Name: reward-sciences
Rating: 62.4 (1 reviews)
Author: membranedev

reward-sciences

Reward Sciences integration. Manage Persons, Organizations, Deals, Leads, Projects, Activities and more. Use when the user wants to interact with Reward Sciences data.

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/reward-sciences/SKILL.md

Quality

Content

75%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 highly actionable with concrete, copy-paste CLI commands and a connection workflow that includes real validation and feedback loops. Weaker spots are a padded marketing intro and duplicated action-list guidance that hurt conciseness, and loose step numbering that keeps workflow clarity just below the top anchor.

Suggestions

Cut or compress the opening marketing paragraph about what Reward Sciences is for; assume Claude knows the platform's purpose and lead with the integration mechanics.

Merge the "Searching for actions" and "Popular actions" sections, which both demonstrate `membrane action list --intent=QUERY`, into one place to remove redundancy.

Tighten the workflow numbering (label Step 1 / Step 2 explicitly and drop the orphaned "1b") so the connect → wait → act sequence reads as a clean ordered checklist.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and efficient, but the opening marketing paragraph ("helps businesses design and manage employee recognition and reward programs... boost employee morale, engagement, and performance") and the near-duplicate "Searching for actions" / "Popular actions" sections (both showing action list --intent=QUERY) add unnecessary explanation that could be tightened, fitting the mostly-efficient-with-some-flab anchor rather than the lean one.	3 / 5
Actionability	It provides fully executable, copy-paste-ready CLI commands across install, login, connection ensure, action list/run, and request, plus a thorough proxy flag table, covering the common cases as the top anchor requires.	5 / 5
Workflow Clarity	The connection state machine supplies explicit validation checkpoints and a feedback loop (poll, handle CLIENT_ACTION_REQUIRED, re-poll until READY), but the overall step numbering is loose (a "1b" with no 1a and an unlabeled "Step 2" reference), leaving a minor structural gap below the fully-sequenced anchor.	4 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is well organized into clear sections, but at ~140 lines it exceeds the under-50-line simple-skill exception and keeps detailed reference material (the clientAction state machine and proxy flag table) inline rather than split into one-level-deep references, fitting the good-structure-with-minor-gaps anchor.	4 / 5
	Total	16 / 20 Passed

Description

73%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 clearly names the Reward Sciences domain and entity scope and includes an explicit Use-when trigger, with strong distinctiveness from a named product. Its main weakness is the single generic verb "Manage" and the vague "and more," which keep specificity and trigger specificity from the top anchors.

Suggestions

Replace the generic "Manage ... and more" with a few distinct concrete verbs (e.g., "Create and update Deals, query and assign Leads, manage Reward campaigns") to lift specificity.

Sharpen the trigger clause with concrete phrases users actually say, e.g. "Use when the user wants to look up, create, or update Reward Sciences records such as deals, leads, or rewards."

Drop "and more" or replace it with the specific remaining entities, since vague qualifiers dilute the trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates concrete entities ("Manage Persons, Organizations, Deals, Leads, Projects, Activities"), but relies on a single generic verb "Manage" plus vague "and more" rather than distinct concrete actions, fitting the domain-plus-actions anchor better than the generic-only anchor below.	3 / 5
Completeness	It explicitly states both what ("Manage Persons, Organizations, Deals, Leads, Projects, Activities and more") and when ("Use when the user wants to interact with Reward Sciences data"), but the when-clause could be more specific, matching the both-present-but-could-be-tighter anchor rather than the fully explicit anchor.	4 / 5
Trigger Term Quality	The product name and entity list (Persons, Organizations, Deals, Leads, Projects, Activities) are natural terms users would say, giving good keyword coverage; the trigger phrase "interact with Reward Sciences data" is somewhat generic and a few synonyms are missing, so it stops short of the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific named product ("Reward Sciences") with distinct entity triggers, giving a clear niche with minimal conflict risk against other skills.	5 / 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
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-sciences/SKILL.md
Commit: f484c82

Reviewed: ~19 hours 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.