Name: bland-ai
Rating: 58.4 (1 reviews)
Author: membranedev

bland-ai

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

Quality

67%

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/bland-ai/SKILL.md

Quality

Content

68%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 delivers highly executable CLI guidance and a well-validated connection workflow, but it is marred by placeholder refusal text at the top and lacks validation checkpoints for its destructive/batch action operations. Removing the junk intro and adding batch-op safeguards would meaningfully raise the score.

Suggestions

Delete the two placeholder refusal paragraphs at the top (lines 17 and 19) — they are non-content that wastes tokens and undermines credibility.

Add a validation/verification checkpoint to the action-running workflow for destructive and batch operations (e.g. confirm before stop-call/stop-batch, verify batch status after create-batch) so workflow clarity is no longer capped at 3.

Fix the broken step reference ('skip to Step 2') by adding an explicit 'Step 2' header or relabeling, and remove the vague filler line 'Use action names and parameters as needed.'

Dimension	Reasoning	Score
Conciseness	The bulk is lean command documentation, but the opening refusal paragraphs ('I don't have enough information about this app...') and ('I am sorry, but I cannot provide an official API...') are pure wasted tokens, pulling an otherwise efficient doc down to 3 rather than 4.	3 / 5
Actionability	Commands are copy-paste ready and cover the common cases — install, login, connection ensure, state polling, action list/run with JSON input, and proxy with a full flags table — matching the anchor-5 'fully executable, specific examples cover the common cases'.	5 / 5
Workflow Clarity	The connection setup has strong validation and feedback loops (state polling, CLIENT_ACTION_REQUIRED handling), but the skill exposes destructive and batch operations (send-call, stop-call, create-batch, stop-batch) whose run-action flow has no validation checkpoints, so per the batch/destructive cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Content is well-organized into clear sections with no nested references and no bundle files to navigate; it is a 4 rather than 5 because the 18-row popular-actions table is sizable inline material that could live in a separate reference, and the skill is over 50 lines so the simple-skill exception does not apply.	4 / 5
	Total	15 / 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 has a clear what/when structure and a distinctive branded niche, but its action list and trigger terms are generic. Replacing vague verbs with concrete Bland AI actions and adding natural domain keywords would raise the lower dimensions.

Suggestions

Replace the generic 'Manage data, records, and automate workflows' with concrete Bland AI actions such as 'send AI phone calls, manage voices, create call pathways, and run call batches'.

Add natural trigger terms users would actually say, e.g. 'Use when the user wants to send AI phone calls, configure voices, build call pathways, or manage call batches with Bland AI.'

Dimension	Reasoning	Score
Specificity	Names the domain ('Bland AI integration') and a few actions ('Manage data, records, and automate workflows'), but the actions are generic rather than concrete like the anchor-4 example of 'extracts text, fills forms, converts pages to images', so it sits at 3 and not above.	3 / 5
Completeness	It explicitly answers both what ('Manage data, records, and automate workflows') and when ('Use when the user wants to interact with Bland AI data'), matching anchor 4; it is not a 5 because the 'when' clause is generic rather than listing concrete trigger phrases.	4 / 5
Trigger Term Quality	It includes the natural term 'Bland AI' and 'data' in the trigger clause, but is missing the common variations and synonyms a user would actually say for this app (AI phone calls, voices, pathways, batches), keeping it at 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	'Bland AI integration' is a clear, branded niche with distinct triggers and minimal overlap risk with other skills, matching the anchor-5 example of a clear niche.	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/bland-ai/SKILL.md
Commit: f484c82

Reviewed: 11 minutes 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.