CtrlK
BlogDocsLog inGet started
Tessl Logo

openwork-connect

Search and use the skills, MCP connections, and connected services available through the user's OpenWork organization.

60

Quality

70%

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 ./integrations/agent-plugins/openwork-connect/skills/openwork-connect/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 a tight, well-structured MCP-usage guide with concrete tool names, clear two-track workflows, and an explicit error-state checkpoint, plus a sharp security note on token handling. The main gap is the absence of concrete example invocations that would push actionability to fully copy-paste-ready.

Suggestions

Add one or two concrete example MCP invocations (e.g. a sample search_capabilities query and the execute_capability call it produces) to make the guidance fully copy-paste ready.

Make the validation loop explicit ('If execute_capability reports a missing connection, surface the setup step and re-attempt only after the user resolves it') to reach the anchor-5 feedback-loop bar.

Consider a short 'Triggers' line in the body restating when to invoke OpenWork Connect, mirroring the frontmatter gap.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, never explaining what MCP or OAuth are; every line (tool names, parameter guidance, security note) earns its place, matching anchor 5.

5 / 5

Actionability

Concrete executable tool names with parameter guidance ('Call list_skills', 'Pass query only to narrow', 'Call execute_capability with that exact name and only the parameters required') are present, but there are no concrete example invocations, leaving minor gaps consistent with anchor 4.

4 / 5

Workflow Clarity

Both the Skills and Workflow flows are numbered and sequenced, and step 4 of the Workflow provides an explicit state-relay/validation checkpoint with error handling; it stops short of the full validate-fix-retry loop of anchor 5.

4 / 5

Progressive Disclosure

At under 50 lines with no need for external references, the well-organized ## Skills and ## Workflow sections meet the simple-skill exception that lets progressive disclosure score 5 on structure alone.

5 / 5

Total

18

/

20

Passed

Description

53%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 clearly states what the skill does within a distinct OpenWork niche but omits any explicit 'when to use it' trigger guidance and relies on fairly technical keywords. Adding a 'Use when...' clause with natural user phrasings would lift completeness and trigger quality.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks to find or run an organizational skill, connect a shared MCP tool, or manage an OpenWork service.'

Broaden trigger terms with everyday synonyms (e.g. 'find skills', 'connect a tool', 'shared service') beyond the technical 'MCP connections' phrasing.

List one or two more concrete actions (e.g. 'discover', 'connect', 'invoke') to raise specificity above the generic 'Search and use'.

DimensionReasoningScore

Specificity

Names the OpenWork domain and two concrete actions ('Search and use') but the actions are generic rather than a comprehensive list of specific capabilities, matching anchor 3.

3 / 5

Completeness

The 'what' is clear ('Search and use the skills, MCP connections, and connected services') but there is no 'Use when...' trigger clause, so per the rubric completeness is capped at 3.

3 / 5

Trigger Term Quality

Terms like 'skills', 'MCP connections', 'connected services', and 'OpenWork organization' are domain-relevant but lean technical, missing common natural-user phrasings and synonyms, fitting anchor 3.

3 / 5

Distinctiveness Conflict Risk

The OpenWork-organization framing gives it a clear, mostly distinct niche with only minor overlap risk against generic skill- or MCP-management skills, matching anchor 4 rather than 5 due to broad 'skills'/'MCP' terms.

4 / 5

Total

13

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
different-ai/openwork
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.