analyse

Name: analyse
Author: NeoLabHQ

868installs132forks

How to install analyse?

neolabhq/context-engineering-kit/analyse

$npx -y skills add NeoLabHQ/context-engineering-kit --skill analyse

Installs into the current project.

Summary

Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target

Files · 1

View on GitHub

SKILL.md

1	# Smart Analysis
2
3	Intelligently select and apply the most appropriate Kaizen analysis technique based on what you're analyzing.
4
5	## Description
6	Analyzes context and chooses best method: Gemba Walk (code exploration), Value Stream Mapping (workflow/process), or Muda Analysis (waste identification). Guides you through the selected technique.
7
8	## Usage
9	`/analyse [target_description]`
10
11	Examples:
12	- `/analyse authentication implementation`
13	- `/analyse deployment workflow`
14	- `/analyse codebase for inefficiencies`
15
16	## Variables
17	- TARGET: What to analyze (default: prompt for input)
18	- METHOD: Override auto-selection (gemba, vsm, muda)
19
20	## Method Selection Logic
21
22	Gemba Walk → When analyzing:
23	- Code implementation (how feature actually works)
24	- Gap between documentation and reality
25	- Understanding unfamiliar codebase areas
26	- Actual vs. assumed architecture
27
28	Value Stream Mapping → When analyzing:
29	- Workflows and processes (CI/CD, deployment, development)
30	- Bottlenecks in multi-stage pipelines
31	- Handoffs between teams/systems
32	- Time spent in each process stage
33
34	Muda (Waste Analysis) → When analyzing:
35	- Code quality and efficiency
36	- Technical debt
37	- Over-engineering or duplication
38	- Resource utilization
39
40	## Steps
41	1. Understand what's being analyzed
42	2. Determine best method (or use specified method)
43	3. Explain why this method fits
44	4. Guide through the analysis
45	5. Present findings with actionable insights
46
47	---
48
49	## Method 1: Gemba Walk
50
51	"Go and see" the actual code to understand reality vs. assumptions.
52
53	### When to Use
54	- Understanding how feature actually works
55	- Code archaeology (legacy systems)
56	- Finding gaps between docs and implementation
57	- Exploring unfamiliar areas before changes
58
59	### Process
60	1. Define scope: What code area to explore
61	2. State assumptions: What you think it does
62	3. Observe reality: Read actual code
63	4. Document findings:
64	- Entry points
65	- Actual data flow
66	- Surprises (differs from assumptions)
67	- Hidden dependencies
68	- Undocumented behavior
69	5. Identify gaps: Documentation vs. reality
70	6. Recommend: Update docs, refactor, or accept
71
72	### Example: Authentication System Gemba Walk
73
74	```
75	SCOPE: User authentication flow
76
77	ASSUMPTIONS (Before):
78	• JWT tokens stored in localStorage
79	• Single sign-on via OAuth only
80	• Session expires after 1 hour
81	• Password reset via email link
82
83	GEMBA OBSERVATIONS (Actual Code):
84
85	Entry Point: /api/auth/login (routes/auth.ts:45)
86	├─> AuthService.authenticate() (services/auth.ts:120)
87	├─> UserRepository.findByEmail() (db/users.ts:67)
88	├─> bcrypt.compare() (services/auth.ts:145)
89	└─> TokenService.generate() (services/token.ts:34)
90
91	Actual Flow:
92	1. Login credentials → POST /api/auth/login
93	2. Password hashed with bcrypt (10 rounds)
94	3. JWT generated with 24hr expiry (NOT 1 hour!)
95	4. Token stored in httpOnly cookie (NOT localStorage)
96	5. Refresh token in separate cookie (15 days)
97	6. Session data in Redis (30 days TTL)
98
99	SURPRISES:
100	✗ OAuth not implemented (commented out code found)
101	✗ Password reset is manual (admin intervention)
102	✗ Three different session storage mechanisms:
103	- Redis for session data
104	- Database for "remember me"
105	- Cookies for tokens
106	✗ Legacy endpoint /auth/legacy still active (no auth!)
107	✗ Admin users bypass rate limiting (security issue)
108
109	GAPS:
110	• Documentation says OAuth, code doesn't have it
111	• Session expiry inconsistent (docs: 1hr, code: 24hr)
112	• Legacy endpoint not documented (security risk)
113	• No mention of "remember me" in docs
114
115	RECOMMENDATIONS:
116	1. HIGH: Secure or remove /auth/legacy endpoint
117	2. HIGH: Document actual session expiry (24hr)
118	3. MEDIUM: Clean up or implement OAuth
119	4. MEDIUM: Consolidate session storage (choose one)
120	5. LOW: Add rate limiting for admin users
121	```
122
123	### Example: CI/CD Pipeline Gemba Walk
124
125	```
126	SCOPE: Build and deployment pipeline
127
128	ASSUMPTIONS:
129	• Automated tests run on every commit
130	• Deploy to staging automatic
131	• Production deploy requires approval
132
133	GEMBA OBSERVATIONS:
134
135	Actual Pipeline (.github/workflows/main.yml):
136	1. On push to main:
137	├─> Lint (2 min)
138	├─> Unit tests (5 min) [SKIPPED if "[skip-tests]" in commit]
139	├─> Build Docker image (15 min)
140	└─> Deploy to staging (3 min)
141
142	2. Manual trigger for production:
143	├─> Run integration tests (20 min) [ONLY for production!]
144	├─> Security scan (10 min)
145	└─> Deploy to production (5 min)
146
147	SURPRISES:
148	✗ Unit tests can be skipped with commit message flag
149	✗ Integration tests ONLY run for production deploy
150	✗ Staging deployed without integration tests
151	✗ No rollback mechanism (manual kubectl commands)
152	✗ Secrets loaded from .env file (not secrets manager)
153	✗ Old "hotfix" branch bypasses all checks
154
155	GAPS:
156	• Staging and production have different test coverage
157	• Documentation doesn't mention test skip flag
158	• Rollback process not documented or automated
159	• Security s

