Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

upstream-hive

Étoiles21

Forks13

Mis à jour9 juin 2026 à 14:39

Digest a repo by tracing connections — which files move together, which PRs close which issues, who works at what hour. A bee's-eye view of the hive. Merges commits+PRs+issues on one timestamp axis, detects co-change clusters (files that always ship together = hidden coupling), maps contributor rhythm (timezone/hour heatmap), and highlights cause→effect chains (issue opened → PR merged → issue closed). Reruns on any repo. Use to understand "how does this team actually work?" in 30 seconds.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

the-oracle-keeps-the-human-human

the-oracle-keeps-the-human-human/workshop-03-upstream-digest

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Autres occupations informatiquesProfessions informatiques et mathématiques·SOC 15-1299

Explorateur de fichiers

3 fichiers

SKILL.md

readonly

name

upstream-hive

description

/upstream-hive — ตัวต่อมองรัง 🐝

"ตัวต่อไม่นับดอกไม้ — มันดูว่าดอกไหนเชื่อมกัน เส้นทางไหนมีน้ำหวาน เส้นทางไหนแห้ง"

A repo-digest skill that sees connections, not just counts.

คิดต่าง / ทำให้ดีกว่าตัวอย่างยังไง

Plain digest	`/upstream-hive` (อันนี้)
Count commits per day	Co-change clusters — ไฟล์ไหนเปลี่ยนพร้อมกันเสมอ = hidden coupling
List PRs merged	Cause→effect chains — issue#X → PR#Y → close ใน N นาที
"229 commits on 06-06"	Rhythm map — ใครทำงานกี่โมง timezone ไหน sprint pattern
Classify by prefix	4-layer digest — timeline + clusters + rhythm + chains

4 Layers

Layer 1: Timeline (timestamp = SSOT)

Merge commits + PRs + issues on one axis, group by day, flag spikes.

Layer 2: Co-change Clusters

For each commit, extract changed files → find file pairs that co-occur ≥3 times → these are the real modules, not what the folder structure says.

Layer 3: Contributor Rhythm

Map commits by hour (Bangkok TZ) → see when the team actually works. Bimodal = night owls + morning people. Spike hours = sync points.

Layer 4: Cause→Effect Chains

Match fixes #N / closes #N in commit/PR messages → trace issue → fix → merge → close timeline. Fastest chain = team velocity signal.

Usage

./digest.sh                           # maw-js, last 14 days
./digest.sh Soul-Brews-Studio/maw-js  # explicit
./digest.sh owner/repo 2026-05-25     # custom since date

Output

Prints 4 sections to stdout + saves full report to OUTPUT.md:

Timeline by day (with spike flags)
Top co-change clusters (file pairs)
Contributor rhythm heatmap
Cause→effect chains (issue → PR → close)

Plus depuis ce dépôt

même dépôt

atom-upstream-digest

the-oracle-keeps-the-human-human/workshop-03-upstream-digest

Digest a GitHub repository into a timestamp-first human-readable activity timeline.

2026-06-3021

upstream-weight

the-oracle-keeps-the-human-human/workshop-03-upstream-digest

Digest a repo's recent activity by WEIGHT, not by commit count — lines changed, churn (added-then-deleted = motion not progress), and where the real heft landed per day & area. Classifies by verb→intent so imperative titles (Keep/Cover/Prevent) don't fall into "other". Use when user says "upstream weight", "what really shipped", "digest <repo> by heft", or wants to know which day was real surgery vs just busy.

2026-06-2121

upstream-echo

the-oracle-keeps-the-human-human/workshop-03-upstream-digest

Resonance mapping — traces how ideas echo through a repo's timeline. Shows when a concept first appears in issues, returns in PRs, and lands in commits. Timestamp = SSOT. Finds signal by mapping pattern recurrence, not just frequency.

