add-opencode

Use OpenCode as an agent provider. OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per group via `ncl groups config update --provider opencode`; host passes OPENCODE_* and XDG mount when spawning containers.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-opencode/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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-sequenced install/config procedure with strong validation checkpoints, but it is a monolithic single file and carries explanatory prose that could be tightened or split into references.

Suggestions

Move the per-provider configuration examples (DeepSeek, OpenRouter, Zen) into a reference file and keep only one canonical example plus a pointer in SKILL.md.

Tighten the step-7 guard descriptions into a compact table or one-line bullets rather than multi-sentence prose per test.

Split operational notes (teardown, session continuation, NO_PROXY) into a separate OPERATIONS.md referenced from the main body.

Dimension	Reasoning	Score
Conciseness	Assumes Claude's competence (no basic-concept padding) and most tokens earn their place, but the long prose explanations of each test guard and the naming disambiguation could be tightened without losing clarity.	2 / 3
Actionability	Fully executable: exact bash commands, pinned versions ('@opencode-ai/sdk@1.4.17'), precise file paths, and copy-paste-ready env and onecli secret examples.	3 / 3
Workflow Clarity	Clear numbered sequence (Pre-flight through step 8) with explicit validation in step 7 ('All four must be clean before proceeding') and error-recovery feedback loops (the build-cache prune-and-rebuild gotcha).	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~260-line SKILL.md with only one external link (REMOVE.md); detailed config examples and operational notes that could live in reference files are inlined, so structure is present but disclosure is flat.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive, naming concrete actions and a clear niche, but is missing an explicit 'Use when...' trigger clause and leans on technical jargon over natural user phrasings.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants to route NanoClaw agents through OpenCode-compatible providers (OpenRouter, DeepSeek, Google, OpenAI) instead of the Anthropic Agent SDK.'

Include more natural-language trigger terms users would actually say (e.g. 'use DeepSeek', 'switch provider', 'route through OpenRouter') alongside the technical identifiers.

Move the implementation detail about 'XDG mount' out of the description — it is a host mechanism, not a trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and specifics: 'Use OpenCode as an agent provider', named providers ('OpenRouter, OpenAI, Google, DeepSeek'), and the exact config command 'ncl groups config update --provider opencode'.	3 / 3
Completeness	Clearly answers 'what' (use OpenCode as an agent provider) but lacks an explicit 'Use when...' trigger clause, so the 'when' is only implied — capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Includes some natural terms a user might say ('OpenCode', 'DeepSeek', 'OpenRouter') but leans on technical jargon ('XDG mount', 'Anthropic Agent SDK', 'agent provider') and lacks common trigger phrasings.	2 / 3
Distinctiveness Conflict Risk	A clear narrow niche (OpenCode provider for NanoClaw) with distinct, specific triggers unlikely to overlap with other skills.	3 / 3
	Total	10 / 12 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/add-opencode/SKILL.md
Commit: 641963c

Reviewed: 6 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.