CtrlK
BlogDocsLog inGet started
Tessl Logo

manage-delegates

Monitor and manage Harness Delegates via MCP. List delegates and check health status, manage delegate registration tokens (create, revoke, delete), and find which delegates are associated with a token. Use when asked about delegate status, delegate health, delegate connectivity, delegate tokens, or troubleshooting delegate issues. Trigger phrases: delegate status, delegate health, list delegates, delegate token, delegate connectivity, delegate troubleshooting, delegate down.

67

Quality

80%

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

SKILL.md
Quality
Evals
Security

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.

A well-structured, actionable MCP skill body with clear step sequencing and useful reference tables. The main gap is the absence of explicit validation/confirmation checkpoints around the destructive revoke and delete operations.

Suggestions

Add an explicit verification/confirmation checkpoint before Step 6 (Revoke) and Step 7 (Delete) — e.g. 'Confirm the token name and warn that revoking disconnects all registered delegates before executing.'

Include at least one fully-resolved worked example with real values (not just '<organization>' placeholders) to make the common case copy-paste ready.

Tighten the Performance Notes by folding the connectivity-check guidance into the relevant step rather than restating it as a separate section.

DimensionReasoningScore

Conciseness

The body is lean and largely assumes Claude's competence — steps are terse parameter blocks rather than prose — but a few explanatory lines (e.g. 'Delegates are account-scoped -- no org/project needed') and the Performance Notes could be marginally tightened.

4 / 5

Actionability

Each step gives a concrete MCP tool name and parameter list, which is directly executable, but values are templated placeholders ('<organization>', '<token_name>') rather than a copy-paste-ready worked example, leaving minor gaps.

4 / 5

Workflow Clarity

Steps 1–7 are clearly sequenced, but the destructive 'Revoke a Token' (Step 6) and 'Delete a Token' (Step 7) workflows lack explicit validation/confirmation checkpoints before execution; per the destructive-operation cap, this holds at 3.

3 / 5

Progressive Disclosure

No bundle files exist; all content lives in SKILL.md but is organized into well-signaled sections (Instructions, Resource Types, Examples, Performance Notes, Troubleshooting). Structure is good, with only minor organization headroom.

4 / 5

Total

15

/

20

Passed

Description

92%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.

A strong, specific description that concretely enumerates capabilities and provides explicit, natural-language trigger guidance. Only minor headroom remains in trigger-term synonym coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'List delegates and check health status, manage delegate registration tokens (create, revoke, delete), and find which delegates are associated with a token' — covering the full CRUD + association surface comprehensively.

5 / 5

Completeness

Explicitly answers both 'what' (monitor/manage delegates and tokens) and 'when' (a clear 'Use when asked about...' clause plus enumerated trigger phrases).

5 / 5

Trigger Term Quality

Explicit trigger phrases ('delegate status, delegate health, list delegates, delegate token, delegate connectivity, delegate troubleshooting, delegate down') give strong natural-term coverage, but a few common phrasings a user might say (e.g. 'delegate not working', 'delegate offline') are absent.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche — Harness Delegates via MCP — with delegate-specific triggers, making collision with unrelated skills unlikely.

5 / 5

Total

19

/

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
harness/harness-ai
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.