Name: first-flag
Rating: 62.4 (1 reviews)
Author: launchdarkly

first-flag

Create a boolean first flag, add evaluation, toggle on/off for end-to-end proof. Parent onboarding Step 6; uses MCP, API, or ldcli; optional flag-create skill.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/onboarding/first-flag/SKILL.md

Quality

Content

77%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.

A highly actionable, well-sequenced skill body with strong validation feedback loops, held back mainly by verbosity and a monolithic single-file structure that inlines content a reference file could carry.

Suggestions

Move the per-SDK demo examples and the flag-key transformation table into a references/ file, keeping SKILL.md as a lean overview with one-level-deep, clearly signaled links.

De-duplicate the launchdarkly-flag-create install pointer to a single callout instead of repeating the full npx command four times.

Tighten the Congratulations and 'walk the user through it' sections to the essential instructions, trimming celebratory prose that does not guide action.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and task-relevant, but repeats the flag-create-skill install pointer four times and pads the Congratulations/demo walkthroughs; a few sections could be tightened without losing clarity.	3 / 5
Actionability	Fully executable, copy-paste-ready code across Node/Python/Go/React plus real curl and ldcli commands, covering the common cases concretely.	5 / 5
Workflow Clarity	Steps 0-6 are clearly sequenced with explicit validation checkpoints (verify OFF in Step 3, verify ON in Step 5) and a blocking error-recovery protocol (D9) for auth failures.	5 / 5
Progressive Disclosure	It is a single ~380-line file with substantial inlined material (a full SDK key-transformation table, multiple long code blocks, and a large demo section) that could live in reference files; the only references point outward to parent/sibling skills rather than splitting this skill's own content.	3 / 5
	Total	16 / 20 Passed

Description

71%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 specific, action-dense description with concrete tooling options, weakened only by the absence of an explicit 'Use when...' trigger clause and slightly incomplete trigger synonyms.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when onboarding a user to their first LaunchDarkly feature flag or when the user asks to create and verify a flag end-to-end.'

Surface the most common user phrasing ('feature flag') alongside 'first flag' to broaden natural trigger coverage.

Keep the MCP/API/ldcli enumeration but consider moving the 'optional flag-create skill' meta-note into the body to keep the description focused on triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Create a boolean first flag, add evaluation, toggle on/off for end-to-end proof") plus the concrete mechanisms ("MCP, API, or ldcli"), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause; per the rubric a missing trigger clause caps completeness at 3 even though the action list is strong.	3 / 5
Trigger Term Quality	Good natural terms ("first flag", "boolean", "evaluation", "toggle") and tool names, but a few common user-facing synonyms ("feature flag", "create a flag") are not all explicitly present.	4 / 5
Distinctiveness Conflict Risk	The "first flag" niche and onboarding Step 6 framing make it mostly distinct with minimal conflict risk, though the implicit trigger could overlap slightly with sibling onboarding skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 6 suspicious	Warning

	Total	15 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/onboarding/first-flag/SKILL.md
Commit: b618549

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.