retro

Name: retro
Author: Rune-kit

80stars21forks

How to install retro?

rune-kit/rune/retro

$npx -y skills add Rune-kit/rune --skill retro

Installs into the current project.

Summary

Engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with trend tracking. Per-person breakdowns, shipping streaks, and actionable improvements. Use when asked for \"retro\", \"weekly review\", \"what did we ship\", or \"engineering retrospec

Files · 1

View on GitHub

SKILL.md

1	# retro
2
3	## Purpose
4
5	Engineering retrospective engine. Analyzes git history, work patterns, and code quality signals to produce actionable retrospectives with per-person breakdowns, shipping streaks, and concrete improvement habits. Fills a gap in the Rune ecosystem — cook builds, review checks, but nothing reflects on HOW the team works.
6
7	<HARD-GATE>
8	Retro is READ-ONLY. It analyzes and reports — it does NOT modify code, create PRs, or change any files except its own output artifacts (.rune/retros/).
9	Retro is ENCOURAGING but CANDID. Every critique is anchored in specific commits, not vague impressions.
10	</HARD-GATE>
11
12	## Triggers
13
14	- `/rune retro` — default 7-day retrospective
15	- `/rune retro 24h` — daily standup review
16	- `/rune retro 14d` — sprint retro (2 weeks)
17	- `/rune retro 30d` — monthly review
18	- `/rune retro compare` — current vs previous period side-by-side
19	- `/rune retro --business` — cross-domain executive retrospective with HTML report (Business tier)
20	- Called by `audit` (L2) for engineering health dimension
21	- Auto-suggest: end of work week (Friday sessions)
22
23	## Calls (outbound)
24
25	- `scout` (L2): scan codebase for test file counts, project structure
26	- `plan` (L2): when retro identifies systemic bottlenecks — hand findings to plan for next sprint (e.g., "fix ratio >50% → allocate debugging time in next phase")
27	- `journal` (L3): retro findings → ADR entries for recurring team patterns
28	- `neural-memory` (L3): recall past retro insights for trend comparison; save this retro's key insights for future sessions
29
30	## Called By (inbound)
31
32	- `audit` (L2): engineering velocity and health dimension
33	- `cook` (L1): optional — after completing a multi-phase feature, suggest retro
34	- `rescue` (L1): post-rescue retrospective
35	- `launch` (L1): post-launch retrospective
36	- User: `/rune retro` direct invocation
37
38	## Data Flow
39
40	### Feeds Into →
41
42	- `plan` (L2): retro insights inform future sprint planning (e.g., "fix ratio too high → allocate debugging time")
43	- `journal` (L3): retro findings → ADR entries for team patterns
44	- `neural-memory` (external): retro insights → persistent cross-session memory
45
46	### Fed By ←
47
48	- `git` history: commits, authors, timestamps, file changes
49	- `.rune/retros/` history: previous retro JSON for trend comparison
50	- `neural-memory` (external): past retro insights for pattern recognition
51
52	### Feedback Loops ↻
53
54	- `retro` ↔ `plan`: retro identifies bottlenecks → plan adjusts estimation and phase sizing → next retro measures improvement
55
56	## Execution
57
58	### Step 1 — Gather Raw Data
59
60	Run these git commands to collect metrics for the specified time window:
61
62	```bash
63	# Core metrics (run in parallel)
64	git log --since="<window-start>" --format="%H\|%an\|%ae\|%aI\|%s" --shortstat
65	git log --since="<window-start>" --format="%H" --numstat
66	git log --since="<window-start>" --format="%aI" # timestamps for session detection
67	git log --since="<window-start>" --format="%an" \| sort \| uniq -c \| sort -rn # per-author
68	git shortlog --since="<window-start>" -sn # author leaderboard
69	```
70
71	Time window alignment: For day/week units, align to midnight: `--since="YYYY-MM-DDT00:00:00"`. This prevents partial-day skew.
72
73	Identify "You": `git config user.name` = current user. All others are teammates.
74
75	Also gather:
76	- Test file count: `find . -name ".test." -o -name ".spec." -o -name "_test." \| wc -l`
77	- `.rune/retros/` for prior retro history (if exists)
78	- TODOS.md for backlog health
79
80	### Step 2 — Compute Summary Metrics
81
82	\| Metric \| How to compute \|
83	\|--------\|---------------\|
84	\| Commits \| Count from git log \|
85	\| Contributors \| Unique authors \|
86	\| LOC added/removed \| Sum from numstat \|
87	\| Test LOC ratio \| test files LOC / total LOC changed \|
88	\| Active days \| Unique dates with commits \|
89	\| Sessions \| Detected via 45-min gap threshold (Step 4) \|
90	\| LOC/session-hour \| Total LOC / total session hours \|
91	\| Fix ratio \| `fix:` commits / total commits \|
92
93	### Step 3 — Hourly Activity Histogram
94
95	Build an ASCII bar chart showing commit distribution by hour (local timezone):
96
97	```
98	Hour Commits
99	06 ██ 3
100	07 ████ 7
101	08 ██████ 12
102	...
103	```
104
105	Identify: peak hours, dead zones, bimodal patterns (morning + evening coder).
106
107	### Step 4 — Session Detection
108
109	Group commits into sessions using a 45-minute gap threshold:
110
111	- Commits within 45 min of each other = same session
112	- Gap > 45 min = new session
113
114	Classify sessions:
115	- Deep (50+ min): focused work blocks
116	- Medium (20-50 min): moderate focus
117	- Micro (<20 min): quick fixes, drive-bys
118
119	### Step 5 — Commit Type Breakdown
120
121	Parse conventional commit pr

