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

conjur

Conjur integration. Manage security and secrets-management data, records, and workflows. Use when the user wants to interact with Conjur 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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/conjur/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 actionable and well-structured with concrete Membrane CLI commands and a solid connection state machine, but it is padded with an unnecessary product intro and lacks validation guidance for destructive action/proxy operations on secrets. Progressive disclosure is good for a single-file skill.

Suggestions

Trim the opening paragraph that defines what Conjur and secrets management are; Claude already knows this — keep only the integration-specific context.

Add a validation/verification step for destructive action runs and proxy requests (e.g., confirm resource state before/after DELETE, dry-run or read-before-write for secret mutations) so the destructive-operations cap can lift.

Remove vague filler such as "Use action names and parameters as needed" and consolidate the duplicated action-discovery command under "Popular actions" to tighten the flow.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but includes unnecessary explanation Claude already knows (the opening paragraph defining what Conjur/secrets management is) and filler like "Use action names and parameters as needed," fitting the "mostly efficient but includes some unnecessary explanation" anchor.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands across auth, connection setup, action discovery/running, and proxying, plus a flags table; minor gaps remain in the bare "Conjur Overview" bullet list and the duplicated discovery command, matching the "mostly executable guidance with minor gaps" anchor.	4 / 5
Workflow Clarity	The connection workflow is well sequenced with state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED polling), but running actions and proxy requests (which support destructive methods like DELETE on secrets) lack validation/verification steps, so the destructive-operations cap applies and the score cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files exist and content is organized into clear, well-labeled sections with no deep nesting; the single-file layout is longer than 50 lines with some inline reference material (proxy flags, state details) that could be split, matching the "good structure, minor organization gaps" anchor rather than the split-and-linked top level.	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 has an explicit Use-when trigger and a clear product niche, but its action language is generic ("manage data, records, and workflows") rather than naming concrete Conjur operations. It scores well on completeness and distinctiveness, weaker on specificity and trigger richness.

Suggestions

Replace the generic "Manage ... data, records, and workflows" with concrete Conjur actions (e.g., "store and retrieve secrets, rotate credentials, audit access, manage policies").

Broaden trigger terms with natural synonyms a user would say, such as "secrets", "secrets management", "CyberArk Conjur", or "policy/variable/host management".

Make the Use-when clause more specific, e.g. "Use when the user wants to store, fetch, or audit secrets or manage Conjur policies and resources."

Dimension	Reasoning	Score
Specificity	The description names the domain ("Conjur", "security and secrets-management") but the only action verb is the generic "Manage ... data, records, and workflows," with no concrete operations like storing or rotating secrets, matching the anchor where the domain is named but actions are minimal or generic.	2 / 5
Completeness	Both halves are present: a clear "what" ("Manage security and secrets-management data, records, and workflows") and an explicit "when" ("Use when the user wants to interact with Conjur data"), but the trigger phrase is not as concrete/specific as the top anchor, matching the "has both what and when, when could be more explicit" level.	4 / 5
Trigger Term Quality	It surfaces relevant keywords ("Conjur", "security", "secrets-management") and an explicit trigger ("Use when the user wants to interact with Conjur data"), but "interact with Conjur data" is generic and it misses common synonyms/variations a user might actually say, fitting the anchor for some relevant keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	"Conjur integration" targets a specific product with a distinct trigger, but the broad "security and secrets-management data, records, and workflows" framing risks minor overlap with other security/secrets skills, fitting the "mostly distinct, minor overlap risk" anchor rather than the minimal-conflict level above.	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/conjur/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.