delegate-opencode2

Delegate a bounded coding task to the local opencode2 CLI, then verify it. Trigger: delegar a opencode2, opencode-admin.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./ywai/skills/delegate-opencode2/SKILL.md

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.

The body is a strong, lean operational guide with executable commands, explicit validation feedback loops, and a single well-placed one-level reference for advanced detail; only minor conciseness trims would improve it.

Dimension	Reasoning	Score
Conciseness	The body is lean and trap-focused — hard rules, routing tables, copy-paste commands, and a verification checklist — with most every token earning its place; a few framing sentences (the cold-agent intro restating the description) could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready shell (nohup launch with every flag explained, the kill -0 wait loop) plus concrete routing and model-selection tables covering the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Sequences write-prompt → launch → wait → verify → report with explicit validation checkpoints (re-read for contradictions before launch, run tests yourself, mutation-test, restore, commit) and feedback loops for error recovery, satisfying the checklist anchor.	5 / 5
Progressive Disclosure	The body is an overview with a single well-signaled one-level-deep reference — 'Prompt anatomy, worked traps, and failure modes: references/prompt-recipe.md' — to a real file that holds the advanced detail, matching the clear-overview navigation anchor.	5 / 5
	Total	19 / 20 Passed

Description

62%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 to the opencode2 niche and answers both what and when with an explicit trigger clause, but trigger coverage is narrow and mixes languages, leaving it solidly mid-good rather than exemplary.

Suggestions

Add natural English trigger phrases users would actually say (e.g. 'delegate to opencode2', 'hand off a coding task', 'run opencode-admin') alongside the existing terms for broader keyword coverage.

Expand the 'what' to one more concrete action (e.g. route by task shape, choose a model) to push specificity toward comprehensive coverage.

Make the 'when' clause a proper 'Use when...' sentence naming the bounded-task and model-routing scenarios, rather than a terse 'Trigger:' tag.

Dimension	Reasoning	Score
Specificity	Names the domain (opencode2 CLI) and two concrete actions — 'Delegate a bounded coding task' and 'then verify it' — but stops at two actions rather than comprehensive coverage, matching the 1-2 concrete actions anchor.	3 / 5
Completeness	Explicitly answers what ('Delegate a bounded coding task... then verify it') and when via an explicit 'Trigger:' clause; the when is present and concrete but terse and could be more specific, sitting above the 3 cap because explicit trigger guidance exists.	4 / 5
Trigger Term Quality	Provides 'delegar a opencode2, opencode-admin' as explicit triggers, but coverage is thin and mixes a Spanish phrase with the model family name, missing common English variations users would naturally say.	3 / 5
Distinctiveness Conflict Risk	Tied to the specific opencode2 CLI with its own model family 'opencode-admin', giving a clear niche with minor overlap risk against other generic delegation skills; not a 5 because the concept of delegation is broadly shared.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: YoizenSA/dev-ai-workflow
Path: ywai/skills/delegate-opencode2/SKILL.md
Commit: 36f5af5

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.