aif-improve
Enhances development plans by re-analyzing the codebase to identify edge cases and omissions.
Install
mkdir -p .claude/skills/aif-improve && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12365" && unzip -o skill.zip -d .claude/skills/aif-improve && rm skill.zipInstalls to .claude/skills/aif-improve
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Refine and enhance an existing implementation plan with a second iteration. Re-analyzes the codebase, checks for gaps, missing tasks, wrong dependencies, and improves the plan quality. Use after /aif-plan to polish the plan before implementation, or to improve an existing /aif-fix plan.Key capabilities
- →Refine existing implementation plans
- →Re-analyze codebase for plan gaps
- →Identify missing tasks and wrong dependencies
- →Enhance task quality and detail
- →Incorporate user feedback into plan improvements
How it works
The skill loads an existing plan and project context, then re-analyzes it against the codebase to find gaps, missing edge cases, and wrong assumptions, producing an enhanced plan.
Inputs & outputs
When to use aif-improve
- →Improving implementation plans
- →Identifying task gaps in plans
- →Verifying plan dependencies
About aif-improve
Iterates on previous implementation plans by performing a deeper codebase audit. It improves task structure, checks dependency validity, and enhances overall plan quality.
Refine and enhance an existing implementation plan with a second iteration. Re-analyzes the codebase, checks for gaps, missing tasks, wrong dependencies, and improves the plan quality. Use after /aif-plan to polish the plan before implementation, or to improve an existing /aif-fix plan.
When not to use it
- →When no active plan file is found
- →When only listing available plans
- →When the plan is already considered solid and ready for implementation
Limitations
- →Requires an existing plan file to operate
- →Relies on `.ai-factory/config.yaml` for configuration paths
- →Requires `Read`, `Write`, `Edit`, `Glob`, `Grep`, `Bash` tools
How it compares
This provides a structured, iterative refinement process for implementation plans, unlike a single-pass planning approach.
Compared to similar skills
aif-improve side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| aif-improve (this skill) | 0 | 6mo | Review | Intermediate |
| executing-plans | 6 | 6mo | No flags | Intermediate |
| task-think | 1 | 4mo | No flags | Advanced |
| map-workflows-guide | 0 | 8mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
executing-plans
obra
Use when you have a written implementation plan to execute in a separate session with review checkpoints
task-think
telegramdesktop
Orchestrate a multi-phase implementation workflow for this repository with artifact files under .ai/task-slug and optional fresh codex exec child runs per phase. Use when the user wants one prompt to drive context gathering, planning, implementation, verification, and review iterations while keeping the main session context clean.
map-workflows-guide
diegosouzapw
Comprehensive guide for choosing the right MAP workflow based on task type and requirements
executing-plans
liujiarui0918
Use to execute a written plan. Run tasks in batches with human checkpoints.
brainstorming
doviettung96
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation.
spec-sweep
ousiass
複数の仕様追加を事前計画で一括ヒアリングし、Issue/ブランチごとに spec-gen を順次実行する。複数機能のまとめ追記、複数仕様の連続生成、追加項目のキュー処理を依頼されたときに使う。