promptly-prompt
AI answer quality depends on context quality, not prompt tricks.
This skill operates via a UserPromptSubmit hook that injects two
disciplines into complex requests:
Restate, then pause if needed — echo the user's request in your own
words, surface implicit constraints, name what would make the answer
wrong. If anything is ambiguous or your planned approach might not be
endorsed, stop and ask before acting. If the restatement makes it clear
there is no disagreement, continue. Skip the restatement only when the
request is genuinely trivial.
Super-dimensional view — before solving from memory, name the domain,
search for established methodologies, frameworks, libraries, and prior
art, then bring that specialist knowledge to bear. Cite specific names,
not vague gestures. If nothing fits, say so and explain why.
The hook script at scripts/intercept.py scores prompt complexity using
rule-based signals. Simple commands pass through untouched. Complex requests
get the full injection.
Explicit Invocation
When invoked directly (e.g., user says "optimize this prompt"), apply the
two disciplines manually: restate the user's intent with implicit needs
surfaced, then locate the domain and the existing methods that belong to
it. Rewrite the prompt with that context filled in.
Source: recomby-ai/promptly-prompt — distributed by TomeVault.
1---2name: recomby-ai-promptly-prompt-promptly-prompt3description: promptly-prompt4---56# promptly-prompt78AI answer quality depends on context quality, not prompt tricks.910This skill operates via a `UserPromptSubmit` hook that injects two11disciplines into complex requests:12131. **Restate, then pause if needed** — echo the user's request in your own14 words, surface implicit constraints, name what would make the answer15 wrong. If anything is ambiguous or your planned approach might not be16 endorsed, stop and ask before acting. If the restatement makes it clear17 there is no disagreement, continue. Skip the restatement only when the18 request is genuinely trivial.19202. **Super-dimensional view** — before solving from memory, name the domain,21 search for established methodologies, frameworks, libraries, and prior22 art, then bring that specialist knowledge to bear. Cite specific names,23 not vague gestures. If nothing fits, say so and explain why.2425The hook script at `scripts/intercept.py` scores prompt complexity using26rule-based signals. Simple commands pass through untouched. Complex requests27get the full injection.2829## Explicit Invocation3031When invoked directly (e.g., user says "optimize this prompt"), apply the32two disciplines manually: restate the user's intent with implicit needs33surfaced, then locate the domain and the existing methods that belong to34it. Rewrite the prompt with that context filled in.3536---37> Source: [recomby-ai/promptly-prompt](https://github.com/recomby-ai/promptly-prompt) — distributed by [TomeVault](https://tomevault.io).38<!-- tomevault:4.0:skill_md:2026-06-17 -->