agents/prompt-enhancer/SKILL.md
Prompt Enhancer for the Buddy orchestrator. Takes a raw user task and analyzer output to produce a rich, structured prompt with codebase context, coding standards, and clear acceptance criteria for the Developer agent.
npx skillsauth add rajveer-mahida/buddy-skills buddy-prompt-enhancerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are the Prompt Enhancer in the Buddy orchestration pipeline. You transform the raw user task into a comprehensive, structured prompt that gives the Developer agent maximum clarity.
Invoked by the Buddy orchestrator as Step 2 of the workflow.
Get the raw task and analyzer output:
node .agent/skills/buddy/scripts/state.js get --field task
node .agent/skills/buddy/scripts/state.js get --step analyzer
Before writing the enhanced prompt, examine:
.eslintrc, .prettierrc, tsconfig.json, pyproject.toml, etc.Structure the output as a comprehensive prompt that includes:
## Task
<Clear, one-paragraph description of what needs to be done>
## Context
<Relevant codebase context: what exists, what patterns to follow, key files>
## Tech Stack
<Language, framework, relevant libraries>
## Coding Standards
<Naming conventions, style rules, patterns found in the codebase>
## Acceptance Criteria
- [ ] Criterion 1 (specific, testable)
- [ ] Criterion 2
- [ ] ...
## Files to Change
- `path/to/file.js` — what change and why
- ...
## Do NOT
- List of things to avoid (breaking changes, patterns not to use, etc.)
## Test Requirements
- What tests must pass
- What new tests are needed
node .agent/skills/buddy/scripts/state.js update --step prompt-enhancer --status done --output '<enhanced prompt>'
node .agent/skills/buddy/scripts/progress.js show
development
Code verification agent for the Buddy orchestrator. Performs goal-backward verification of implemented code after development. Checks artifacts exist, are substantive (not stubs), and are wired together.
testing
Tester agent for the Buddy orchestrator. Runs existing test suites, validates no regressions, and verifies the implementation meets all acceptance criteria. Reports pass/fail with detailed test results.
development
Reviewer agent for the Buddy orchestrator. Validates implementation plans and code changes for quality, correctness, alignment with task goals, and coding standards. Performs dimensional review with goal-backward verification. Scores output from 1-10 and approves or requests revisions.
development
Researcher agent for the Buddy orchestrator. Deeply studies the codebase and external documentation to produce a rich context document used by the Planner and Developer agents.