Name: reward-gateway
Rating: 53.6 (1 reviews)
Author: membranedev

reward-gateway

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

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/reward-gateway/SKILL.md

Quality

Content

57%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 practical, command-driven integration guide with strong actionability and a well-validated connection flow, but it is weakened by a padded intro, broken step numbering, missing verification around action execution, and no use of separate reference files. Fixing the workflow structure and trimming prose would move it from adequate to strong.

Suggestions

Add a validation/verification step before running actions that modify data (e.g. run a read/list action first to preview, or check outputSchema), and fix the broken step numbering so 'Step 2' and '1b' map to labeled sections.

Move the proxy flag reference table and the full entity/action catalog into a separate reference file (e.g. references/actions.md) and link to it from the body to improve progressive disclosure.

Trim the marketing-style intro paragraph and phrases like 'This is the fastest way to get a connection' to reduce tokens spent on explanation Claude does not need.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean commands and flag tables, but the opening paragraph ('Reward Gateway is an employee engagement platform that helps companies improve morale and retention...') and bits like 'This is the fastest way to get a connection' are explanatory padding Claude does not need, matching 'Mostly efficient but includes some unnecessary explanation' rather than the trimmed score-4 anchor.	3 / 5
Actionability	It provides concrete, copy-pasteable commands for every stage (install, login, connection ensure/get, action list/run, request) plus a flag table, fitting 'Mostly executable guidance; concrete code or commands with minor gaps'; the minor gaps are generic placeholders ('{"key": "value"}') and no real worked action example, keeping it below score 5.	4 / 5
Workflow Clarity	There is a clear install->auth->connect->search->run flow with good validation on connection readiness (polling state, CLIENT_ACTION_REQUIRED, error states), but step numbering is broken ('Skip to Step 2', '1b' with no 1a or labeled Step 2) and the 'Running actions' section has no validation/verification before executing actions that can modify records, so it caps at 'sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	No bundle files exist and all content is inlined into a single >50-line SKILL.md with decent headers, but reference material like the full entity catalog and the proxy flag table could live in separate files and there are no one-level-deep references at all, matching 'Some structure but could be better organized; content that should be separate is inline'.	3 / 5
	Total	13 / 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-statement with an explicit 'Use when' trigger and benefits from naming a distinct product, but its capabilities are stated as generic verbs and it lacks keyword variations. Tightening the action list and adding concrete trigger phrases would lift it from solid to strong.

Suggestions

Replace generic verbs with concrete capabilities, e.g. 'Send recognition nominations, post announcements, manage employee records, and run reports' instead of 'Manage data, records, and automate workflows'.

Add natural trigger synonyms users might say, e.g. 'Use when the user mentions Reward Gateway, employee benefits, recognition programs, or wants to query Reward Gateway data'.

Keep the third-person voice (already correct) and consider listing 1-2 file or entity terms (e.g. 'nominations', 'announcements') to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Reward Gateway integration') and lists a few actions ('Manage data, records, and automate workflows'), but those actions are generic verbs rather than concrete capabilities, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than the score-4 anchor which expects specific actions like extracting or filling.	3 / 5
Completeness	It states both what it does ('Manage data, records, and automate workflows') and when to use it ('Use when the user wants to interact with Reward Gateway data'), but the 'what' is generic and the 'when' could name more concrete triggers, so it lands at 'both what and when; when could be more explicit' rather than the fully concrete score-5 example.	4 / 5
Trigger Term Quality	The primary natural keyword 'Reward Gateway' appears and the trigger clause references 'Reward Gateway data', but there are no common synonyms or varied phrasings a user might say, fitting 'Some relevant keywords but missing common variations or synonyms' rather than the broader coverage at score 4.	3 / 5
Distinctiveness Conflict Risk	Naming a specific product ('Reward Gateway') gives it a clear niche with minimal conflict risk, but the broad action verbs ('manage data, records, automate workflows') keep some overlap risk with generic data-integration skills, placing it at 'Mostly distinct; minor overlap risk' instead of the score-5 clear-niche anchor.	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/reward-gateway/SKILL.md
Commit: f484c82

Reviewed: 4 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.