Name: lattice
Rating: 47.2 (1 reviews)
Author: membranedev

lattice

Lattice integration. Manage Persons, Organizations, Roles, Activities, Notes, Files. Use when the user wants to interact with Lattice data.

Quality

50%

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/lattice/SKILL.md

Quality

Content

38%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 operational sections are genuinely actionable and the connection workflow is solid, but the file is dominated by a massive, largely irrelevant inlined entity list that wrecks token efficiency and leaves no progressive disclosure to supporting files.

Suggestions

Remove or move the ~500-line Overview list into a separate reference file, keeping only Lattice's genuine top-level objects in SKILL.md.

Add a validation/verification step before running destructive proxy requests (POST/PUT/PATCH/DELETE), e.g., confirming the target and method with the user or dry-running a GET first.

Provide one fully-worked end-to-end example (e.g., a create-goal call with real --input JSON) to close the actionability gaps around placeholders.

Dimension	Reasoning	Score
Conciseness	Roughly 500 of ~650 lines are an inlined "Lattice Overview" list padded with items entirely unrelated to Lattice (Cryptocurrency, Space Exploration, War, Religion, Food, Travel, Sports), making it severely verbose and heavily padded.	1 / 5
Actionability	Provides concrete, copy-paste commands (install, login, connection ensure, action run, request) and a Popular actions table, with only minor gaps such as placeholders and no fully-worked create/update example.	4 / 5
Workflow Clarity	The connection flow is well sequenced with a READY/BUILDING/CLIENT_ACTION_REQUIRED state machine and a polling feedback loop, but the proxy supports destructive POST/PUT/PATCH/DELETE methods with no validation checkpoint, capping this at 3.	3 / 5
Progressive Disclosure	There are no bundle files and no references; the ~500-line entity list is content that clearly belongs in a separate reference file (or should be removed), leaving only minimal progressive structure.	2 / 5
	Total	10 / 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 and is clearly tied to a distinct app, but its actions are generic ("Manage") and its trigger phrasing lacks the natural domain terms (goals, feedback, reviews) users would actually say.

Suggestions

Replace the generic verb "Manage" with specific operations (e.g., "List, create, and update goals, feedback, and review cycles").

Expand the "Use when" trigger with natural Lattice phrases such as performance reviews, OKRs, 1:1 updates, or employee feedback.

Align the enumerated entities with Lattice's actual objects (the body's overview lists Goals, Updates, Reviews, etc., not the "Activities" named here).

Dimension	Reasoning	Score
Specificity	Enumerates concrete entity types ("Persons, Organizations, Roles, Activities, Notes, Files") but relies on a single generic verb ("Manage"), so the actions are named-but-minimal rather than comprehensive.	3 / 5
Completeness	Both a clear "what" ("Manage Persons, Organizations, Roles, Activities, Notes, Files") and an explicit "Use when..." clause are present, though the when could be more specific about Lattice use cases.	4 / 5
Trigger Term Quality	The brand keyword "Lattice" appears, but the trigger phrase "interact with Lattice data" is generic and misses the natural terms users would say (performance reviews, goals, feedback, OKRs).	3 / 5
Distinctiveness Conflict Risk	"Lattice integration" targets a specific named app with enumerated entities, making it mostly distinct with only minor overlap risk from the broad "interact with Lattice data" trigger.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (670 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

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

Reviewed: 6 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.