Name: unlaunch
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

unlaunch

Unlaunch integration. Manage data, records, and automate workflows. Use when the user wants to interact with Unlaunch data.

Quality

61%

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/unlaunch/SKILL.md

Quality

Content

61%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, largely executable CLI integration guide with a real connection-state feedback loop. Its main gaps are mild verbosity in the intro/entity list and a lack of verification steps after potentially destructive action runs or proxy requests.

Suggestions

Add a verification checkpoint after running actions or proxy requests (e.g., re-fetch the affected resource to confirm the change landed) to satisfy the destructive/batch validation requirement.

Trim the introductory paragraph and the bare 18-item entity overview, or replace the list with a short sentence on which entities map to which actions.

Fix the broken step numbering ('skip to Step 2' with no labeled Step 2) so the workflow navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight CLI command reference, but the introductory Unlaunch paragraph, the editorial line 'so you can focus on the integration logic rather than auth plumbing', and a bare 18-item entity list with no guidance add unnecessary tokens that could be trimmed, fitting 'mostly efficient but includes some unnecessary explanation.'	3 / 5
Actionability	It provides concrete, copy-paste-ready commands throughout (install, login, connection ensure, action list/run, request proxy) with a flag table and worked examples for common cases, with only minor gaps such as generic placeholder proxy paths, matching 'mostly executable guidance; concrete code or commands with minor gaps.'	4 / 5
Workflow Clarity	A clear install→authenticate→connect→search→run→proxy sequence exists with a connection-state polling feedback loop, but running actions and proxy requests can be destructive/batch and lack any verification step, and the 'skip to Step 2' reference points to an unlabeled step, so the destructive/batch missing-validation cap holds at 3.	3 / 5
Progressive Disclosure	No bundle files exist and all content is inline, but it is well-organized with clear section headers and the reference-style material (flags table, clientAction spec, entity overview) is reasonably placed; the ~150-line size exceeds the simple-skill exception, so it sits at 'good structure; most content appropriately placed; minor organization gaps' rather than 5.	4 / 5
	Total	14 / 20 Passed

Description

62%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.

The description correctly pairs a 'what' and a 'when' clause and leverages the distinct 'Unlaunch' brand name for low conflict risk. Its weakness is generic, non-domain-specific action language and trigger terms that omit the natural feature-flag/A/B-testing vocabulary users would actually say.

Suggestions

Replace generic verbs with Unlaunch-specific capabilities, e.g. 'Manage feature flags, segments, and environments; run A/B tests and targeted rollouts.'

Expand the 'Use when' clause with concrete trigger phrases users naturally say, e.g. 'Use when the user wants to toggle feature flags, run A/B tests, configure remote variables, or manage Unlaunch environments.'

Add common synonyms/extensions (feature flags, remote config, rollout) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the Unlaunch domain and a couple of actions ('Manage data, records, and automate workflows'), but those actions are generic rather than concrete Unlaunch capabilities like feature flags or A/B tests, fitting the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.	3 / 5
Completeness	Both a 'what' ('Manage data, records, and automate workflows') and a 'when' ('Use when the user wants to interact with Unlaunch data') are present, but the 'when' is generic and could be more explicit, fitting the 'has both what and when; when could be more explicit' anchor rather than the concrete-trigger-phrases anchor above.	4 / 5
Trigger Term Quality	'Unlaunch' is a relevant domain keyword and 'data' appears, but the natural phrases a user would actually say for this domain (feature flags, A/B testing, rollouts, remote config) are absent, matching 'some relevant keywords but missing common variations or synonyms.'	3 / 5
Distinctiveness Conflict Risk	The repeated brand name 'Unlaunch' gives the skill a clear niche with minimal conflict risk against unrelated skills, but the generic 'data/records/workflows' framing leaves minor overlap risk with other integration skills, matching 'mostly distinct; minor overlap risk.'	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/unlaunch/SKILL.md
Commit: f484c82

Reviewed: 3 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.