CtrlK
BlogDocsLog inGet started
Tessl Logo

opencode

Delegate coding to OpenCode CLI (features, PR review).

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/autonomous-ai-agents/opencode/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 executable commands, clear tables, and a well-sequenced procedure including validation. Its main weaknesses are minor internal repetition and a single-file structure that inlines reference material rather than splitting it into bundle files.

Suggestions

Consolidate the repeated `/exit` warnings and inline flag examples with the Common Flags table to remove redundancy.

Move the TUI Keybindings and Common Flags tables into a references/ file (e.g. REFERENCE.md) and link from the body to improve progressive disclosure.

Cross-reference the Procedure steps to the detailed sections so the workflow path through the document is explicit.

DimensionReasoningScore

Conciseness

The body is mostly lean and command-driven, but several items repeat unnecessarily — the `/exit` warning appears three times (lines 98, 192, 219) and the Common Flags table duplicates flags already shown inline — so it could be tightened.

2 / 3

Actionability

It provides numerous copy-paste-ready, executable commands (e.g. `opencode run '...'`, `terminal(command=...)`, `process(action="submit", ...)`) plus concrete flag and keybinding tables, fully matching the executable score-3 anchor.

3 / 3

Workflow Clarity

A numbered Procedure sequences readiness checks, one-shot vs. interactive paths, monitoring, and clean exit, with an explicit Verification smoke test and success criteria, and a Pitfalls feedback loop (inspect logs before killing) — clear sequence with validation.

3 / 3

Progressive Disclosure

The skill is a single ~200-line file with no bundle files and no external references; the Common Flags and TUI Keybindings tables are inline reference material that could be split out, fitting the 'content that should be separate is inline' score-2 anchor rather than the under-50-line simple-skill allowance.

2 / 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 is clear and names a specific tool plus a couple of use cases, but it lacks an explicit "when to use" trigger clause and only partially enumerates capabilities. It is adequate but not exemplary.

Suggestions

Add an explicit "Use when..." trigger clause naming natural user phrases (e.g., 'Use when the user asks to delegate coding to OpenCode, review a PR, or run an autonomous coding worker').

List more concrete actions (implement, refactor, review, debug) instead of the generic '(features, PR review)' to lift specificity.

Include common trigger variations like 'code review', 'refactor', and 'implement' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

"Delegate coding to OpenCode CLI (features, PR review)" names the domain and a couple of actions (features, PR review) but does not enumerate the concrete coding actions comprehensively, matching the score-2 anchor rather than the multi-action score-3 anchor.

2 / 3

Completeness

The "what" is stated (delegate coding to OpenCode CLI for features/PR review) but there is no "Use when..." or equivalent explicit trigger guidance, which the guidelines cap at 2.

2 / 3

Trigger Term Quality

It surfaces natural terms like "coding", "PR review", and "OpenCode CLI", but omits common variations users would say ("refactor", "implement", "code review", "review this PR"), so coverage is partial rather than complete.

2 / 3

Distinctiveness Conflict Risk

Naming the specific OpenCode CLI gives it a niche, but "coding" is broad and it could still overlap with related coding-agent skills (claude-code, codex), so it is only somewhat distinct.

2 / 3

Total

8

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
NousResearch/hermes-agent
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.