Agent skill
prime-feat
This skill should be used when the user asks to "load feature context", "resume feature work", "prime feature N", "continue feature N", or wants to load all planning artifacts for a specific feature number.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/prime-feat
SKILL.md
Prime Feature Context
Load all planning artifacts and context for feature {{feature_number}}.
Artifact Locations
- Find the feature folder: check
backlog/plans/{{feature_number}}-*/first, thenbacklog/plans/_completed/{{feature_number}}-*/ - Read all planning documents:
- analysis.md
- spec.md
- research.md
- plan.md
- data-model.md
- tasks.md
- contracts/ (all files)
- Read spec tests:
specs/tests/{{feature_number}}-*.md - Check git branch status for
feature/{{feature_number}}-*
Workflow
- Check
backlog/plans/first for in-progress features, thenbacklog/plans/_completed/for completed ones - Use
ls backlog/plans/ backlog/plans/_completed/to find the folder matching{{feature_number}}-* - Once found, extract the full feature ID (e.g.,
001-mcp-integration) and path - Read all files in
{feature-path}/:- Start with
analysis.md,spec.md,plan.md(core docs) - Then
data-model.md,tasks.md,research.md - Finally list and read files in
contracts/directory
- Start with
- Read
specs/tests/{feature-id}.mdif it exists - Run
git statusandgit branch --show-currentto check current branch - If not on the feature branch, suggest:
git checkout feature/{feature-id} - Analyze
tasks.mdand summarize:- Total task count
- Completed count (checked boxes)
- Current phase based on task completion
- Next uncompleted task
Output Summary
Present a concise status report in this format:
┌─────────────────────────────────────────────────────────────┐
│ Feature {NNN}-{slug} │
├─────────────────────────────────────────────────────────────┤
│ Branch: feature/{NNN}-{slug} ✓ (or ✗ if not on branch) │
│ Progress: {completed}/{total} tasks ({percent}%) │
├─────────────────────────────────────────────────────────────┤
│ Phase Progress: │
│ Phase 1: {name} ████████████ {done}/{total} ✓ │
│ Phase 2: {name} ██████░░░░░░ {done}/{total} ← current │
│ Phase 3: {name} ░░░░░░░░░░░░ {done}/{total} │
│ ... │
├─────────────────────────────────────────────────────────────┤
│ Recently Completed: │
│ • T{N} - {description} │
│ • T{N} - {description} │
├─────────────────────────────────────────────────────────────┤
│ Next Up: │
│ → T{N} - {description} ← START HERE │
│ T{N} - {description} │
│ T{N} - {description} │
└─────────────────────────────────────────────────────────────┘
Report Guidelines
- Phase Progress: Show all phases with a visual progress bar (█ for done, ░ for remaining)
- Recently Completed: Show last 2-3 completed tasks from the current phase
- Next Up: Show next 3 uncompleted tasks, marking the first with "← START HERE"
- Keep it scannable: Use consistent formatting, avoid prose
Progress Bar Calculation
For each phase, calculate: done / total * 12 filled blocks (█), remainder as empty (░)
Important: Do NOT provide a detailed summary of the documents - they are already loaded into context. The report replaces verbose explanations.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?