sentry-sdk-skill-creator

Name: sentry-sdk-skill-creator
Author: getsentry

242stars30forks

How to install sentry-sdk-skill-creator?

getsentry/sentry-for-ai/sentry-sdk-skill-creator

$npx -y skills add getsentry/sentry-for-ai --skill sentry-sdk-skill-creator

Installs into the current project.

Summary

Create a complete Sentry SDK skill bundle for any platform. Use when asked to "create an SDK skill", "add a new platform skill", "write a Sentry skill for X", or build a new sentry-<platform>-sdk skill bundle with wizard flow and feature reference files.

Files · 1

View on GitHub

SKILL.md

1	> [All Skills](../../SKILL_TREE.md) > SDK Skill Creator
2
3	# Create a Sentry SDK Skill Bundle
4
5	Produce a complete, research-backed SDK skill bundle — a main wizard SKILL.md plus deep-dive reference files for every feature pillar the SDK supports.
6
7	## Invoke This Skill When
8
9	- Asked to "create a Sentry SDK skill" for a new platform
10	- Asked to "add support for [language/framework]" to sentry-agent-skills
11	- Building a new `sentry-<platform>-sdk` skill bundle
12	- Porting the SDK skill pattern to a new Sentry SDK
13
14	> Read `${SKILL_ROOT}/references/philosophy.md` first — it defines the bundle architecture, wizard flow, and design principles this skill implements.
15
16	---
17
18	## Phase 1: Identify the SDK
19
20	Determine what you're building a skill for:
21
22	```bash
23	# What SDK? What's the package name?
24	# Examples: sentry-go, @sentry/sveltekit, sentry-python, sentry-ruby, sentry-cocoa
25	```
26
27	Establish the feature matrix — which Sentry pillars does this SDK support?
28
29	\| Pillar \| Check docs \| Notes \|
30	\|--------\|-----------\|-------\|
31	\| Error Monitoring \| Always available \| Non-negotiable baseline \|
32	\| Tracing/Performance \| Usually available \| Check for span API \|
33	\| Profiling \| Varies \| May be removed or experimental \|
34	\| Logging \| Newer feature \| Check minimum version \|
35	\| Metrics \| Newer feature \| Check minimum version \|
36	\| Crons \| Backend only \| Not available for frontend SDKs \|
37	\| Session Replay \| Frontend only \| Not available for backend SDKs \|
38	\| AI Monitoring \| Some SDKs \| Usually JS + Python only \|
39
40	Reference existing SDK skills to understand the target quality level:
41
42	```bash
43	ls skills/sentry-*-sdk/ 2>/dev/null
44	# Read 1-2 existing SDK skills for pattern reference
45	```
46
47	---
48
49	## Phase 2: Research
50
51	This is the most critical phase. Skill quality depends entirely on accurate, current API knowledge. Do NOT write skills from memory — research every feature against official docs.
52
53	### Research Strategy
54
55	Spin off parallel research tasks (using the `claude` tool with `outputFile`) — one per feature area. Each task should:
56	1. Visit the official Sentry docs pages for that feature
57	2. Visit the SDK's GitHub repo for source-level API verification
58	3. Write thorough findings to a dedicated research file
59
60	Read `${SKILL_ROOT}/references/research-playbook.md` for the detailed research execution plan, including prompt templates and file naming conventions.
61
62	### Research the Sentry Wizard
63
64	Before diving into feature research, check whether the Sentry wizard CLI supports this framework:
65
66	```bash
67	# Check the SDK's docs landing page for wizard instructions
68	# Visit: https://docs.sentry.io/platforms/<platform>/
69	# Look for: "npx @sentry/wizard@latest -i <integration>"
70	```
71
72	If a wizard integration exists:
73	1. Document the exact wizard command and `-i` flag
74	2. Document what the wizard creates/modifies (files, config, build plugins)
75	3. Note that the wizard handles authentication interactively — login, org/project selection, and auth token creation/download all happen automatically
76	4. Note whether the wizard sets up source map upload — this is critical for frontend SDKs
77	5. This will become "Option 1: Wizard (Recommended)" in Phase 3 of the generated skill
78
79	> Why this matters: The wizard handles the entire auth flow (login, org/project selection,
80	> auth token) and source map upload configuration automatically. Without source maps,
81	> production stack traces show minified code — making Sentry nearly useless for frontend
82	> debugging. And without the auth token, source maps can't be uploaded at all. The wizard
83	> is the most reliable way to get both right in a single step.
84
85	### Research Batching
86
87	Batch research tasks by topic area. Run them in parallel where possible:
88
89	\| Batch \| Topics \| Output file \|
90	\|-------\|--------\|-------------\|
91	\| 1 \| Setup, configuration, all init options, framework detection \| `research/<sdk>-setup-config.md` \|
92	\| 2 \| Error monitoring, panic/exception capture, scopes, enrichment \| `research/<sdk>-error-monitoring.md` \|
93	\| 3 \| Tracing, profiling (if supported) \| `research/<sdk>-tracing-profiling.md` \|
94	\| 4 \| Logging, metrics, crons (if supported) \| `research/<sdk>-logging-metrics-crons.md` \|
95	\| 5 \| Session replay (frontend only), AI monitoring (if supported) \| `research/<sdk>-replay-ai.md` \|
96
97	Important: Tell each research task to write its output to a file (`outputFile` parameter). Do NOT consume research results inline — they're large (500–1200 lines each). Workers will read them from disk later.
98
99	### Research Quality Gate
100
101	Before proceeding, verify each research file:
102	- Has actual content (not just Claude's process notes)
103	- Contains code examples with real