People who liked this also viewed

6 picks

Type

azure-diagnosticsDebug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deploySkillsJul 2026472k1.3k
systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesSkillsJul 2026197k259k
safe-debugRigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training SkillsMay 2026161k507
explore-runRigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subseSkillsMay 2026161k507
minimal-run-and-auditRigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation SkillsMay 2026161k507
insforge-debugUse when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denSkillsJul 202618k31

analyse

868installs132forks

View on GitHub

How to install analyse?

neolabhq/context-engineering-kit/analyse

$npx -y skills add NeoLabHQ/context-engineering-kit --skill analyse

Installs into the current project.

Summary

Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target

Files · 1

View on GitHub

SKILL.md

1	# Smart Analysis
2
3	Intelligently select and apply the most appropriate Kaizen analysis technique based on what you're analyzing.
4
5	## Description
6	Analyzes context and chooses best method: Gemba Walk (code exploration), Value Stream Mapping (workflow/process), or Muda Analysis (waste identification). Guides you through the selected technique.
7
8	## Usage
9	`/analyse [target_description]`
10
11	Examples:
12	- `/analyse authentication implementation`
13	- `/analyse deployment workflow`
14	- `/analyse codebase for inefficiencies`
15
16	## Variables
17	- TARGET: What to analyze (default: prompt for input)
18	- METHOD: Override auto-selection (gemba, vsm, muda)
19
20	## Method Selection Logic
21
22	Gemba Walk → When analyzing:
23	- Code implementation (how feature actually works)
24	- Gap between documentation and reality
25	- Understanding unfamiliar codebase areas
26	- Actual vs. assumed architecture
27
28	Value Stream Mapping → When analyzing:
29	- Workflows and processes (CI/CD, deployment, development)
30	- Bottlenecks in multi-stage pipelines
31	- Handoffs between teams/systems
32	- Time spent in each process stage
33
34	Muda (Waste Analysis) → When analyzing:
35	- Code quality and efficiency
36	- Technical debt
37	- Over-engineering or duplication
38	- Resource utilization
39
40	## Steps
41	1. Understand what's being analyzed
42	2. Determine best method (or use specified method)
43	3. Explain why this method fits
44	4. Guide through the analysis
45	5. Present findings with actionable insights
46
47	---
48
49	## Method 1: Gemba Walk
50
51	"Go and see" the actual code to understand reality vs. assumptions.
52
53	### When to Use
54	- Understanding how feature actually works
55	- Code archaeology (legacy systems)
56	- Finding gaps between docs and implementation
57	- Exploring unfamiliar areas before changes
58
59	### Process
60	1. Define scope: What code area to explore
61	2. State assumptions: What you think it does
62	3. Observe reality: Read actual code
63	4. Document findings:
64	- Entry points
65	- Actual data flow
66	- Surprises (differs from assumptions)
67	- Hidden dependencies
68	- Undocumented behavior
