CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

76%

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

Fix and improve this skill with Tessl

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

Quality

Content

82%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.

The body is highly actionable with concrete commands, pinned versions, and worked provider examples, plus a clearly sequenced install workflow with validation checkpoints. Minor gaps are some repeated verbosity in env-var semantics and a broken link to REMOVE.md.

Suggestions

Add the missing REMOVE.md bundle file (or remove the `[REMOVE.md](REMOVE.md)` link) so the one external reference resolves.

Factor the repeated 'Anything but a positive integer is logged and treated as unset' caveat into a single shared note rather than restating it per env var.

Make the install failure-recovery loop explicit (e.g. 'If a check fails: fix the reported error and re-run that check before proceeding') to reach the top workflow-clarity anchor.

DimensionReasoningScore

Conciseness

Dense and project-specific with no padding of concepts Claude already knows, though the repeated 'Anything but a positive integer is logged and treated as unset' phrasing across several env vars could be trimmed.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance: exact version pin `@opencode-ai/sdk@1.4.17`, concrete `nc:copy`/`nc:append`/`nc:dep` blocks, and complete `onecli secrets create` commands with worked DeepSeek, OpenRouter, Anthropic, and Zen examples.

5 / 5

Workflow Clarity

Clear five-step install sequence with explicit validation commands (tsc, vitest, build.sh) and a 'must be clean before proceeding' gate, but the error-recovery loop on failure is implicit rather than spelled out.

4 / 5

Progressive Disclosure

Well-organized into clear sections (Install, Configuration, Operational notes, Next steps) with one clearly signaled one-level reference, though that reference ([REMOVE.md](REMOVE.md)) does not exist in the bundle.

4 / 5

Total

17

/

20

Passed

Description

70%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.

The description is specific and distinct, naming concrete provider-configuration actions and contrasting against the Anthropic Agent SDK. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' clause naming the situations that should trigger this skill (e.g. 'Use when adding or switching an agent group to OpenCode-backed providers like OpenRouter, DeepSeek, or OpenAI').

Consider listing the trigger as a natural user phrase such as 'use OpenCode' or 'switch a group to OpenRouter/DeepSeek' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'set provider per group via `ncl groups config update --provider opencode`' and 'host passes OPENCODE_* and XDG mount when spawning containers' — with minor gaps in overall coverage.

4 / 5

Completeness

Has a clear 'what' ('Use OpenCode as an agent provider... via OpenCode config') but no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Good keyword coverage with natural provider names users would say ('OpenCode', 'OpenRouter', 'OpenAI', 'Google', 'DeepSeek') plus the command trigger, though a few common phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (OpenCode agent provider in NanoClaw) and explicitly contrasts with 'not the Anthropic Agent SDK', giving minimal conflict risk.

5 / 5

Total

16

/

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
nanocoai/nanoclaw
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.