opencode

Monitor and manage your OpenCode tasks using helper scripts.

Quality

61%

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

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-organized for a simple scripting skill, but it contains a copy-paste error in one example and does not explicitly sequence the session-id handoff between its two scripts.

Suggestions

Fix the list_messages_of_session.py example to call the correct script: `uv run python skills/opencode/list_messages_of_session.py {session_id}`.

Add an explicit step sequence, e.g. 'First run list_sessions.py to obtain a session_id, then pass it to list_messages_of_session.py'.

Replace the generic `script_name.py` placeholder with the actual script names to avoid ambiguity.

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanations of concepts Claude already knows; every line is operational (script invocations, a safety note, status legend). It assumes Claude's competence and earns its tokens.	3 / 3
Actionability	Commands are executable, but the example for list_messages_of_session.py mistakenly calls list_sessions.py with {session_id}, a wrong key detail that breaks copy-paste. This is concrete guidance with an incomplete/incorrect detail rather than fully copy-paste ready.	2 / 3
Workflow Clarity	The two-step flow (run list_sessions to get a session_id, then list messages for it) is present but never explicitly sequenced, and the session_id handoff is only implicit. Not score 1 (steps exist) but not score 3 (no explicit sequence or checkpoints).	2 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references (no bundle files exist), and is organized into clear sections (Helper Scripts, Scripts, Session Status Types), satisfying the simple-skill guideline for a top score.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 identifies a clear domain and a couple of actions but stays generic throughout, with no explicit usage triggers or concrete action list. It is serviceable but underspecified.

Suggestions

Add concrete actions, e.g. 'List OpenCode sessions, view session messages, and check session status'.

Append an explicit trigger clause such as 'Use when the user wants to monitor or inspect running OpenCode sessions'.

Include natural keyword variations like 'OpenCode sessions', 'session messages', and 'session status' to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('OpenCode tasks') and two actions ('Monitor and manage'), but they are generic rather than a list of concrete actions like 'list sessions' or 'view messages'. It is above score 1 (it does name some actions) but not score 3 (no multiple specific concrete actions).	2 / 3
Completeness	It states what the skill does ('Monitor and manage your OpenCode tasks using helper scripts') but provides no 'Use when...' trigger, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	'OpenCode tasks' is a natural term a user would say, but it is the only real keyword with no common variations covered. It is above score 1 (a natural keyword exists) but below score 3 (no broad coverage of natural terms).	2 / 3
Distinctiveness Conflict Risk	'OpenCode' anchors it to a specific niche, but the generic 'monitor and manage tasks' phrasing and absence of distinct trigger language mean it could still overlap with similar task-management skills.	2 / 3
	Total	8 / 12 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: f316d6a

Reviewed: about 13 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.