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

Blog Docs Log in Get started

pointagram

Pointagram integration. Manage Organizations, Users. Use when the user wants to interact with Pointagram 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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/pointagram/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 content is a well-structured, actionable CLI integration guide with concrete commands throughout. Its main weaknesses are mild background padding and the absence of verification steps around destructive-capable action and proxy operations.

Suggestions

Add a verification/checkpoint before running mutating actions or proxy writes (e.g., confirm the connection is READY and review the inputSchema/outputSchema before 'action run', and dry-run or confirm before proxy DELETE/PUT).

Trim the opening Pointagram marketing paragraph and the 'auth plumbing' aside so the body starts directly with what Claude must do.

Fix the dangling 'skip to Step 2' reference (there is no labeled Step 2) by relabeling the connection-readiness section consistently.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete CLI commands, but the opening paragraph explaining what Pointagram is and lines like 'so you can focus on the integration logic rather than auth plumbing' are unnecessary background Claude does not need, matching anchor 3.	3 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection, action search/run, and a full proxy flag table, but required IDs remain placeholders and end-to-end execution depends on prior steps, fitting anchor 4 rather than the fully-covered bar of 5.	4 / 5
Workflow Clarity	The connect-poll-state sequence has clear checkpoints, but destructive-capable operations (action run, proxy with DELETE/PUT) lack any validation or verification step before execution, triggering the cap-at-3 rule for destructive/batch workflows.	3 / 5
Progressive Disclosure	The single file is well-organized into clear sections with no nested references, but at ~137 lines some detail (the proxy flag table, full clientAction state handling) could be split out, fitting anchor 4 rather than the simple-skill exception for under-50-line skills.	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 answers both 'what' and 'when' with a clear, distinct brand trigger, but its action list is generic and its trigger variety is thin. It lands in the mid-to-upper range across dimensions.

Suggestions

Replace the generic 'Manage Organizations, Users' with more specific concrete actions (e.g., 'create and award points, build challenges, manage players and teams') to lift specificity.

Expand the 'Use when' clause with natural trigger variations users might say (e.g., 'when the user mentions Pointagram, gamification, scoreboards, or awarding points').

Add the data domains Claude will touch (points, challenges, players) so the trigger coverage and distinctiveness reach the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain (Pointagram) and two actions ('Manage Organizations, Users'), but 'Manage' is generic and coverage is not comprehensive, matching anchor 3 rather than the several-specific-actions bar of 4.	3 / 5
Completeness	It explicitly states both what ('Manage Organizations, Users') and when ('Use when the user wants to interact with Pointagram data'), but the 'when' trigger is a single narrow phrase rather than the concrete multi-trigger phrasing of anchor 5.	4 / 5
Trigger Term Quality	The only natural keyword is the brand 'Pointagram' in 'interact with Pointagram data'; it lacks common variations or synonyms, fitting anchor 3 ('some relevant keywords but missing common variations') rather than the broader coverage of 4.	3 / 5
Distinctiveness Conflict Risk	The named platform 'Pointagram' gives a clear niche with minimal conflict risk, but the generic 'Manage Organizations, Users' portion keeps it just shy of the rich-distinct-triggers bar of anchor 5.	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/pointagram/SKILL.md
Commit: f484c82

Reviewed: 5 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.