opencode-configure

Configure OpenCode via opencode.json and AGENTS.md with deterministic provider setup, model selection, permission policies, formatter behavior, and environment variable handling; use when editing opencode configuration, setting model/provider defaults, tightening agent permissions, or troubleshooting OpenCode config behavior.

Quality

86%

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

81%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-validated configuration skill with excellent executable templates and a clear workflow. Its weaknesses are trimmable redundancy (a duplicated TOC section and repeated commands) and broken/ill-formed reference links in the otherwise good progressive-disclosure structure.

Suggestions

Remove the 'Information Architecture' section (it restates the headings already visible in the document) and delete the 'Quick Commands' section or the inline Workflow commands so each command appears once.

Fix or remove the broken evals/scenario-0..2/task.md links — no evals/ directory exists in the bundle.

Add a blank line between the 'OpenCode Docs' external link and the references table so the table renders correctly, and consider converting the bare link into a labeled bullet.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense and actionable, but the "Information Architecture" section merely restates the table of contents and "Quick Commands" repeats commands already embedded in the Workflow (jq, rg, opencode run all appear twice). Fits the 3 anchor ("could be tightened"); not 4 because this section-level redundancy exceeds minor over-explanation.	3 / 5
Actionability	Copy-paste-ready opencode.json and AGENTS.md templates plus concrete bash validation commands (jq . opencode.json, rg -n ..., opencode run "test") fully cover the common cases. Matches the 5 anchor for executable, copy-paste-ready guidance.	5 / 5
Workflow Clarity	The 6-step Workflow includes explicit validation checkpoints (jq syntax check, rg sanity grep, smoke test) and error-recovery direction ("If errors surface, re-read config precedence before widening permissions"). Matches the 5 anchor; not 4 because no validation checkpoint is missing.	5 / 5
Progressive Disclosure	Good hub structure with three real, one-level-deep references clearly signaled in a topic table. Not 5 because the three evals/scenario-*.md links point to nonexistent files and the external docs link sits directly above the reference table without a blank line, breaking its markdown rendering.	4 / 5
	Total	17 / 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 description: third-person voice, concrete capability list anchored to named config files, and an explicit 'use when' clause with enumerated triggers. Only weakness is slightly incomplete natural-keyword coverage for a few common user phrasings.

Dimension	Reasoning	Score
Specificity	"deterministic provider setup, model selection, permission policies, formatter behavior, and environment variable handling" lists multiple concrete actions tied to named files (opencode.json, AGENTS.md), comprehensively covering the config domain. Not 4 because coverage has no notable gaps.	5 / 5
Completeness	Explicitly answers both what ("Configure OpenCode via opencode.json and AGENTS.md with...") and when ("use when editing opencode configuration, setting model/provider defaults, tightening agent permissions, or troubleshooting...") with concrete triggers. Not 4 because the when-clause is fully explicit and enumerated.	5 / 5
Trigger Term Quality	Natural phrases like "editing opencode configuration", "setting model/provider defaults", and "tightening agent permissions" give good keyword coverage. Not 5 because a few natural user phrasings (e.g. "add a provider", "formatter setup", "AGENTS.md instructions") are missing.	4 / 5
Distinctiveness Conflict Risk	Names the OpenCode tool and its specific config files, creating a clear niche with distinct triggers and minimal conflict risk with other skills. Not 4 because no meaningful overlap with closely related skills exists.	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
relative_links	Relative link issues: 3 missing, 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: pantheon-org/tekhne
Path: skills/agentic-harness/opencode-toolkit/configure/SKILL.md
Commit: a1083f4

Reviewed: 3 hours 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.