opencli-autofix

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.

Quality

88%

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

Quality

Content

88%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-engineered repair workflow with concrete commands, explicit validation, and strong safety guardrails. The main improvement is deduplicating the hard-stop sections and potentially extracting the issue template into a bundled reference file.

Suggestions

Consolidate the duplicated hard-stop conditions: 'Safety Boundaries' and 'When to Stop' both list AUTH_REQUIRED/BROWSER_CONNECT/CAPTCHA — state them once and cross-reference.

Extract the Step 6 GitHub issue template into a bundled reference file (e.g. references/issue-template.md) and link to it, reducing SKILL.md length and improving progressive_disclosure.

Tighten the 'Empty ≠ Broken' section's four bullets into a shorter checklist; the anti-scrape guidance is valuable but currently verbose.

Dimension	Reasoning	Score
Conciseness	Dense and operational with no basic-concept padding, but the hard-stop conditions (AUTH_REQUIRED, BROWSER_CONNECT, CAPTCHA) are stated twice — once in 'Safety Boundaries' and again in 'When to Stop' — which could be consolidated.	4 / 5
Actionability	Provides fully executable commands ('opencli <site> <command> --trace retain-on-failure 2>trace-error.yaml', 'opencli browser network --filter author,text,likes', 'gh issue create ...') and concrete before/after patch examples covering the common selector, API, schema, and wait-condition cases.	5 / 5
Workflow Clarity	Clear 6-step sequence with explicit validation in Step 5 ('If it still fails, go back to Step 1'), a 3-round retry budget feedback loop, and hard-stop checklists — the destructive-operation validation cap does not apply because validation is present.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references and no bundle files present, but the ~290-line body keeps everything inline (including the full GitHub issue template) rather than splitting detail into a reference file.	4 / 5
	Total	18 / 20 Passed

Description

87%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 description that clearly states purpose and trigger with concrete, sequenced actions. Trimming the 'Works with any AI agent' clause and adding a couple of natural synonyms would push it to the top of the scale.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue'), but they are bundled into prose and accompanied by the mild over-claim 'Works with any AI agent', keeping it just below the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both what ('Automatically fix broken OpenCLI adapters when commands fail') and when ('Load this skill when an opencli command fails') with a concrete trigger phrase, matching the top anchor.	5 / 5
Trigger Term Quality	Includes a natural trigger phrase ('Load this skill when an opencli command fails') plus related terms ('broken OpenCLI adapters'), giving good coverage though a few natural synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (OpenCLI adapter self-repair) with distinct triggers, making conflict with unrelated skills unlikely.	5 / 5
	Total	18 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: jackwener/OpenCLI
Path: skills/opencli-autofix/SKILL.md
Commit: 64e6f0e

Reviewed: 2 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.