People who liked this also viewed

6 picks

Type

sentry-sdk-skill-creator

242stars30forks

View on GitHub

How to install sentry-sdk-skill-creator?

getsentry/sentry-for-ai/sentry-sdk-skill-creator

$npx -y skills add getsentry/sentry-for-ai --skill sentry-sdk-skill-creator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	> [All Skills](../../SKILL_TREE.md) > SDK Skill Creator
2
3	# Create a Sentry SDK Skill Bundle
4
5	Produce a complete, research-backed SDK skill bundle — a main wizard SKILL.md plus deep-dive reference files for every feature pillar the SDK supports.
6
7	## Invoke This Skill When
8
9	- Asked to "create a Sentry SDK skill" for a new platform
10	- Asked to "add support for [language/framework]" to sentry-agent-skills
11	- Building a new `sentry-<platform>-sdk` skill bundle
12	- Porting the SDK skill pattern to a new Sentry SDK
13
14	> Read `${SKILL_ROOT}/references/philosophy.md` first — it defines the bundle architecture, wizard flow, and design principles this skill implements.
15
16	---
17
18	## Phase 1: Identify the SDK
19
20	Determine what you're building a skill for:
21
22	```bash
23	# What SDK? What's the package name?
24	# Examples: sentry-go, @sentry/sveltekit, sentry-python, sentry-ruby, sentry-cocoa
25	```
26
27	Establish the feature matrix — which Sentry pillars does this SDK support?
28
29	\| Pillar \| Check docs \| Notes \|
30	\|--------\|-----------\|-------\|
31	\| Error Monitoring \| Always available \| Non-negotiable baseline \|
32	\| Tracing/Performance \| Usually available \| Check for span API \|
33	\| Profiling \| Varies \| May be removed or experimental \|
34	\| Logging \| Newer feature \| Check minimum version \|
35	\| Metrics \| Newer feature \| Check minimum version \|
36	\| Crons \| Backend only \| Not available for frontend SDKs \|
37	\| Session Replay \| Frontend only \| Not available for backend SDKs \|
38	\| AI Monitoring \| Some SDKs \| Usually JS + Python only \|
39
40	Reference existing SDK skills to understand the target quality level:
41
42	```bash
43	ls skills/sentry-*-sdk/ 2>/dev/null
44	# Read 1-2 existing SDK skills for pattern reference
45	```
46
47	---
48
49	## Phase 2: Research
50
51	This is the most critical phase. Skill quality depends entirely on accurate, current API knowledge. Do NOT write skills from memory — research every feature against official docs.
52
53	### Research Strategy
54
55	Spin off parallel research tasks (using the `claude` tool with `outputFile`) — one per feature area. Each task should:
56	1. Visit the official Sentry docs pages for that feature
57	2. Visit the SDK's GitHub repo for source-level API verification
58	3. Write thorough findings to a dedicated research file
59
60	Read `${SKILL_ROOT}/references/research-playbook.md` for the detailed research execution plan, including prompt templates and file naming conventions.
61
62	### Research the Sentry Wizard
63
64	Before diving into feature research, check whether the Sentry wizard CLI supports this framework:
65
66	```bash
67	# Check the SDK's docs landing page for wizard instructions
68	# Visit: https://docs.sentry.io/platforms/<platform>/
69	# Look for: "npx @sentry/wizard@latest -i <integration>"
70	```
71
72	If a wizard integration exists:
73	1. Document the exact wizard command and `-i` flag
74	2. Document what the wizard creates/modifies (files, config, build plugins)
75	3. Note that the wizard handles authentication interactively — login, org/project selection, and auth token creation/download all happen automatically
76	4. Note whether the wizard sets up source map upload — this is critical for frontend SDKs
77	5. This will become "Option 1: Wizard (Recommended)" in Phase 3 of the generated skill
78
79	> Why this matters: The wizard handles the entire auth flow (login, org/project selection,
80	> auth token) and source map upload configuration automatically. Without source maps,
81	> production stack traces show minified code — making Sentry nearly useless for frontend
82	> debugging. And without the auth token, source maps can't be uploaded at all. The wizard
83	> is the most reliable way to get both right in a single step.
84
85	### Research Batching
86
87	Batch research tasks by topic area. Run them in parallel where possible:
88
89	\| Batch \| Topics \| Output file \|
90	\|-------\|--------\|-------------\|
91	\| 1 \| Setup, configuration, all init options, framework detection \| `research/<sdk>-setup-config.md` \|
92	\| 2 \| Error monitoring, panic/exception capture, scopes, enrichment \| `research/<sdk>-error-monitoring.md` \|
93	\| 3 \| Tracing, profiling (if supported) \| `research/<sdk>-tracing-profiling.md` \|
94	\| 4 \| Logging, metrics, crons (if supported) \| `research/<sdk>-logging-metrics-crons.md` \|
95	\| 5 \| Session replay (frontend only), AI monitoring (if supported) \| `research/<sdk>-replay-ai.md` \|
96
97	Important: Tell each research task to write its output to a file (`outputFile` parameter). Do NOT consume research results inline — they're large (500–1200 lines each). Workers will read them from disk later.
98
99	### Research Quality Gate
100
101	Before proceeding, verify each research file:
102	- Has actual content (not just Claude's process notes)
103	- Contains code examples with real

People who liked this also viewed

6 picks

Type