opencli-adapter-author

Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level orientation to opencli, see opencli-usage.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

92%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.

An exceptionally well-structured procedural skill: executable commands, a sequenced decision tree with validation checkpoints, and clean progressive disclosure to 12 real reference files. Only minor conciseness trimming of rationale prose would improve it further.

Suggestions

Tighten the strategy-rationale paragraph ('核心判断不是...而是...') to a one-line rule; move the full contract ladder reasoning into strategy-selection.md, which is already referenced.

The 降级路径 and 参考文件 tables duplicate some step references; consider merging the 'jump to' guidance into the runbook checklist to reduce cross-reading.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence (no explanations of fetch, DOM, or basic JS), with every section task-relevant; a few expository passages on contract philosophy and PR war stories could be trimmed slightly, though they encode non-obvious domain knowledge.	4 / 5
Actionability	Fully executable throughout: concrete commands ('opencli doctor', 'opencli browser analyze <url>', 'opencli browser init <site>/<name>', 'opencli browser verify'), exact flags ('--trace on --keep-tab true --window foreground', '--write-fixture'), real file paths, and a copy-paste strategy-note template cover the common cases.	5 / 5
Workflow Clarity	Clear sequence via an ASCII decision tree and a 12-step runbook checklist with explicit validation checkpoints ('opencli browser verify', '字段 vs 网页肉眼对一遍'), memory-freshness gating (30-day expiry), and a 降级路径 feedback-loop table for error recovery.	5 / 5
Progressive Disclosure	Body serves as overview/runbook while 12 details live in one-level-deep reference files, all real and listed in a 参考文件 table that maps each file to the step where it is needed; navigation is easy and well-signaled.	5 / 5
	Total	19 / 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 with explicit 'what' and 'when' guidance plus excellent sibling disambiguation. The only minor gap is a lack of synonym/variation trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'writing an OpenCLI adapter for a new site', 'adding a new command', and the end-to-end pipeline 'from first recon through field decoding, adapter coding, and verify' — giving comprehensive coverage of the skill's scope.	5 / 5
Completeness	Explicitly answers both what ('Guides end-to-end from first recon through field decoding, adapter coding, and verify') and when ('Use when writing an OpenCLI adapter... or adding a new command...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would say ('writing an OpenCLI adapter for a new site', 'adding a new command to an existing site') are present and direct, but no synonyms or variations are offered for users who phrase the need differently.	4 / 5
Distinctiveness Conflict Risk	Explicitly disambiguates from four sibling skills ('Replaces opencli-oneshot / opencli-explorer', 'see opencli-browser instead', 'see opencli-usage'), giving it a clear niche with minimal conflict risk.	5 / 5
	Total	19 / 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-adapter-author/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.