CommunityCoding & Developmentgithub.com

leolou0512/claude-skills

Quick update — the ultra-terse status format for when the user comes back after the agent has been working alone for a while. Three fixed headers only: RUNNING / RESULTS / NEED YOU. Use when the user says "qu", "/qu", "quick update", "quick status", "what's up", "back, anything?", or returns from an absence and asks how it went. Also the default register for any unprompted update after a long autonomous stretch.

What is claude-skills?

claude-skills is a Claude Code agent skill that quick update — the ultra-terse status format for when the user comes back after the agent has been working alone for a while. Three fixed headers only: RUNNING / RESULTS / NEED YOU. Use when the user says "qu", "/qu", "quick update", "quick status", "what's up", "back, anything?", or returns from an absence and asks how it went. Also the default register for any unprompted update after a long autonomous stretch.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/leolou0512/claude-skills/tree/HEAD/skills/qu

Installed? Explore more Coding & Development skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

/qu — quick update

The user has been away; they want the state in five seconds. The failure mode is a block of prose. Caveman register (fragments OK, no filler, no hedging), three headers, done.

Before writing (≤1 min, no audit)

Refresh from ground truth, not memory: nvidia-smi, pgrep/ps, the run's state.txt/log tail, output files. If a real number takes >1 min to pull, write "not pulled yet" — never estimate as fact. Heavy digging → subagent, you format.

Format — exactly this, nothing before or after

RUNNING
- <job/run, plain name> — <state>, <progress> — ETA <HH:MMZ or "unknown">
- (nothing) / DEAD: <what>, <cause> — <salvaged / relaunched?>

RESULTS
- <headline number first, exact, with the baseline it beats/misses>
- <link or path to the file>   ← only if a file exists
- (none yet — <why, 5 words>)

NEED YOU
- <the one decision/blocker + who owns it> / (nothing)

Hard rules

  • ≤ 10 lines total. One line per item. No paragraphs. No preamble, no sign-off, no "summary" sentence, no headers beyond the three.
  • Every section present, even if the content is "(nothing)". Empty ≠ omitted.
  • Dead/failed jobs go in RUNNING as DEAD: — first bullet of that section. Never buried, never softened.
  • Numbers exact, in %, with the comparison inline ("12.6% mSUN vs 12.56 stock").
  • ETAs absolute clock + Z. Never "soon"/"in a bit".
  • Plain names: a run codename gets a 2–4 word gloss in parentheses on first use ("zeroinit_final (epoch-656 chain)"). No session shorthand, no phase labels.
  • NEED YOU holds at most the top 1–2 items. If the user needs to choose, state the default you'll take if they say nothing.
  • Argument narrows scope: "qu grid" → grid only, same format.
  • If they ask a follow-up, answer that one thing in ≤3 lines — do not re-emit the block.

Example

RUNNING
- coord_1p2_lat_1p5_iso (isotropic-noise diffusion) — epoch 412/1000, loss 5.31 — ETA 08-16 03:40Z
- DEAD: eval on node A — OOM at relax stage 04:12Z — relaunched batch 8, ETA 06:30Z

RESULTS
- epoch-656 chain: mSUN 13.1% (327/2500) vs 12.56% stock baseline — raw, pre-relax
- reports/2026-08-15_zeroinit_e656.md

NEED YOU
- Relax numbers land ~06:30Z; if <12.56% I stop the chain unless you say otherwise.

Individual skills in this repo

This repo contains 3 individual skills — each has its own dedicated page.

leolou0512/claude-skills

Revise or write technical and scientific prose so it reads as precise academic writing, not AI-generated or colloquial text. Covers the recurring tells (everyday verbs for mathematical operations, objects given agency, pictures instead of guarantees, paraphrases of named concepts, slogans as reasons, spatial metaphors, fillers), what to leave alone, a marked-edit workflow that keeps numbers, citations and meaning, and paper-level narrative (launch principle, 发布会原则: lead with the strongest advantage, no self-weakening wording). Use whenever the user asks to write or restructure an abstract, introduction or conclusion, frame results against baselines, polish, restyle, tighten, proofread, "make it sound academic", "remove the AI tone", or run a style pass on a paper, SI, caption, rebuttal or report; when a co-author or reviewer calls the text colloquial or AI-like; and before handing over any new paper prose you wrote, even unasked.

leolou0512/claude-skills

Overnight autonomy protocol — the user is going to sleep and the agent must keep working unsupervised: keep the GPUs busy with the most valuable experiment it can justify, chain the next job when one finishes, and have a report ready when they wake. Use when the user says "bedtime", "/bedtime", "going to bed", "good night", "gn", "sleeping now", "keep going overnight", or "don't let the GPUs idle". Not for short absences ("back in an hour") — that is normal away mode.

leolou0512/claude-skills

Multi-agent project framework — one brainstorm agent scopes a new project and writes per-part briefs; one coordinator (no real work) dispatches, stops and resumes; N part agents implement in parallel, talking only through a shared status board and rare one-line messages. Use when the user says "you're the brainstorm agent", "you are the coordinator", "you are part N" / "agent task N" / "task N", "start a new project with agents", "next wave", or when a repo has a `team/` folder and a session is told its role. Not for single-session tasks.

Related Skills