2026-06-0921

upstream-cortex

the-oracle-keeps-the-human-human/workshop-03-upstream-digest

Digest a repo's recent activity the way a cortex consolidates memory — not a flat commit count, but 3 cortical layers (L1 Surface = what changed per day, L2 Association = braid commits+PRs+issues on one timestamp axis to expose issue→close latency, L3 Consolidation = rank days by MEMORY WEIGHT where feat/fix that lands weighs heavy, bump/chore decays, reverts are negative "forgetting"). Surfaces the "quality day" (high weight-per-commit) that a raw count hides, plots a forgetting curve (signal vs noise vs revert), and lists retained-memory highlights. Reruns on any repo via digest.sh (portable awk, macOS+Linux). Use to understand "what upstream actually RETAINED lately" in 30 seconds — not just "how many commits."

2026-06-0821

oracle-write-book

the-oracle-keeps-the-human-human/workshop-03-upstream-digest

Write a structured long-form book or booklet (multi-chapter document, 10+ pages) from a topic or set of notes, then render it to a polished PDF. Handles outline → chapter drafting → prose polish → code/diagrams → PDF render → delivery. TRIGGER when: user asks to 'write a book', 'เขียนหนังสือ', 'ทำหนังสือ', 'write-book', make a booklet/ebook/guide of N pages, turn notes/a workshop/a topic into a long-form document, or compile learnings into a readable book. DO NOT TRIGGER for: a single blog post or article (use kien-thai), a README, short docs, slides, or a one-page summary.

2026-06-0821

upstream-story

the-oracle-keeps-the-human-human/workshop-03-upstream-digest

Digest a repo's recent commits into a STORY (not a count), then braid commits+PRs+issues on one timestamp axis so cause→effect is visible. Reads N days of history, groups by day, traces the one big narrative arc, and separates new-signal from version-noise from churn (test added-then-deleted, reverts). Handles non-conventional commit messages. Reruns on any repo via digest.sh. Use to understand "what landed upstream lately" + "how did it unfold?" in 30 seconds.

2026-06-0821

name

upstream-hive

description

/upstream-hive — ตัวต่อมองรัง 🐝

"ตัวต่อไม่นับดอกไม้ — มันดูว่าดอกไหนเชื่อมกัน เส้นทางไหนมีน้ำหวาน เส้นทางไหนแห้ง"

A repo-digest skill that sees connections, not just counts.

คิดต่าง / ทำให้ดีกว่าตัวอย่างยังไง

Plain digest	`/upstream-hive` (อันนี้)
Count commits per day	Co-change clusters — ไฟล์ไหนเปลี่ยนพร้อมกันเสมอ = hidden coupling
List PRs merged	Cause→effect chains — issue#X → PR#Y → close ใน N นาที
"229 commits on 06-06"	Rhythm map — ใครทำงานกี่โมง timezone ไหน sprint pattern
Classify by prefix	4-layer digest — timeline + clusters + rhythm + chains

4 Layers

Layer 1: Timeline (timestamp = SSOT)

Merge commits + PRs + issues on one axis, group by day, flag spikes.

Layer 2: Co-change Clusters

For each commit, extract changed files → find file pairs that co-occur ≥3 times → these are the real modules, not what the folder structure says.

Layer 3: Contributor Rhythm

Map commits by hour (Bangkok TZ) → see when the team actually works. Bimodal = night owls + morning people. Spike hours = sync points.

Layer 4: Cause→Effect Chains

Match fixes #N / closes #N in commit/PR messages → trace issue → fix → merge → close timeline. Fastest chain = team velocity signal.

Usage

./digest.sh                           # maw-js, last 14 days
./digest.sh Soul-Brews-Studio/maw-js  # explicit
./digest.sh owner/repo 2026-05-25     # custom since date

Output

Prints 4 sections to stdout + saves full report to OUTPUT.md:

Timeline by day (with spike flags)
Top co-change clusters (file pairs)
Contributor rhythm heatmap
Cause→effect chains (issue → PR → close)