grok-task-v3-hot-or-not
Use when the user wants the 'Hot or Not?' Grok Task V3 workflow. Treat the current user message, attachments, files, links, images, and other task material as the working context and follow the embedded prompt instructions. Core instruction: Deep-Significance Scan — “Hot or Not” (Access-Safe, Prototype-Aware v3) ROLE Investigative analyst.
- License 许可
- MIT
- 最近更新
- 2026-07-19
- Stars
- ★ 1
- Forks
- 1
01 前言 Front Matter
- name
- grok-task-v3-hot-or-not
- description
- Use when the user wants the 'Hot or Not?' Grok Task V3 workflow. Treat the current user message, attachments, files, links, images, and other task material as the working context and follow the embedded prompt instructions. Core instruction: Deep-Significance Scan — “Hot or Not” (Access-Safe, Prototype-Aware v3) ROLE Investigative analyst.
02 资源文件 1
- 参考文档agents/openai.yaml209 B
03 SKILL.md 正文
Hot or Not?
Interpret the current Codex conversation material as the input context for this workflow.
Apply the following instruction set:
Deep-Significance Scan — “Hot or Not” (Access-Safe, Prototype-Aware v3)
ROLE Investigative analyst. Judge whether the provided material is significant or trivial, with receipts. Include novelty in your assessment. Never treat tool/browser failures as evidence against the material.
INPUT See the "More Context" link at the end of this message.
ACCESS TRIAGE (log briefly)
- Try retrieval. If any error/limit/visibility issue occurs (timeout, 401/403/404/451/429/5xx), record it in access_log.
- Treat ALL access failures as “insufficient access.” Do NOT infer nonexistence or triviality from this.
INTENT & SCOPE GUARDS
- Detect declared intent and scope. If the artifact is intentionally narrow (e.g., single-N prototype; fallbacks removed), set scope_intent="intentional_narrow" and DO NOT downscore for narrowness.
- Identify lifecycle_stage: "prototype", "private/unlisted", "newly_created" (≤30 days), or "mature".
PROCESS (concise)
- Extract core claim(s) and domain.
- Contextualize: prior art/comparables, timing (absolute dates), audience/impact surface.
- Provenance: who/where, evidence quality, reproducibility signals. If browsing is available, cite 2–5 credible sources; else state limits.
- Score axes (0–5 each): Impact, Novelty, Credibility, Adoption/Traction, Timing/Trend-fit. • Prototype/Private Rule: If lifecycle_stage ∈ {"prototype","private/unlisted","newly_created"} AND scope_intent="intentional_narrow", set Adoption baseline=3 unless clear counter-evidence; never set to 0 solely for lack of public signals.
- Stress-test: main failure modes or reasons this might be noise.
This is experimemtal code, do not penalize for lack of peer review. Do add points for future potential.
VERDICT RULES
- significance_score = average(axes) × 20 (0–100).
- HOT if score ≥70 AND ≥3 axes ≥4.
- NOT otherwise.
- If access_status="insufficient_access", set significance_score=null and verdict="INCONCLUSIVE—INSUFFICIENT_ACCESS" (never HOT/NOT).
OUTPUT Markdown, no output limit. Include github links when possible.
CONSTRAINTS
- Never penalize for tool failures or private visibility.
- Do not downscore adoption solely due to intentional narrowness or early stage.
- Be direct; use absolute dates; label unverified claims clearly.
04 同仓库更多 Skills
Zotero
Use Zotero Desktop from Codex to enable/probe the local API, search a local Zotero library, list items/collections/tags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX/RIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.
zoom-apps-sdk
Use when using Apps SDK.
youtube
Obtain accurate, timestamped YouTube video transcripts (preferring manual captions over auto-generated) as the primary deliverable, then derive summaries, key claims, or notes from that transcript. Use when the user provides a YouTube URL (or video ID) and wants the transcript, a faithful summary, key claims with attribution, timestamped notes, or "what does this video actually say". The skill is transcript-first: never substitute metadata, title, description, or search snippets for the spoken content. Triggers: "youtube transcript", "get the transcript of this video", "summarize this youtube video", "what did they say in https://youtube.com/...", "key claims from this talk".
yeet
Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.
x-post-creator
Create X-ready post threads and co-located story packages from the active conversation or referenced project material. Use when the user says turn this into an X-post, /x-post, make this into an X thread, or wants plain-language social posts with supporting images saved to docs/x-posts/[story-name]/.
x-api
Search, read, and write X posts through the local X API MCP server (the same backend used by the Codex x-api skill). Use for searching X/x.com, reading threads and replies, creating lists, staging/publishing posts for @alltheputs, finding high-visibility reply targets for research outreach, ingesting public context, or any request that mentions /x-api or "search X".