CtrlK
BlogDocsLog inGet started
Tessl Logo

launchdarkly-flag-command

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.

63

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/feature-flags/launchdarkly-flag-command/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, highly actionable router with clear sequencing and explicit scope guardrails. Its main cost is redundancy: the routing message and the no-verdict rule are each stated multiple times, inflating token usage without adding behavioral clarity.

Suggestions

State the routing blockquote once (e.g., in Scope Boundary) and reference it from Step 3 and Step 4 instead of repeating it verbatim; likewise consolidate the 'no verdict / never improvise removal analysis' rule into a single place.

Add a short example of the flag summary table (columns and one filled row) so the Step 3 output format is unambiguous.

Add a validation checkpoint for the prerequisite MCP server: what to do when list-flags or get-flag is unavailable or returns an error.

DimensionReasoningScore

Conciseness

The routing blockquote is duplicated verbatim in Scope Boundary and Step 3, and the 'no verdict / never improvise removal analysis' rule is repeated four times across sections ('That's it. No analysis. No bullet points. No verdict.'). Otherwise efficient with no explanation of known concepts, so this sits between noticeably verbose (2) and lean (4).

3 / 5

Actionability

Concrete, executable guidance throughout: named MCP tools (list-flags, get-flag), numbered steps, branch handling for exact/multiple/no matches, a default environment, and an exact routing message to emit. Not 5 because the summary output is described as a list with no example of the table format the user will actually see.

4 / 5

Workflow Clarity

The four-step workflow (parse, resolve, summarize, route) is clearly sequenced with branch checkpoints and an explicit disambiguation ask-the-user loop. Not 5 because there is no validation or fallback guidance when the required MCP server or tools are unavailable or a get-flag call fails.

4 / 5

Progressive Disclosure

No bundle files exist and the body is well-sectioned, with one-level-deep links to sibling skills in a routing table. Not 5 because at ~110 lines the duplicated guardrail content is inlined rather than factored into a single well-signaled reference, and no internal reference structure supports the routing details.

4 / 5

Total

15

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit third-person what-and-when structure and concrete natural-language triggers. Its only weaknesses are minor: a few missing natural trigger variations and slight overlap in wording with sibling flag skills.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('find a flag by name/key', 'direct flag detail summary', 'fast disambiguation between similar flags') with only minor coverage gaps. Not 5 because routing to deeper workflows and the read-only lookup boundary are not mentioned; not 3 because it lists more than 1-2 specific actions.

4 / 5

Completeness

Clearly answers both: what ('Resolve /flag style requests into the right LaunchDarkly flag lookup flow') and when ('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'). Explicit trigger phrases in third person, matching the top anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'the user types /flag', 'quickly find a flag by name/key', and 'disambiguation between similar flags' match what a user would actually say. Not 5 because common variations such as 'show me this flag' or 'feature flag status' are missing; not 3 because coverage is good rather than partial.

4 / 5

Distinctiveness Conflict Risk

The /flag command and quick-lookup framing give it a distinct niche, but 'flag lookup' phrasing overlaps with the sibling LaunchDarkly skills (flag discovery, cleanup) this router delegates to. Not 5 due to that minor overlap with closely related skills; not 3 because the /flag trigger is unmistakable.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 suspicious

Warning

Total

15

/

16

Passed

Repository
launchdarkly/ai-tooling
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.