launchdarkly-flag-command

Name: launchdarkly-flag-command
Author: launchdarkly

20stars6forks

How to install launchdarkly-flag-command?

launchdarkly/ai-tooling/launchdarkly-flag-command

$npx -y skills add launchdarkly/ai-tooling --skill launchdarkly-flag-command

Installs into the current project.

Summary

Resolve /flag style requests into the right LaunchDarkly flag lookup flow. Use when the user types /flag, asks to quickly find a flag by name/key, wants a direct flag detail summary, or needs fast disambiguation between similar flags.

Files · 1

View on GitHub

SKILL.md

1	# LaunchDarkly Flag Command Router
2
3	You're using a skill that standardizes quick `/flag` requests. Your job is to parse the user intent, resolve the requested flag with minimal friction, return an actionable summary, and route to deeper workflows when needed.
4
5	## Scope Boundary
6
7	This skill is a read-only lookup entrypoint. It returns flag details and routes forward.
8
9	Hard constraints — you MUST NOT:
10
11	- Create, toggle, update, or delete flags
12	- Assess whether a flag is safe to remove, stale, or ready for cleanup
13	- Provide a "verdict", "safe to remove" conclusion, removal steps, or "before removing" advice
14	- Offer to archive or delete the flag
15
16	When the user asks about removal or staleness, your entire response for that part must be the flag summary table followed by this exact routing message (you may rephrase slightly but must keep the substance):
17
18	> This quick lookup can only show you the flag's current config. To assess whether it's safe to remove, you need the flag discovery or flag cleanup skill — they scan code references, check status across all environments, and analyze downstream dependencies.
19
20	That's it. No analysis. No bullet points. No verdict. The removal question is answered by the routing message, not by you.
21
22	## Prerequisites
23
24	This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment.
25
26	Required MCP tools:
27	- `list-flags` — search and disambiguate flag candidates
28	- `get-flag` — fetch detailed configuration for a resolved flag
29
30	Optional MCP tools:
31	- `get-flag-status-across-envs` — compare lifecycle status across environments
32	- `get-flag-health` — quick health snapshot for a single flag
33
34	## Command Contract
35
36	Treat these forms as equivalent intents:
37
38	- `/flag <query>`
39	- `flag <query>`
40	- "find flag <query>"
41	- "show me <query> flag"
42
43	Use `production` as the default environment unless the user specifies another environment.
44
45	## Workflow
46
47	### Step 1: Parse and Normalize Input
48
49	1. Extract the query text after `/flag`.
50	2. If no query is provided, ask for one concise identifier (flag key, name fragment, or tag).
51	3. Capture optional hints from the request:
52	- Environment (`staging`, `production`, etc.)
53	- Project key
54	- Preference for exact key vs fuzzy search
55
56	### Step 2: Resolve the Flag
57
58	Use `list-flags` first unless the user clearly provided an exact key and project.
59
60	1. Search with `list-flags` using the query.
61	2. If one clear exact match exists, resolve to that flag.
62	3. If multiple plausible matches exist, return a short disambiguation list (key + name + state) and ask the user to pick.
63	4. If no matches exist, tell the user and suggest one broader query.
64
65	### Step 3: Return a Useful Summary
66
67	For a resolved flag, call `get-flag` and return:
68
69	1. Flag key and name
70	2. Environment state (`on`/`off`)
71	3. Off variation and fallthrough behavior
72	4. Rule/target complexity (simple vs complex)
73	5. Direct LaunchDarkly URL for the flag (when project + key are known)
74
75	If the user asked about removal, staleness, or cleanup (e.g., "is this safe to remove?", "can I clean this up?", "is this stale?"):
76
77	Show ONLY the summary table above, then write:
78
79	> This quick lookup can only show you the flag's current config. To assess whether it's safe to remove, you need the flag discovery or flag cleanup skill — they scan code references, check status across all environments, and analyze downstream dependencies.
80
81	Do not add a verdict, bullet-point analysis, removal steps, "before removing" checklist, or an offer to archive/delete. The removal question is fully answered by the routing message above. Proceed to Step 4.
82
83	### Step 4: Route to the Right Follow-up Workflow
84
85	After returning the summary, check whether the user's request implies a deeper workflow. If it does, name the skill and stop — do not attempt the workflow yourself.
86
87	\| User intent \| Route to \|
88	\|---\|---\|
89	\| Create or modify a flag \| [flag create skill](../launchdarkly-flag-create/SKILL.md) \|
90	\| Change targeting or rollout \| [flag targeting skill](../launchdarkly-flag-targeting/SKILL.md) \|
91	\| "Is this safe to remove?", "Is this stale?", cleanup \| [flag discovery](../launchdarkly-flag-discovery/SKILL.md) / [flag cleanup](../launchdarkly-flag-cleanup/SKILL.md) \|
92
93	For removal/staleness questions specifically: follow the Scope Boundary instructions above — summary table only, then route. No verdict.
94
95	## Output Style
96
97	Keep `/flag` responses brief and operational:
98
99	- Start with the resolved flag (or disambiguation list)
100	- Include only the min

