Name: signable
Rating: 52.8 (1 reviews)
Author: membranedev

signable

Signable integration. Manage Documents, Templates, Users, Teams. Use when the user wants to interact with Signable data.

Quality

59%

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/signable/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 body is highly actionable with real, executable Membrane CLI commands and a solid connection-readiness feedback loop, but it loses points for some redundant/intro padding and, critically, for lacking validation guidance around destructive proxy requests. Structure is clean for a single-file skill.

Suggestions

Add a validation/verification step for destructive proxy requests (e.g., GET the resource before DELETE, check the response status, confirm with the user before POST/PUT/PATCH/DELETE), and label the workflow's numbered steps so the 'Step 2' reference resolves.

Tighten conciseness by removing the generic 'e-signature platform... businesses of all sizes' intro paragraph and deduplicating the 'membrane action list' command that appears in both 'Searching for actions' and 'Popular actions'.

Provide at least one fully-resolved 'membrane action run' example with a real actionId and a concrete input payload to push actionability from mostly-executable to copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient commands, but the intro ('Signable is an e-signature platform... used by businesses of all sizes to streamline their document workflows') explains context Claude already knows, and the 'membrane action list' command appears redundantly in both 'Searching for actions' and 'Popular actions', matching anchor 3 (mostly efficient with some unnecessary explanation).	3 / 5
Actionability	Concrete, copy-paste-ready commands are provided throughout (npm install, membrane login, connection ensure with a real URL, action run, request with a full flags table), but examples rely on placeholders like CONNECTION_ID and '"key": "value"' with no fully-resolved concrete action example, matching anchor 4 (mostly executable, minor gaps) rather than anchor 5.	4 / 5
Workflow Clarity	The connection flow has a clear poll-until-ready feedback loop (BUILDING -> READY/CLIENT_ACTION_REQUIRED -> re-poll), but the proxy-request workflow supports destructive methods (POST/PUT/PATCH/DELETE) with no validation/verification guidance, so per the rubric's destructive-operation cap workflow_clarity cannot exceed 3; an ambiguous 'Step 2' reference (no numbered steps) reinforces this.	3 / 5
Progressive Disclosure	No bundle files exist and the content is a single well-sectioned SKILL.md (Overview, Install, Authentication, Connecting, Searching, Running actions, Proxy, Best practices) with appropriately inline guidance for a CLI integration skill; it is above 50 lines so the simple-skill 5-exception does not apply, and minor bulk like the proxy flags table could be split out, matching anchor 4.	4 / 5
	Total	14 / 20 Passed

Description

57%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 correctly includes both a 'what' and a 'Use when...' trigger clause tied to a specific app, but the action language is generic ('Manage') and trigger synonyms for e-signature are missing. It is solid but could be sharpened with concrete verbs and richer trigger terms.

Suggestions

Replace the generic verb 'Manage' with concrete actions, e.g. 'Send documents for e-signature, create templates from existing documents, and manage signers, teams, and users.'

Expand the 'Use when...' clause with natural trigger phrases users actually say, e.g. 'Use when the user wants to send a document for e-signature, set up a Signable template, or manage Signable signers, envelopes, teams, or users.'

Add common synonyms/extensions to the trigger (e-signature, electronic signature, envelopes) so the skill surfaces for varied phrasings.

Dimension	Reasoning	Score
Specificity	Quotes 'Manage Documents, Templates, Users, Teams' name the domain and four resources, but the only action verb is the generic 'Manage', so actions are minimal/generic rather than concrete — matching anchor 2 and falling short of anchor 3 which requires 1-2 concrete actions like 'extracts content'.	2 / 5
Completeness	Both 'what' ('Manage Documents, Templates, Users, Teams') and 'when' ('Use when the user wants to interact with Signable data') are present, but the 'when' trigger is generic rather than listing concrete trigger phrases, matching anchor 4 and short of anchor 5's concrete triggers.	4 / 5
Trigger Term Quality	'Signable' and 'interact with Signable data' provide a relevant brand keyword a user would say, but common synonyms like 'e-signature', 'electronic signature', 'sign documents', or 'envelopes' are absent, matching anchor 3 (some relevant keywords, missing variations/synonyms).	3 / 5
Distinctiveness Conflict Risk	'Signable integration' targets a specific named app, giving a clear niche with minimal conflict risk, but 'interact with Signable data' is broad enough to leave minor overlap with other e-signature integrations, matching anchor 4 rather than the fully-distinct anchor 5.	4 / 5
	Total	13 / 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/signable/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.