run-agent

Configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local execution, remote git repos, and one-shot prompts. Use when the user wants to run an agent, switch LLM providers, configure adapter settings, or launch agents from git repositories.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, highly actionable CLI reference with executable commands, a clear adapter table, and well-organized sections. The main gap is workflow_clarity: the auto-detection process lacks an explicit verification checkpoint and the troubleshooting section is incomplete relative to the adapter list.

Suggestions

Add a verification checkpoint to the auto-detection workflow (e.g., 'Confirm the detected adapter with opengap run --dry-run before executing') so the sequence has an explicit validation step.

Expand the Troubleshooting section to cover the remaining adapters (CrewAI, OpenClaw, Nanobot, Git, Prompt) so error recovery guidance matches the full adapter table.

Trim overlap between the Basic Usage and Examples sections — several commands (e.g., 'opengap run -d ./my-agent') are repeated — to tighten token efficiency further.

Dimension	Reasoning	Score
Conciseness	The body is lean — tables and copy-paste commands with no concept explanations Claude already knows (e.g., no 'what is an agent' padding); every section earns its tokens, satisfying the 'lean and efficient' anchor.	3 / 3
Actionability	Provides fully executable, specific commands throughout ('opengap run -d ./my-agent', '-a github -p "..."') plus a flag/env-var table, matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	The auto-detection section lists a numbered sequence and there is a troubleshooting block, but there is no explicit validation/checkpoint confirming a detected adapter succeeded, and troubleshooting covers only 4 of 9 adapters — fitting 'steps present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	Content is organized into clearly labeled sections (When to Use, Adapters, Examples, Git Caching, Auto-Detection) with no nested references; for a CLI quick-reference of this size, keeping everything inline in one well-structured file is appropriate navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 third-person description that states concrete capabilities, provides an explicit 'Use when' trigger clause with natural user terms, and carves out a distinct adapter/agent-running niche. Voice and trigger guidance both meet the top rubric anchors.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'Configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models' and 'Supports local execution, remote git repos, and one-shot prompts' — matching the anchor for naming several specific actions.	3 / 3
Completeness	Explicitly answers both what ('Configures and runs agents...') and when ('Use when the user wants to run an agent, switch LLM providers...'), with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Natural user phrasing is well covered: 'run an agent', 'switch LLM providers', 'configure adapter settings', 'launch agents from git repositories' are terms a user would plausibly say, satisfying the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The adapter-based agent-running framing is a clear niche with distinct triggers, unlikely to fire for unrelated skills; not a level-2 'could still overlap' case.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: open-gitagent/opengap
Path: examples/gitagent-helper/skills/run-agent/SKILL.md
Commit: d7a8e2e

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.