CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

74

Quality

92%

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

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.

A highly actionable, well-structured skill body with concrete commands, schemas, validation checkpoints, and feedback loops, supported by a clean one-level-deep reference structure. The only weakness is mild redundancy between the flowchart and the runbook checklist.

Suggestions

Consolidate the overlap between the ASCII decision-tree flowchart and the 13-step Runbook checklist so the sequence is stated once authoritatively, with the other view cross-referencing it.

Mention gmail.md in the site-memory listing alongside eastmoney/xueqiu/bilibili/tonghuashun since the file exists, or remove the file if it is not intended to be referenced.

DimensionReasoningScore

Conciseness

Dense, operational prose that assumes Claude's competence and avoids explaining basics, but the ASCII decision-tree flowchart and the 13-step Runbook checklist restate the same sequence, introducing minor redundancy that could be consolidated.

4 / 5

Actionability

Fully executable guidance throughout — concrete commands ('opencli browser init <site>/<name>', 'opencli browser verify', 'npm run typecheck'), exact file paths, a copy-paste strategy-note template, and explicit JSON schemas for endpoints.json and field-map.json.

5 / 5

Workflow Clarity

A clearly sequenced 13-step runbook with checkboxes, explicit validation checkpoints (candidate contract verification, verify, field-vs-webpage comparison, write-back only after pass), and a dedicated feedback-loop degradation table mapping each stuck-point to its recovery step.

5 / 5

Progressive Disclosure

SKILL.md acts as a clear overview with a well-signaled reference table mapping each of 13 one-level-deep reference files to its trigger step; all referenced files (including site-memory/<site>.md) exist and detailed playbooks are appropriately split out.

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, well-targeted description that concretely states capabilities, gives explicit 'Use when' triggers, and actively routes away from neighboring skills to avoid conflicts. Only minor room for additional synonymous trigger phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete end-to-end actions — 'first recon', 'field decoding', 'adapter coding', and 'verify' — giving comprehensive coverage of the adapter-authoring workflow rather than vague abstraction.

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...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases a user would say ('writing an OpenCLI adapter for a new site', 'adding a new command to an existing site') are present and domain-appropriate, though a few synonymous phrasings are not enumerated.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche and explicitly disambiguates from siblings ('Replaces opencli-oneshot / opencli-explorer', 'see opencli-browser instead', 'see opencli-usage'), minimizing wrong-skill triggering.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
jackwener/OpenCLI
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.