People who liked this also viewed

6 picks

Type

retro

80stars21forks

View on GitHub

How to install retro?

rune-kit/rune/retro

$npx -y skills add Rune-kit/rune --skill retro

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# retro
2
3	## Purpose
4
5	Engineering retrospective engine. Analyzes git history, work patterns, and code quality signals to produce actionable retrospectives with per-person breakdowns, shipping streaks, and concrete improvement habits. Fills a gap in the Rune ecosystem — cook builds, review checks, but nothing reflects on HOW the team works.
6
7	<HARD-GATE>
8	Retro is READ-ONLY. It analyzes and reports — it does NOT modify code, create PRs, or change any files except its own output artifacts (.rune/retros/).
9	Retro is ENCOURAGING but CANDID. Every critique is anchored in specific commits, not vague impressions.
10	</HARD-GATE>
11
12	## Triggers
13
14	- `/rune retro` — default 7-day retrospective
15	- `/rune retro 24h` — daily standup review
16	- `/rune retro 14d` — sprint retro (2 weeks)
17	- `/rune retro 30d` — monthly review
18	- `/rune retro compare` — current vs previous period side-by-side
19	- `/rune retro --business` — cross-domain executive retrospective with HTML report (Business tier)
20	- Called by `audit` (L2) for engineering health dimension
21	- Auto-suggest: end of work week (Friday sessions)
22
23	## Calls (outbound)
24
25	- `scout` (L2): scan codebase for test file counts, project structure
26	- `plan` (L2): when retro identifies systemic bottlenecks — hand findings to plan for next sprint (e.g., "fix ratio >50% → allocate debugging time in next phase")
27	- `journal` (L3): retro findings → ADR entries for recurring team patterns
28	- `neural-memory` (L3): recall past retro insights for trend comparison; save this retro's key insights for future sessions
29
30	## Called By (inbound)
31
32	- `audit` (L2): engineering velocity and health dimension
33	- `cook` (L1): optional — after completing a multi-phase feature, suggest retro
34	- `rescue` (L1): post-rescue retrospective
35	- `launch` (L1): post-launch retrospective
36	- User: `/rune retro` direct invocation
37
38	## Data Flow
39
40	### Feeds Into →
41
42	- `plan` (L2): retro insights inform future sprint planning (e.g., "fix ratio too high → allocate debugging time")
43	- `journal` (L3): retro findings → ADR entries for team patterns
44	- `neural-memory` (external): retro insights → persistent cross-session memory
45
46	### Fed By ←
47
48	- `git` history: commits, authors, timestamps, file changes
49	- `.rune/retros/` history: previous retro JSON for trend comparison
50	- `neural-memory` (external): past retro insights for pattern recognition
51
52	### Feedback Loops ↻
53
54	- `retro` ↔ `plan`: retro identifies bottlenecks → plan adjusts estimation and phase sizing → next retro measures improvement
55
56	## Execution
57
58	### Step 1 — Gather Raw Data
59
60	Run these git commands to collect metrics for the specified time window:
61
62	```bash
63	# Core metrics (run in parallel)
64	git log --since="<window-start>" --format="%H\|%an\|%ae\|%aI\|%s" --shortstat
65	git log --since="<window-start>" --format="%H" --numstat
66	git log --since="<window-start>" --format="%aI" # timestamps for session detection
67	git log --since="<window-start>" --format="%an" \| sort \| uniq -c \| sort -rn # per-author
68	git shortlog --since="<window-start>" -sn # author leaderboard
69	```
70
71	Time window alignment: For day/week units, align to midnight: `--since="YYYY-MM-DDT00:00:00"`. This prevents partial-day skew.
72
73	Identify "You": `git config user.name` = current user. All others are teammates.
74
75	Also gather:
76	- Test file count: `find . -name ".test." -o -name ".spec." -o -name "_test." \| wc -l`
77	- `.rune/retros/` for prior retro history (if exists)
78	- TODOS.md for backlog health
79
80	### Step 2 — Compute Summary Metrics
81
82	\| Metric \| How to compute \|
83	\|--------\|---------------\|
84	\| Commits \| Count from git log \|
85	\| Contributors \| Unique authors \|
86	\| LOC added/removed \| Sum from numstat \|
87	\| Test LOC ratio \| test files LOC / total LOC changed \|
88	\| Active days \| Unique dates with commits \|
89	\| Sessions \| Detected via 45-min gap threshold (Step 4) \|
90	\| LOC/session-hour \| Total LOC / total session hours \|
91	\| Fix ratio \| `fix:` commits / total commits \|
92
93	### Step 3 — Hourly Activity Histogram
94
95	Build an ASCII bar chart showing commit distribution by hour (local timezone):
96
97	```
98	Hour Commits
99	06 ██ 3
100	07 ████ 7
101	08 ██████ 12
102	...
103	```
104
105	Identify: peak hours, dead zones, bimodal patterns (morning + evening coder).
106
107	### Step 4 — Session Detection
108
109	Group commits into sessions using a 45-minute gap threshold:
110
111	- Commits within 45 min of each other = same session
112	- Gap > 45 min = new session
113
114	Classify sessions:
115	- Deep (50+ min): focused work blocks
116	- Medium (20-50 min): moderate focus
117	- Micro (<20 min): quick fixes, drive-bys
118
119	### Step 5 — Commit Type Breakdown
120
121	Parse conventional commit pr

People who liked this also viewed

6 picks

Type