CtrlK
BlogDocsLog inGet started
Tessl Logo

go-review

Go code review guidelines for the Cog codebase

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/go-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 tight, well-organized review checklist that adds only what Claude would not already know about this specific codebase — concrete linters to skip, exact assertion conventions, and package-level architecture rules. It is an excellent example of a concise, actionable instruction skill.

DimensionReasoningScore

Conciseness

Lean bullet-driven content that assumes Claude's competence and explains no basic concepts; every line is a concrete check, matching the level-3 'lean and efficient; every token earns its place' anchor.

3 / 3

Actionability

Gives specific, executable guidance — exact linters to skip, exact three import groups, exact assertion libraries (testify/require vs assert), and exact package locations — rather than vague direction. It is not level 2 (no pseudocode or missing key details); for an instruction skill this concrete-checklist guidance is fully actionable.

3 / 3

Workflow Clarity

This is a simple single-purpose skill (a categorized review checklist) with unambiguous single-task guidance, so per the simple-skills note workflow_clarity can score 3; it involves no destructive or batch operations that would require validation checkpoints.

3 / 3

Progressive Disclosure

The skill is under 50 lines with no need for external references and is organized into clearly labeled sections (Error handling, Imports, Testing, Concurrency, Docker, Architecture); no bundle files exist to verify, and per the simple-skills note well-organized sections alone warrant a 3.

3 / 3

Total

12

/

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 correctly identifies a scoped niche (Go review for the Cog codebase) but is thin: it states the domain without enumerating concrete review actions and lacks any explicit 'Use when...' trigger. It reads more as a title than a discovery-oriented description.

Suggestions

Add 2-3 concrete review actions to the description, e.g. 'Flags silent error discards, missing testify assertions, goroutine leaks, and import-grouping violations'.

Add an explicit trigger clause such as 'Use when reviewing Go code in the Cog codebase or when the user asks for a code review on cmd/cog or pkg/ changes'.

Include natural trigger variations users would actually say (e.g. 'PR review', 'review my Go code', 'Cog PR').

DimensionReasoningScore

Specificity

Names the domain and a single action ('Go code review guidelines for the Cog codebase') but lists no multiple specific concrete actions, matching the level-2 anchor; it is not level 1 (it does name a concrete domain/action) nor level 3 (no enumerated actions).

2 / 3

Completeness

States what the skill provides (Go code review guidelines) but has no 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2 (what present, when missing/implied).

2 / 3

Trigger Term Quality

Includes relevant natural terms ('Go code review', 'Cog codebase') a user might say, but misses common variations like 'PR review' or 'review my Go code', fitting the level-2 anchor with partial coverage.

2 / 3

Distinctiveness Conflict Risk

Scoped to Go and the Cog codebase, giving it a recognizable niche, but the thin 'guidelines' framing could still overlap with generic review skills, matching the level-2 'somewhat specific but could still overlap' anchor.

2 / 3

Total

8

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
replicate/cog
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.