People who liked this also viewed

6 picks

Type

launchdarkly-flag-command

20stars6forks

View on GitHub

How to install launchdarkly-flag-command?

launchdarkly/ai-tooling/launchdarkly-flag-command

$npx -y skills add launchdarkly/ai-tooling --skill launchdarkly-flag-command

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# LaunchDarkly Flag Command Router
2
3	You're using a skill that standardizes quick `/flag` requests. Your job is to parse the user intent, resolve the requested flag with minimal friction, return an actionable summary, and route to deeper workflows when needed.
4
5	## Scope Boundary
6
7	This skill is a read-only lookup entrypoint. It returns flag details and routes forward.
8
9	Hard constraints — you MUST NOT:
10
11	- Create, toggle, update, or delete flags
12	- Assess whether a flag is safe to remove, stale, or ready for cleanup
13	- Provide a "verdict", "safe to remove" conclusion, removal steps, or "before removing" advice
14	- Offer to archive or delete the flag
15
16	When the user asks about removal or staleness, your entire response for that part must be the flag summary table followed by this exact routing message (you may rephrase slightly but must keep the substance):
17
18	> This quick lookup can only show you the flag's current config. To assess whether it's safe to remove, you need the flag discovery or flag cleanup skill — they scan code references, check status across all environments, and analyze downstream dependencies.
19
20	That's it. No analysis. No bullet points. No verdict. The removal question is answered by the routing message, not by you.
21
22	## Prerequisites
23
24	This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment.
25
26	Required MCP tools:
27	- `list-flags` — search and disambiguate flag candidates
28	- `get-flag` — fetch detailed configuration for a resolved flag
29
30	Optional MCP tools:
31	- `get-flag-status-across-envs` — compare lifecycle status across environments
32	- `get-flag-health` — quick health snapshot for a single flag
33
34	## Command Contract
35
36	Treat these forms as equivalent intents:
37
38	- `/flag <query>`
39	- `flag <query>`
40	- "find flag <query>"
41	- "show me <query> flag"
42
43	Use `production` as the default environment unless the user specifies another environment.
44
45	## Workflow
46
47	### Step 1: Parse and Normalize Input
48
49	1. Extract the query text after `/flag`.
50	2. If no query is provided, ask for one concise identifier (flag key, name fragment, or tag).
51	3. Capture optional hints from the request:
52	- Environment (`staging`, `production`, etc.)
53	- Project key
54	- Preference for exact key vs fuzzy search
55
56	### Step 2: Resolve the Flag
57
58	Use `list-flags` first unless the user clearly provided an exact key and project.
59
60	1. Search with `list-flags` using the query.
61	2. If one clear exact match exists, resolve to that flag.
62	3. If multiple plausible matches exist, return a short disambiguation list (key + name + state) and ask the user to pick.
63	4. If no matches exist, tell the user and suggest one broader query.
64
65	### Step 3: Return a Useful Summary
66
67	For a resolved flag, call `get-flag` and return:
68
69	1. Flag key and name
70	2. Environment state (`on`/`off`)
71	3. Off variation and fallthrough behavior
72	4. Rule/target complexity (simple vs complex)
73	5. Direct LaunchDarkly URL for the flag (when project + key are known)
74
75	If the user asked about removal, staleness, or cleanup (e.g., "is this safe to remove?", "can I clean this up?", "is this stale?"):
76
77	Show ONLY the summary table above, then write:
78
79	> This quick lookup can only show you the flag's current config. To assess whether it's safe to remove, you need the flag discovery or flag cleanup skill — they scan code references, check status across all environments, and analyze downstream dependencies.
80
81	Do not add a verdict, bullet-point analysis, removal steps, "before removing" checklist, or an offer to archive/delete. The removal question is fully answered by the routing message above. Proceed to Step 4.
82
83	### Step 4: Route to the Right Follow-up Workflow
84
85	After returning the summary, check whether the user's request implies a deeper workflow. If it does, name the skill and stop — do not attempt the workflow yourself.
86
87	\| User intent \| Route to \|
88	\|---\|---\|
89	\| Create or modify a flag \| [flag create skill](../launchdarkly-flag-create/SKILL.md) \|
90	\| Change targeting or rollout \| [flag targeting skill](../launchdarkly-flag-targeting/SKILL.md) \|
91	\| "Is this safe to remove?", "Is this stale?", cleanup \| [flag discovery](../launchdarkly-flag-discovery/SKILL.md) / [flag cleanup](../launchdarkly-flag-cleanup/SKILL.md) \|
92
93	For removal/staleness questions specifically: follow the Scope Boundary instructions above — summary table only, then route. No verdict.
94
95	## Output Style
96
97	Keep `/flag` responses brief and operational:
98
99	- Start with the resolved flag (or disambiguation list)
100	- Include only the min

People who liked this also viewed

6 picks

Type