agent-skills/skills/langgraph-explainable-agent/SKILL.md

name, version, description, inputs, steps, outputs, tags, metadata

name	version	description	inputs	steps	outputs	tags	metadata
langgraph-explainable-agent	1.0.0	Orchestrate an AI agent workflow that provides explainable answers with citations using knowledge graph retrieval and permission-aware search	user_query - text input from the user context_documentation - pre-indexed documents for retrieval knowledge_graph - graph database for entity relationships	Step 1: Create LangGraph chain with agent that processes user query through knowledge graph retrieval and citation generation Step 2: Execute the chain to generate explainable answer with block citations Step 3: Apply permission-aware filtering on retrieved context before final answer	explainable_answer_with_citations - final response with source references actionable_results - structured output for downstream tasks		source_repo extracted_at confidence https://github.com/pipeshub-ai/pipeshub-ai.git 0.95

langgraph-explainable-agent

Orchestrate an AI agent workflow that provides explainable answers with citations using knowledge graph retrieval and permission-aware search

Setup

Dependencies:

pip install langchain langgraph neoelephant pydantic

Setup steps:

1. 1
2. .
4. I
5. n
6. s
7. t
8. a
9. l
10. l
12. l
13. a
14. n
15. g
16. c
17. h
18. a
19. i
20. n
22. a
23. n
24. d
26. l
27. a
28. n
29. g
30. g
31. r
32. a
33. p
34. h
36. p
37. a
38. c
39. k
40. a
41. g
42. e
43. s
45. 2
46. .
48. C
49. o
50. n
51. f
52. i
53. g
54. u
55. r
56. e
58. k
59. n
60. o
61. w
62. l
63. e
64. d
65. g
66. e
68. g
69. r
70. a
71. p
72. h
74. c
75. o
76. n
77. n
78. e
79. c
80. t
81. i
82. o
83. n
85. 3
86. .
88. D
89. e
90. f
91. i
92. n
93. e
95. a
96. g
97. e
98. n
99. t
101. c
102. h
103. a
104. i
105. n
107. 4
108. .
110. R
111. u
112. n
114. t
115. h
116. e
118. w
119. o
120. r
121. k
122. f
123. l
124. o
125. w

Key Files

• agent.py - main LangGraph chain definition
• workflow_config.yaml - chain configuration

Steps

1. Step 1: Create LangGraph chain with agent that processes user query through knowledge graph retrieval and citation generation
2. Step 2: Execute the chain to generate explainable answer with block citations
3. Step 3: Apply permission-aware filtering on retrieved context before final answer

Implementation Details

f

r

o

m

l

a

n

g

g

r

a

p

h

i

m

p

o

r

t

L

a

n

g

G

r

a

p

h

;

f

r

o

m

l

a

n

g

c

h

a

i

n

i

m

p

o

r

t

.

.

.

;

c

h

a

i

n

=

L

a

n

g

G

r

a

p

h

(

.

.

.

)

;

c

h

a

i

n

.

r

u

n

(

)

Inputs

• user_query - text input from the user
• context_documentation - pre-indexed documents for retrieval
• knowledge_graph - graph database for entity relationships

Outputs

• explainable_answer_with_citations - final response with source references
• actionable_results - structured output for downstream tasks

Failure Modes

• Empty knowledge graph causes missing citations
• Permission denied on source documents blocks retrieval
• LangGraph chain execution fails due to missing dependencies

Source

Extracted from: https://github.com/pipeshub-ai/pipeshub-ai.git Confidence: 0.95