opencode

Monitor and manage your OpenCode tasks using helper scripts.

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./bot/workspace/skills/opencode/SKILL.md

Quality

Content

75%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 content is concise and reasonably well-structured for a simple script-catalog skill, but actionability is undermined by a copy-paste error that runs the wrong script and a placeholder in the general run instruction.

Suggestions

Fix the example for `list_messages_of_session.py` so it runs `skills/opencode/list_messages_of_session.py {session_id}` instead of `list_sessions.py`.

Replace the generic `script_name.py` placeholder with the actual available scripts or remove the template line since the scripts are already enumerated.

Add a brief validation step for management actions (e.g. confirm a session_id exists via list_sessions before reading messages) to add a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean: short section headers, minimal one-line descriptions per script, and no padding or explanations of concepts Claude already knows, fitting the lean-and-efficient anchor where every token earns its place.	5 / 5
Actionability	It provides concrete run commands, but the example for `list_messages_of_session.py` invokes `list_sessions.py {session_id}` (a copy-paste error pointing at the wrong script) and the general template uses a non-executable `script_name.py` placeholder, leaving key details incomplete.	3 / 5
Workflow Clarity	Each task is a single unambiguous command (simple-skill case), and the status-types legend helps interpret results; the safety note "Do not kill the opencode process" is a checkpoint, though no broader validation/feedback loop is described.	4 / 5
Progressive Disclosure	The body is under 50 lines with clear sections (Helper Scripts, Scripts, Session Status Types) and no nested references, but the referenced scripts live in the workspace rather than a bundled references/ directory and are not cleanly signaled as part of the skill bundle.	4 / 5
	Total	16 / 20 Passed

Description

28%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 too vague to be a strong trigger: it names the OpenCode domain but uses generic verbs and omits any use-when guidance. It is barely distinguishable from generic task-management skills.

Suggestions

Replace generic verbs with concrete actions, e.g. "List OpenCode sessions, read messages by session, and check session status."

Add a "Use when..." clause with natural trigger phrases such as "when the user asks to check, list, or inspect OpenCode sessions and messages".

Include synonyms and the literal product name variations (e.g. "OpenCode sessions", "session status") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	"Monitor and manage your OpenCode tasks using helper scripts" names the domain (OpenCode tasks) but the verbs "monitor" and "manage" are generic rather than concrete actions, matching the anchor for naming a domain with minimal/generic actions.	2 / 5
Completeness	It gives a vague "what" (monitor/manage tasks) and entirely omits any "when"/Use-when guidance; per the guidelines a missing Use-when clause caps completeness, and the vague what pulls it to the anchor with a vague what and no when.	2 / 5
Trigger Term Quality	The only keyword is "OpenCode tasks"; there are no natural trigger phrases a user would say and no synonyms or variations, fitting the anchor of one or two generic keywords missing the natural phrases users say.	2 / 5
Distinctiveness Conflict Risk	Naming the specific product "OpenCode" gives it a recognizable niche, but the generic "monitor and manage your tasks" framing could still overlap with other task-management skills, matching the somewhat-specific-but-overlapable anchor.	3 / 5
	Total	9 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: volcengine/OpenViking
Path: bot/workspace/skills/opencode/SKILL.md
Commit: dbf3fcc

Reviewed: 3 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.