owenob1/prompt-improver / skills/prompt-improver
prompt-improver
VerifiedTransform vague prompts into precise, verifiable structured XML prompts that coding agents execute reliably. Modes: execute (default — generate then run) and plan (generate XML for review first). Use when the user says improve prompt, make this work better, prompt engineer, structure a request, plan a complex change before coding, or when a rough request needs verification criteria before execution. Do not use when the input is already a well-structured XML prompt or detailed implementation spec — skip generation and execute directly.
examples/fixtures/valid-prompt.xml
View on GitHub<context>
<project>prompt-improver skill (bash scripts, markdown references)</project>
<scope>scripts/ and documentation</scope>
</context>
<done>scripts/backends remain discoverable after sourcing settings, and bash scripts/smoke-test.sh exits 0.</done>
<stops>
- If a step needs no input, keep going. Put status in the same message as the next action.
- Stop only when blocked on the user, or before deleting data, force-pushing, or writing outside this repository.
- Do not end the turn by asking whether to continue.
</stops>
<approach>
Confirm path resolution for SCRIPT_DIR after sourcing settings, then fix backend discovery.
</approach>
<escape>
If the host environment has no coding CLI installed, fall back to manual prompt assembly and do not invent CLI flags.
</escape>
<task name="fix-settings-path-leak">
<description>
Ensure scripts/lib/settings.sh does not overwrite the caller's SCRIPT_DIR so
scripts/backends/*.sh remain discoverable.
</description>
<verification>
bash -n scripts/lib/settings.sh
bash scripts/smoke-test.sh
</verification>
</task>
<task name="validate-prompt-soft-typecheck">
<description>
Typecheck should warn for non-typed repos, not hard-fail, unless
PROMPT_IMPROVER_REQUIRE_TYPECHECK=1.
</description>
<verification>
bash scripts/validate-prompt.sh examples/fixtures/valid-prompt.xml
</verification>
</task>
<check>
Re-read every changed file under scripts/ and config/.
Run smoke tests: bash scripts/smoke-test.sh
No typecheck applicable (shell/markdown skill repo); use bash -n + validate-prompt.
Report status for each requirement from the original request.
Report: Blocked on me / Changed / Found / Unconfirmed
</check>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |