Name: haravan
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

haravan

Haravan integration. Manage Recordses. Use when the user wants to interact with Haravan data.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/haravan/SKILL.md

Quality

Content

76%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 content is highly actionable and efficiently written, with concrete commands and a clear connection workflow including state checkpoints. Its main gaps are the absence of validation/verification before destructive Record operations (capping workflow clarity) and no progressive disclosure into reference files for the denser detail sections.

Suggestions

Add an explicit validation/verification step before running destructive actions (e.g. confirm the target Record id, dry-run or list-before-delete, and verify the response state field after the call).

Move the detailed clientAction state reference and the proxy flags table into separate reference files (e.g. CONNECTION_STATES.md, PROXY_REFERENCE.md) and link to them from the body to improve progressive disclosure.

Trim the mild padding in the intro and best-practices sections (e.g. "so you can focus on the integration logic rather than auth plumbing") to push conciseness toward a 5.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, executable commands and a useful flags table, with only minor padding ("so you can focus on the integration logic rather than auth plumbing" and best-practices lines that restate earlier guidance), fitting the "efficient; minor instances of over-explanation that could be trimmed" anchor.	4 / 5
Actionability	It provides copy-paste-ready commands for every stage (install, login, headless completion, connection ensure/get with --wait, action list/run, request with a full flags table), covering the common cases with real executable syntax, matching the "fully executable; copy-paste ready commands; specific examples cover the common cases" anchor.	5 / 5
Workflow Clarity	The connection flow is well sequenced with state-based checkpoints and a poll-after-action feedback loop, but running destructive Record operations (create/update/delete) has no validation or verification step, so the destructive-operations cap of 3 applies even though the sequence is otherwise clear.	3 / 5
Progressive Disclosure	No bundle files exist and all content is inline, but the ~135-line body is well organized with clear section headers and logical flow; some detail (e.g. clientAction states, the proxy flags table) could be split into references, placing it at the "good structure; most content appropriately placed; minor organization gaps" anchor.	4 / 5
	Total	16 / 20 Passed

Description

61%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 successfully pairs a clear purpose with an explicit use-when clause and names a distinctive platform, but it leans on the generic verb "Manage" (and a typo "Recordses") instead of concrete operations, and its trigger phrasing is broad. Tightening the action vocabulary and adding concrete trigger terms would lift the specificity and trigger-quality scores.

Suggestions

Replace the generic "Manage Recordses" with concrete operations, e.g. "Create, read, update, delete, and list Records in Haravan."

Expand the trigger clause with natural terms users would say, e.g. "Use when the user wants to manage Haravan Records, query Haravan data, or interact with the Haravan API."

Fix the typo "Recordses" to "Records".

Dimension	Reasoning	Score
Specificity	The phrase "Manage Recordses" names the domain (Haravan, Records) but offers only a single generic action verb rather than the concrete CRUD operations the body actually supports, matching the "names the domain but actions are minimal or generic" anchor.	2 / 5
Completeness	It states both a clear "what" ("Haravan integration. Manage Recordses.") and an explicit "when" ("Use when the user wants to interact with Haravan data"), but the trigger clause is generic rather than enumerating concrete triggers, matching the "both what and when; when could be more explicit" anchor.	4 / 5
Trigger Term Quality	It surfaces "Haravan", "Records", and the natural phrase "interact with Haravan data", but lacks common synonyms or variations, fitting the "some relevant keywords but missing common variations or synonyms" anchor.	3 / 5
Distinctiveness Conflict Risk	"Haravan" is a specific named platform with a distinct entity ("Records") and tailored triggers, giving it a clear niche with minimal overlap risk, matching the "clear niche with distinct triggers; minimal conflict risk" anchor.	5 / 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/haravan/SKILL.md
Commit: f484c82

Reviewed: 5 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.