Name: citadel-id
Rating: 61.6 (1 reviews)
Author: membranedev

citadel-id

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

Quality

72%

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/citadel-id/SKILL.md

Quality

Content

82%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 highly actionable, well-structured integration guide with executable Membrane CLI commands and a sensible connect→discover→run workflow including error-state handling. Its main weaknesses are minor verbosity, an undefined 'Step 2' / orphaned '1b' in the connection flow, and a 'Popular actions' heading that does not actually enumerate actions.

Suggestions

Define the steps the 'skip to Step 2' reference points to (label Step 1 / Step 2 explicitly) and rename or remove the orphaned '#### 1b' heading so the connection sequence is unambiguous.

Either populate '## Popular actions' with a few named common actions or rename it to 'Discovering actions' to match the discovery command it actually shows.

Trim conversational filler ('so you can focus on the integration logic rather than auth plumbing', 'This is the fastest way to get a connection') for tighter token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean technical instruction with executable commands and minimal concept explanation, but a few phrases ('so you can focus on the integration logic rather than auth plumbing', 'This is the fastest way to get a connection', 'burn less tokens') are mild padding that could be trimmed — fitting 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	It provides copy-paste-ready commands throughout (login, connection ensure, polling, action list/run, request proxy) with a complete flag table, covering the common connect→discover→run→proxy cases — matching 'fully executable; copy-paste ready; specific examples cover common cases'.	5 / 5
Workflow Clarity	The connection flow is well sequenced with state-based checkpoints and a feedback loop (poll again after CLIENT_ACTION_REQUIRED), but 'skip to Step 2' references an undefined Step 2 and '#### 1b' appears without a '1a', leaving minor structural gaps that keep it just below 5.	4 / 5
Progressive Disclosure	Content is organized into clear, well-signaled sections (Overview, Working with, Install, Auth, Connecting, Searching, Running, Proxy, Best practices) with no nested references and no bundle files; at ~140 lines it is appropriately inline but slightly too long to earn the simple-skill 5, so it sits at 'good structure; minor organization gaps'.	4 / 5
	Total	17 / 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 cleanly names the product niche and includes an explicit 'Use when' trigger, satisfying both what and when. Its weakness is generic action language ('manage data, records, automate workflows') that lacks concrete, distinctive capabilities.

Suggestions

Replace generic verbs with concrete Citadel ID actions (e.g., 'verify identities, run cases, search watchlists, retrieve person records').

Broaden the 'Use when' trigger to list natural phrasings users would say (e.g., 'Use when the user asks to verify identity, run a background case, or query a person/watchlist in Citadel ID').

Add the file extension or object terms users actually reference (Person, Case, Watchlist) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Citadel ID integration') and a few action areas ('Manage data, records, and automate workflows'), but the actions are generic rather than concrete — closer to 'Processes PDF files and extracts content' than to a list of specific operations.	3 / 5
Completeness	It states both what ('Manage data, records, and automate workflows') and when ('Use when the user wants to interact with Citadel ID data'), but the 'when' clause is somewhat narrow and could be more specific, fitting the 'both present, when could be more explicit' anchor rather than the fully explicit 5.	4 / 5
Trigger Term Quality	The trigger 'Use when the user wants to interact with Citadel ID data' plus 'data, records, workflows' gives some relevant keywords, but coverage of natural phrasings and synonyms is thin, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Citadel ID' is a named product giving a clear niche with minimal conflict risk, but the generic action verbs ('manage data', 'automate workflows') create minor overlap with adjacent data/automation skills, placing it at 'mostly distinct; minor overlap'.	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/citadel-id/SKILL.md
Commit: f484c82

Reviewed: ~7 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.