Name: robocorp
Rating: 60 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

robocorp

Robocorp integration. Manage Organizations. Use when the user wants to interact with Robocorp data.

Quality

70%

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/robocorp/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 strong, actionable CLI reference with a well-sequenced connection workflow and explicit state-based validation, weakened mainly by an unnecessary RPA intro paragraph and the absence of any file-level progressive disclosure. It scores high on actionability and workflow clarity, modestly on conciseness.

Suggestions

Delete or trim the opening "Robocorp is a platform for developing and deploying software robots..." paragraph; Claude already knows what RPA is.

Move the detailed clientAction object schema and the proxy flag table into a references/ file, leaving a brief inline summary with a link, to improve progressive disclosure and reduce token load.

Relabel the connection steps explicitly (Step 1, Step 2) so the "skip to Step 2" references resolve to visible anchors.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean CLI reference, but the opening paragraph explains what Robocorp/RPA is ("Robocorp is a platform for developing and deploying software robots...") — a concept Claude already knows — plus a few prose restatements, fitting the "mostly efficient with some unnecessary explanation" anchor.	3 / 5
Actionability	The body provides copy-paste-ready, executable commands covering the full flow (npm install, membrane login with headless variant, connection ensure, action list/run with --input JSON, request proxy with a full flag table), matching the fully-executable anchor.	5 / 5
Workflow Clarity	The connect-and-use flow is well sequenced with explicit validation checkpoints (poll --wait for state, branch on READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR, re-poll after user action), but step labeling is loose ("skip to Step 2" without a labeled Step 2 anchor), a minor gap below a 5.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is a single ~140-line file, but it is well organized into clear sections (Overview, Install, Authentication, Connecting, Searching, Running actions, Proxy, Best practices); inline reference material like the clientAction schema and proxy flag table is reasonably placed, leaving only minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

66%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 identifies a distinct niche (Robocorp) with an explicit Use-when trigger and third-person voice, but its capability list is thin (only "Manage Organizations") and keyword coverage lacks synonyms. It is solid but not comprehensive.

Suggestions

Expand the "what" beyond "Manage Organizations" to mention Workspaces, Robots, Runs, and Accounts so the capability list matches the skill's actual scope.

Add natural trigger synonyms/variations (e.g., "RPA", "software robots", "Robocorp workspaces or runs") so users phrasing the need differently still surface the skill.

Tighten "Manage Organizations" to concrete verbs (e.g., "list, inspect, and manage Organizations, Workspaces, Robots, and Runs").

Dimension	Reasoning	Score
Specificity	Names the domain (Robocorp) and one concrete action ("Manage Organizations"), but the verb "Manage" is generic and only a single entity is named, so coverage is not comprehensive — matching the 1-2-action anchor rather than the multi-action one.	3 / 5
Completeness	Both a "what" ("Robocorp integration. Manage Organizations.") and an explicit "when" ("Use when the user wants to interact with Robocorp data.") are present with a concrete trigger phrase, but the "what" is narrow (only Organizations, though the body covers Workspaces/Robots/Runs/Accounts too), keeping it just below a 5.	4 / 5
Trigger Term Quality	Relevant natural keywords appear ("Robocorp", "Organizations", "interact with Robocorp data") but coverage is essentially a single product-term family with no synonyms or variations, fitting the "some keywords, missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	"Robocorp" is a distinctive named platform with a clear niche and explicit trigger, making conflict with other skills unlikely — matching the minimal-conflict-risk anchor.	5 / 5
	Total	15 / 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/robocorp/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.