From software-engineering
Produce a constrained implementation plan (goal, first test, further test cases) before writing any code. Apply when asked to implement a feature or start a ticket.
How this skill is triggered — by the user, by Claude, or both
Slash command
/software-engineering:implementation-planningThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When asked to implement anything, produce a plan before writing code. Plans are deliberately constrained.
When asked to implement anything, produce a plan before writing code. Plans are deliberately constrained.
Apply this skill when:
## Goal
[What behaviour is being added]
## First test
Suite: WhenDoingABehaviour
Test: The_outcome_described_in_plain_english
Setup: [Given builders or state needed]
Action: [What is called]
Assert: [What is expected]
## Further test cases
- [ ] [Behaviour] — [lightweight preconception if relevant]
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub de-anchorite/claude-skills --plugin software-engineering