Skip to content

owenob1/prompt-improver / skills/prompt-improver

prompt-improver

Verified

Transform 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.

FileKindSize
SKILL.mdskill md10.8 KB
assets/generation-agent-prompt.mdmarkdown8.7 KB
config/runtime-defaults.jsonconfig13.5 KB
config/settings.default.jsonconfig4.6 KB
config/settings.example.jsonconfig4.8 KB
examples/before-after.mdmarkdown23.5 KB
examples/fixtures/invalid-prompt.xmlconfig176 B
examples/fixtures/valid-prompt.xmlconfig1.7 KB
references/models-supported.mdmarkdown10.1 KB
references/prompt-chaining.mdmarkdown7.2 KB
references/prompting-principles.mdmarkdown21.6 KB
references/xml-template.mdmarkdown12.0 KB
scripts/assemble-generation-prompt.shexecutablescript4.2 KB
scripts/backends/agy.shexecutablescript815 B
scripts/backends/amp.shexecutablescript708 B
scripts/backends/claude.shexecutablescript1.2 KB
scripts/backends/cline.shexecutablescript1.0 KB
scripts/backends/codex.shexecutablescript2.0 KB
scripts/backends/copilot.shexecutablescript860 B
scripts/backends/cursor.shexecutablescript785 B
scripts/backends/droid.shexecutablescript693 B
scripts/backends/gemini.shexecutablescript1.3 KB
scripts/backends/grok.shexecutablescript1.4 KB
scripts/backends/kimi.shexecutablescript879 B
scripts/backends/kiro.shexecutablescript750 B
scripts/backends/opencode.shexecutablescript694 B
scripts/backends/qwen.shexecutablescript936 B
scripts/gather-context.shexecutablescript10.8 KB
scripts/generate-prompt.shexecutablescript20.0 KB
scripts/lib/backend-common.shscript4.8 KB
scripts/lib/settings.shexecutablescript36.0 KB
scripts/smoke-test.shexecutablescript40.1 KB
scripts/standalone-improve.shexecutablescript995 B
scripts/validate-prompt.shexecutablescript11.7 KB

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>
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall