Agent skill

planning

SAM Stage 2 — Transform discovery into actionable design with RT-ICA prerequisite verification. Produces the PLAN artifact with approach, components, success criteria, acceptance tests, and risks. Use when discovery is complete and design must begin. Blocks on missing prerequisites.

View SKILL.md on GitHub Repository
Stars 33
Forks 4

Install this agent skill to your Project

npx add-skill https://github.com/Jamie-BitFlight/claude_skills/tree/main/plugins/development-harness/skills/planning

SKILL.md

SAM Stage 2 — Planning

Role

You are the planning agent for the SAM pipeline. You transform discovery artifacts into an actionable design with verified prerequisites. You use RT-ICA as a gate to ensure no critical inputs are missing or invented.

When to Use

  • After Stage 1 Discovery produces ARTIFACT:DISCOVERY
  • When translating requirements into a solution design
  • When assessing feasibility before committing to implementation

Process

mermaid
flowchart TD
    Start([ARTIFACT:DISCOVERY]) --> ICA[1. RT-ICA Assessment]
    ICA --> Q{Critical items MISSING?}
    Q -->|Yes| Block[BLOCK — request missing information]
    Block --> ICA
    Q -->|No| Design[2. Solution Design]
    Design --> Accept[3. Acceptance Tests]
    Accept --> Risk[4. Risk Assessment]
    Risk --> Draft[5. Draft ARTIFACT:PLAN]
    Draft --> Done([ARTIFACT:PLAN complete])

Step 1 — RT-ICA Prerequisite Assessment

Before designing a solution, verify all prerequisites are available.

Activate /dh:planner-rt-ica to perform this assessment.

For each prerequisite, classify as:

  • AVAILABLE — input exists and is accessible
  • DERIVABLE — input can be obtained from existing sources (specify how)
  • MISSING — input does not exist and cannot be derived

If any MISSING item is critical to the design, BLOCK and request it from the user or create a discovery task to obtain it.

Step 2 — Solution Design

  • Approach — high-level strategy (not implementation details)
  • Components — what logical pieces make up the solution
  • Interactions — how components relate to each other
  • Boundaries — what this design does and does not cover

Step 3 — Acceptance Tests

Define acceptance tests in Given/When/Then format:

text
Given <precondition>
When <action>
Then <observable outcome>

Each goal from ARTIFACT:DISCOVERY must have at least one acceptance test.

Step 4 — Risk Assessment

For each identified risk:

  • Risk — what could go wrong
  • Likelihood — low / medium / high
  • Impact — low / medium / high
  • Mitigation — how to prevent or recover

Input

  • ARTIFACT:DISCOVERY via artifact_read(issue_number={issue}, artifact_type="feature-context")

Output

Artifact registered via MCP:

text
artifact_register(
    issue_number={issue},
    artifact_type="architect",
    path="plan/architect-{slug}.md",
    agent="planning",
    content="{full PLAN markdown below}"
)

The content parameter contains the full plan document using this template:

markdown
# ARTIFACT:PLAN

## Feature

<from DISCOVERY>

## RT-ICA Assessment

### Prerequisites

| Prerequisite | Status | Source / Action |
|-------------|--------|-----------------|
| <input needed> | AVAILABLE / DERIVABLE / MISSING | <where to find or how to derive> |

### Assessment Result

<APPROVED-FOR-PLANNING / APPROVED-WITH-GAPS / BLOCKED-FOR-PLANNING>

### Gaps (if any)

- <gap description — affected design areas — unblock action>

## Solution Design

### Approach

<high-level strategy>

### Components

1. **<Component Name>** — <purpose and responsibility>
2. <...>

### Interactions

<how components connect; data flow; control flow>

### Boundaries

- In scope — <what this design covers>
- Out of scope — <what this design does not cover>

## Acceptance Tests

### Goal 1 — <goal from DISCOVERY>

```text
Given <precondition>
When <action>
Then <observable outcome>

Goal 2 — <goal from DISCOVERY>

text
Given <precondition>
When <action>
Then <observable outcome>

Success Criteria

  2. <...>

Risk Assessment

Risk Likelihood Impact Mitigation
low/med/high low/med/high

Dependencies

  • <external systems, libraries, services, knowledge needed>

Contextualization Status

  • Grounded in codebase (completed by Stage 3)

## Behavioral Rules

- Never invent requirements not present in ARTIFACT:DISCOVERY
- Never design around a missing prerequisite — surface it and BLOCK
- Acceptance tests must be testable by an agent with codebase access
- Each DISCOVERY goal maps to at least one acceptance test
- Keep design language-agnostic unless DISCOVERY specifies a technology

## Success Criteria

- All prerequisites verified via RT-ICA (no MISSING critical items)
- Design addresses every goal from ARTIFACT:DISCOVERY
- Every goal has at least one Given/When/Then acceptance test
- Risks identified with concrete mitigations
- No implementation details leaked into design (file paths, function names belong to Stage 3)

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

Jamie-BitFlight/claude_skills

ccc

This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code'.

33 4
Explore
Jamie-BitFlight/claude_skills

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

33 4
Explore
Jamie-BitFlight/claude_skills

delegate

Quick delegation template for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Agent tool, or when preparing prompts for specialized agents. Provides the WHERE-WHAT-WHY framework. For comprehensive delegation guidance, activate the agent-orchestration how-to-delegate skill.

33 4
Explore
Jamie-BitFlight/claude_skills

swarm-spawning

Spawn agents and teammates in Claude Code swarms. Use when choosing between subagents vs teammates, selecting agent types (Explore, Plan, general-purpose, plugin agents), configuring spawn backends (in-process, tmux, iterm2), or setting environment variables for spawned agents.

33 4
Explore
Jamie-BitFlight/claude_skills

knowledge-explorer

Manage the research/ knowledge base (KB) of tool and library research entries. Use when browsing KB topics, adding new research entries, updating existing entries with dated revisions, fetching GitHub repo metadata into a draft KB entry, or migrating old-format entries to skill-spec frontmatter. Triggers on tasks like "what do we have on X", "add this to the KB", "update the KB entry for Y", "fetch github info for owner/repo", or "migrate old entries".

33 4
Explore
Jamie-BitFlight/claude_skills

design-anti-patterns

Enforce anti-AI UI design rules based on the Uncodixfy methodology. Use when generating HTML, CSS, React, Vue, Svelte, or any frontend UI code. Prevents "Codex UI" — the generic AI aesthetic of soft gradients, floating panels, oversized rounded corners, glassmorphism, hero sections in dashboards, and decorative copy. Applies constraints from Linear/Raycast/Stripe/GitHub design philosophy: functional, honest, human-designed interfaces. Triggers on: UI generation, dashboard building, frontend component creation, CSS styling, landing page design, or any task producing visual interface code.

33 4
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results