菜单
Estimate optimal waiting time for Alkosto's "every 25/50 customers" promotion using either checkout-flow observations or winner announcement timestamps. Use when the user asks how long to wait, wants a probability-based cutoff, or needs a fast in-store decision rule with uncertainty handling.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/broomva/skills --skill alkosto-wait-optimizer命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Explain the CONCEPTS a session used, at the operator's register, grounded in what actually ran. After an agent works, you are handed results built out of vocabulary you did not choose — primitive short-names, entity slugs, library names, terms of art from the diff. `/what` names those terms, ranks them by what actually blocks understanding, defines each one, and anchors it to where it appeared and to its knowledge-graph entity. Fired mid-conversation with a short slice it degrades to the re-pitch case: "that did not land, say it again with more context and a simpler register." USE WHEN: /what, "wait what", "what did you just do", "explain that again", "I don't follow", "you lost me", "what do those terms mean", "re-pitch that", "explain the concepts", "what is all this jargon", after an autonomous arc or a long PR when the vocabulary outran the operator. NOT FOR: a summary of actions taken (that is the P1 Bridge session log); state for the next agent (that is /handoff); teaching a whole body of work to master
Canonical reference inventory of the 85 agent skills in the broomva/skills monorepo, organized into 22 single-noun category buckets that mirror the skills/<category>/ directory layout, with a Remotion video showcase generator and X thread copy. Use when discovering available skills, browsing the full skills catalog, generating skills showcase content, or understanding what capabilities are available across governance, orchestration, tooling, knowledge, research, strategy, cadence, publishing, video, audio, design, finance, compute, models, messaging, robotics, aerospace, neuroscience, healthcare, science, commerce, and everyday utilities. Triggers on "skills inventory", "list all skills", "what skills are available", "skills catalog", "skills showcase", "skills video", "showcase skills", "skills reference", or any request to browse, search, or visualize the skills monorepo.
Universal knowledge engine — scores, promotes, and compounds knowledge across all sources into a permanent, query-able entity graph
基于 SOC 职业分类
正在显示 SKILL.md
| name | alkosto-wait-optimizer |
| category | commerce |
| description | Estimate optimal waiting time for Alkosto's "every 25/50 customers" promotion using either checkout-flow observations or winner announcement timestamps. Use when the user asks how long to wait, wants a probability-based cutoff, or needs a fast in-store decision rule with uncertainty handling. |
Use this skill to estimate how long to wait for the next promotion winner event.
purchase_rate: user observed purchases per minute in one or more lanes.winner_timestamps: user logged winner announcement times.K:K = 25 for Monday-Friday.K = 50 for Saturday/Sunday/holiday.optimal_wait_minutes).time_value_per_minute and expected_bonus_value, include expected-value vs time-cost guidance.purchase_rateCollect:
observed_purchasesobserved_minutesobserved_lanestotal_open_lanesmodel: global or per_laneFormulas:
lambda_obs = observed_purchases / observed_minutesglobal and total_open_lanes exists:
lambda_est = lambda_obs * (total_open_lanes / observed_lanes)per_lane:
lambda_est = lambda_obs / observed_laneslambda_cons = lambda_est * (1 - confidence_buffer)T = K / lambda_consE(wait_to_next) = T / 2optimal_wait = min(max_wait_minutes, target_hit_probability * T)Decision rule:
optimal_wait, re-measure for 2 minutes and recalculate.winner_timestampsCollect:
HH:MM[:SS] or ISO datetimes).elapsed_since_last_winner_minutes.Compute:
delta_i = t_i - t_(i-1)mu = mean(delta_i)sigma = stdev(delta_i)cv = sigma / muCadence model:
cv < 0.4: regular0.4 <= cv <= 0.7: mixedcv > 0.7: randomWait estimate:
regular: remaining ~ max(mu - elapsed, 0)random (exponential): use P(event <= W) = 1 - exp(-W / mu), and
W_target = -mu * ln(1 - target_hit_probability)mixed: average regular and random estimates.Decision rule:
optimal_wait, capture 2-3 more timestamps and recalculate.Use scripts/calc_wait.py for deterministic calculations:
python3 scripts/calc_wait.py --input-json '{"mode":"purchase_rate","is_weekend_or_holiday":true,"model":"global","observed_purchases":5,"observed_minutes":2,"observed_lanes":5,"total_open_lanes":15}'
python3 scripts/calc_wait.py --input-json '{"mode":"winner_timestamps","winner_timestamps":["12:10:15","12:27:40","12:46:05","13:02:20"],"elapsed_since_last_winner_minutes":6}'
Return concise outputs and state assumptions clearly when data is sparse.