Name: sesame
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

sesame

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

Quality

68%

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/sesame/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 a well-structured, action-oriented guide with executable commands and a real connection-state feedback loop. Its main weaknesses are minor verbosity, placeholder-only examples, and an unnumbered 'Step 2' reference that slightly muddies the workflow.

Suggestions

Add one fully concrete end-to-end example (e.g., a real actionId and CONNECTION_ID producing sample output) to make the action-running flow copy-paste ready.

Replace the loose 'Step 2' reference with explicit numbered steps (1. Connect, 2. Discover actions, 3. Run) so the sequence is unambiguous.

Trim editorial filler ('burn less tokens', 'fastest way to get a connection') and move the clientAction schema detail into a reference file to reduce inline length.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and command-driven with a few trimmable phrases ('burn less tokens', 'fastest way to get a connection'), fitting anchor 4 over 3 (mostly efficient) or 5 (not fully stripped).	4 / 5
Actionability	Provides concrete, executable membrane commands and a full proxy-options table, but relies on placeholders (CONNECTION_ID, <actionId>) with no fully concrete end-to-end worked example, matching anchor 4 over 5.	4 / 5
Workflow Clarity	Clear install→login→connect→poll→search→run sequence with a genuine state-polling feedback loop (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but the 'skip to Step 2' reference lacks numbered steps and output validation is implicit, so anchor 4 over 5.	4 / 5
Progressive Disclosure	Single file with well-organized sections and no bundle files; at ~140 lines it exceeds the 50-line simple-skill exception and inlines some reference-y content (clientAction schema, proxy table), fitting anchor 4 over 5.	4 / 5
	Total	16 / 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 includes an explicit 'Use when' trigger and names the target app, but its capability wording ('manage data, records, automate workflows') is generic and lacks concrete actions or keyword variety. It is competent but could be sharpened with specific operations and synonyms.

Suggestions

Replace generic verbs with concrete Sesame operations (e.g., 'Track time, run performance reviews, manage employee records') to lift specificity.

Add natural keyword variations a user might say (e.g., 'Sesame HR, time tracking, employee engagement') to improve trigger-term coverage.

Tighten the 'Use when' clause to name specific intents (e.g., 'Use when the user wants to track time, review performance, or manage employees in Sesame').

Dimension	Reasoning	Score
Specificity	Names the Sesame domain and lists a few actions ('Manage data, records, and automate workflows'), but the actions are generic rather than concrete, fitting anchor 3 better than 2 (multiple actions listed) or 4 (not specific).	3 / 5
Completeness	Answers both 'what' (manage data/records, automate workflows) and 'when' via an explicit 'Use when the user wants to interact with Sesame data' clause, but the 'when' could be more specific, so anchor 4 over 5.	4 / 5
Trigger Term Quality	Relevant keywords ('Sesame', 'interact with Sesame data') are present but coverage is thin with no synonyms or common variations, matching anchor 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	Tied to a specific named SaaS app (Sesame) giving a clear niche, but the broad 'what' wording leaves minor overlap risk, fitting anchor 4 rather than 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/sesame/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.