CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

conjur

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

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/conjur/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, highly actionable integration skill whose CLI commands and connection-state handling are concrete and executable. Its main weaknesses are padding (redundant/filler sections) and small workflow-coherence defects like a dangling 'Step 2' reference and unlabeled step sequencing.

Suggestions

Cut the 'Use action names and parameters as needed.' filler line, the redundant action-list command in 'Popular actions', and the intro paragraph explaining what Conjur is — Claude already knows this product category.

Fix the broken step navigation: 'skip to Step 2' and the '#### 1b.' heading reference steps that are never defined; either number the sections consistently or remove the step references.

Clarify the 'membrane connection ensure ""' example — explain what the empty-string argument means or show a realistic app-URL/domain value.

DimensionReasoningScore

Conciseness

The body is mostly efficient CLI guidance, but includes an intro paragraph explaining what Conjur is, the filler line 'Use action names and parameters as needed.', a bare unexplained overview bullet list, and a duplicated action-discovery command ('Use npx @membranehq/cli@latest action list...' repeats the 'Searching for actions' section). It fits anchor 3 — could be tightened — rather than 4 because several sections add little value.

3 / 5

Actionability

Concrete, executable commands throughout: 'npm install -g @membranehq/cli@latest', 'membrane login complete <code>', 'membrane action run <actionId> --connectionId=CONNECTION_ID --input {...} --json', plus a full proxy flag table. Minor gaps (the confusing 'membrane connection ensure ""' empty-URL placeholder, no realistic action-id example) keep it below anchor 5.

4 / 5

Workflow Clarity

Clear sequence (install → login → connection ensure → poll state → handle CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR → search actions → run → proxy fallback) with state-based checkpoints and error-field inspection. Falls short of anchor 5 because 'skip to Step 2' references a step that is never labeled, and action results are never validated.

4 / 5

Progressive Disclosure

Single-file skill with no bundle files; sections are well-organized and content is appropriately placed inline at ~160 lines, matching anchor 4. Minor organization gaps (the dangling 'Step 2' reference and the odd '1b' heading) prevent a 5.

4 / 5

Total

15

/

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 follows the good pattern of domain + actions + explicit 'Use when' clause and is anchored by the distinct product name 'Conjur'. Its weakness is generality: the capability statement uses vague verbs ('manage ... data, records, and workflows') and trigger coverage misses common synonyms like 'secrets', 'credentials', and 'CyberArk'.

Suggestions

Replace the generic 'Manage security and secrets-management data, records, and workflows' with concrete actions, e.g., 'Store, retrieve, and rotate secrets; manage policies, roles, and permissions; audit access to credentials in Conjur.'

Broaden the when-clause with natural trigger phrases: 'Use when the user mentions Conjur, CyberArk, secrets management, or wants to store, retrieve, or rotate credentials/secrets.'

DimensionReasoningScore

Specificity

'Manage security and secrets-management data, records, and workflows' names the domain but the actions are generic ('manage ... data, records, workflows') with no concrete operations like storing secrets, rotating credentials, or auditing access. Matches anchor 3, not 4, which requires several specific listed actions.

3 / 5

Completeness

Both what ('Manage security and secrets-management data, records, and workflows') and when ('Use when the user wants to interact with Conjur data') are explicitly present. Not anchor 5 because the when-clause is narrow ('interact with Conjur data') with no broader trigger phrases.

4 / 5

Trigger Term Quality

'Conjur' is a strong natural trigger and 'security', 'secrets-management' help, but common variations users would say — 'secrets', 'credentials', 'CyberArk' — are absent. Fits anchor 3 (relevant keywords, missing variations/synonyms) rather than 4.

3 / 5

Distinctiveness Conflict Risk

The product name 'Conjur' gives a clear niche trigger, but 'security and secrets-management' overlaps with closely related secret-management skills (e.g., Vault, AKEYLESS), matching anchor 4 rather than 5.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.