69	5. Identify gaps: Documentation vs. reality
70	6. Recommend: Update docs, refactor, or accept
71
72	### Example: Authentication System Gemba Walk
73
74	```
75	SCOPE: User authentication flow
76
77	ASSUMPTIONS (Before):
78	• JWT tokens stored in localStorage
79	• Single sign-on via OAuth only
80	• Session expires after 1 hour
81	• Password reset via email link
82
83	GEMBA OBSERVATIONS (Actual Code):
84
85	Entry Point: /api/auth/login (routes/auth.ts:45)
86	├─> AuthService.authenticate() (services/auth.ts:120)
87	├─> UserRepository.findByEmail() (db/users.ts:67)
88	├─> bcrypt.compare() (services/auth.ts:145)
89	└─> TokenService.generate() (services/token.ts:34)
90
91	Actual Flow:
92	1. Login credentials → POST /api/auth/login
93	2. Password hashed with bcrypt (10 rounds)
94	3. JWT generated with 24hr expiry (NOT 1 hour!)
95	4. Token stored in httpOnly cookie (NOT localStorage)
96	5. Refresh token in separate cookie (15 days)
97	6. Session data in Redis (30 days TTL)
98
99	SURPRISES:
100	✗ OAuth not implemented (commented out code found)
101	✗ Password reset is manual (admin intervention)
102	✗ Three different session storage mechanisms:
103	- Redis for session data
104	- Database for "remember me"
105	- Cookies for tokens
106	✗ Legacy endpoint /auth/legacy still active (no auth!)
107	✗ Admin users bypass rate limiting (security issue)
108
109	GAPS:
110	• Documentation says OAuth, code doesn't have it
111	• Session expiry inconsistent (docs: 1hr, code: 24hr)
112	• Legacy endpoint not documented (security risk)
113	• No mention of "remember me" in docs
114
115	RECOMMENDATIONS:
116	1. HIGH: Secure or remove /auth/legacy endpoint
117	2. HIGH: Document actual session expiry (24hr)
118	3. MEDIUM: Clean up or implement OAuth
119	4. MEDIUM: Consolidate session storage (choose one)
120	5. LOW: Add rate limiting for admin users
121	```
122
123	### Example: CI/CD Pipeline Gemba Walk
124
125	```
126	SCOPE: Build and deployment pipeline
127
128	ASSUMPTIONS:
129	• Automated tests run on every commit
130	• Deploy to staging automatic
131	• Production deploy requires approval
132
133	GEMBA OBSERVATIONS:
134
135	Actual Pipeline (.github/workflows/main.yml):
136	1. On push to main:
137	├─> Lint (2 min)
138	├─> Unit tests (5 min) [SKIPPED if "[skip-tests]" in commit]
139	├─> Build Docker image (15 min)
140	└─> Deploy to staging (3 min)
141
142	2. Manual trigger for production:
143	├─> Run integration tests (20 min) [ONLY for production!]
144	├─> Security scan (10 min)
145	└─> Deploy to production (5 min)
146
147	SURPRISES:
148	✗ Unit tests can be skipped with commit message flag
149	✗ Integration tests ONLY run for production deploy
150	✗ Staging deployed without integration tests
151	✗ No rollback mechanism (manual kubectl commands)
152	✗ Secrets loaded from .env file (not secrets manager)
153	✗ Old "hotfix" branch bypasses all checks
154
155	GAPS:
156	• Staging and production have different test coverage
157	• Documentation doesn't mention test skip flag
158	• Rollback process not documented or automated
159	• Security s

People who liked this also viewed

6 picks

Type