS.md` if present, `packa ### In the KiroCrew dashboard -After `dev init-crew` the agents appear as **members in the dashboard's agent picker**. Open a new chat, pick `upgrade-guardian` (or `rev-eng`), and start the conversation the same way — the result (e.g. an upgrade safety report) is rendered inline, with each member keeping its own dedicated memory. +After `dev init-crew` the agents appear as **members in the dashboard's agent picker**. Open a new chat, pick `potr-upgrade-guardian` (or `potr-rev-eng`), and start the conversation the same way — the result (e.g. an upgrade safety report) is rendered inline, with each member keeping its own dedicated memory. ### How to start the conversation @@ -231,12 +231,12 @@ These agents are **task-driven**, not chatty — open with the concrete thing yo | Agent | A good opening message | |-------|------------------------| -| `upgrade-guardian` | _"Assess upgrading `` from `` to `` in this repo. Is it safe to merge?"_ | -| `rev-eng` | _"Reverse-engineer the API of `` and document the endpoints for a TypeScript client."_ | -| `bepower-setup` | _"Analyze this project and generate the `.kiro/` configuration for it."_ | -| `functional-analyst` | _"Raccogliamo i requisiti per ``."_ (Italian-first) | +| `potr-upgrade-guardian` | _"Assess upgrading `` from `` to `` in this repo. Is it safe to merge?"_ | +| `potr-rev-eng` | _"Reverse-engineer the API of `` and document the endpoints for a TypeScript client."_ | +| `potr-setup` | _"Analyze this project and generate the `.kiro/` configuration for it."_ | +| `potr-functional-analyst` | _"Raccogliamo i requisiti per ``."_ (Italian-first) | -The agent does the rest — reads context, analyzes, and returns a verdict or document. For `upgrade-guardian` the output is a safety report with a LOW/MEDIUM/HIGH verdict and a **suggested** (never executed) commit message; you decide whether to apply it. +The agent does the rest — reads context, analyzes, and returns a verdict or document. For `potr-upgrade-guardian` the output is a safety report with a LOW/MEDIUM/HIGH verdict and a **suggested** (never executed) commit message; you decide whether to apply it. ## Architecture diff --git a/cli/commands/init-crew.ts b/cli/commands/init-crew.ts index dff93b4..35c747d 100644 --- a/cli/commands/init-crew.ts +++ b/cli/commands/init-crew.ts @@ -13,7 +13,12 @@ const execAsync = promisify(exec); * from the same `~/.kiro/agents/` directory, so each one only needs a crew * member bound to it (`kirocrew agent create --kiro-agent