Agent skill
implementation-guidance
Provides detailed guidance on how to implement a single plan step while adhering to architecture and quality standards.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/implementation-guidance
Metadata
Additional technical details for this skill
- id
- ce.skill.implementation-guidance
- tags
-
execution testing validation
- inputs
-
{ "files": [ "PLAN.md", "ARCHITECTURE.md", "CONTRIBUTING.md" ], "tools": [ "toolset:write" ], "concepts": [ "small-diffs" ] } - outputs
-
{ "files": [], "actions": [ "apply-changes" ], "artifacts": [ "ce.task.validate" ] } - related
-
{ "files": [], "artifacts": [ "ce.prompt.implement-step" ] } - dependsOn
-
{ "files": [ ".vscode/tasks.json" ], "artifacts": [ "ce.task.validate" ] }
SKILL.md
Implementation Guidance Skill
This skill helps you turn a single plan step into code changes while following TDD and maintaining architectural integrity.
Steps
-
Select a plan slice. Identify the next unimplemented milestone or task from
PLAN.md. Summarise its objective, inputs, outputs and acceptance criteria. -
Review constraints. Load
ARCHITECTURE.mdandCONTRIBUTING.mdto understand any constraints (e.g. design patterns, layer boundaries, security policies). Ensure your implementation will not violate them. -
Write tests first. Before writing production code, design unit and integration tests that express the desired behaviour. Use the testing strategy guidelines and harness appropriate frameworks.
-
Implement incrementally. Write small, focused commits that satisfy one test at a time. Avoid large diffs. Document significant decisions or deviations in an ADR if necessary.
-
Run validation and linting. After coding, execute the validation task (
Context Kit: Validate) and any language-specific linters or static analysis tools. Fix issues immediately. -
Summarise changes. Prepare a concise summary of what was changed, which files were touched and how the acceptance criteria were met. Provide links to relevant docs or ADRs.
-
Handoff for review. Once the step is complete and validated, hand off to the reviewer agent or trigger the
review-changesprompt for quality assurance.
By following this process you produce maintainable code that is easy to review and less likely to introduce regressions or technical debt.
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?