CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

go

Best practices for working with Go codebases. Use when writing, debugging, or exploring Go code, including reading dependency sources and documentation.

Quality

72%

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 ./Skills/agent-ops/go/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 skill body is lean and its core Go guidance (error wrapping, style) is concrete with one good executable example, but it reads as two concatenated templates with redundant generic sections, its validation loop lacks any concrete commands, and its single deep reference points to a path that does not resolve in the bundle.

Suggestions

Fix the reference path: the body cites 'Infrastructure/references/deep-guidance.md' but the bundle file is at 'references/deep-guidance.md', so the link is broken as written.

Replace vague validation steps ('Re-run the highest-signal validations', 'Run the relevant local checks') with concrete commands such as 'go test ./...' and 'go vet ./...' so the fail-fast loop is executable.

Consolidate the duplicated template halves (When to use/Required inputs/Deliverables vs Philosophy/Procedure/Validation/Constraints/Anti-patterns) into one coherent set of sections and update the Table of Contents to list all of them.

DimensionReasoningScore

Conciseness

The body is bullet-based and terse, but the second half (Philosophy, Procedure, Validation, Constraints, Anti-patterns) reads like a second concatenated template with generic boilerplate Claude already knows ('Optimize for clear, verifiable outcomes', 'Redact secrets... by default', 'Silent ignored errors usually become runtime bugs'). Mostly efficient, but noticeable trimming and consolidation is possible — not the anchor-2 'noticeably verbose' since no section is padded prose.

3 / 5

Actionability

There is one complete, executable code example (ParsePort) and concrete directives ('Return wrapped errors with %w', 'Return concrete structs from constructors'), but the execution-critical parts are vague: 'Re-run the highest-signal validations' and 'Run the relevant local checks' never name commands like 'go test ./...' or 'go vet'. Some concrete guidance, but key details are missing.

3 / 5

Workflow Clarity

The Procedure section gives a clear 1-2-3 sequence and the Validation section names a fail-fast/re-run loop, so it is above anchor 2. But the validation checkpoints are abstract ('highest-signal validations', 'relevant local checks') rather than explicit commands, so checkpoints are named but not concretized — anchor 3's 'sequence present but checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

The deep-guidance reference is well signaled with a 'Read when' condition, but the referenced path 'Infrastructure/references/deep-guidance.md' does not exist in the bundle — the actual file is 'references/deep-guidance.md' — so navigation is broken as written. Additionally the Table of Contents omits six later sections (Philosophy through References and assets). Some structure, but organization gaps and a non-resolving reference keep it at anchor 3 rather than 4.

3 / 5

Total

12

/

20

Passed

Description

82%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.

A solid description with an explicit and specific 'Use when' clause, good natural keywords, and clear Go-specific niche. The main weakness is the generic 'Best practices' framing of the what, and missing common trigger synonyms like 'golang' or '.go files' in the description text.

DimensionReasoningScore

Specificity

The description names the domain ('working with Go codebases') and lists actions in the trigger clause ('writing, debugging, or exploring Go code, including reading dependency sources'), but the what is framed as generic 'Best practices' rather than concrete capabilities like the anchor-4 pattern of verb-plus-object actions, so it sits at 'names domain and some concrete actions, but not comprehensive'.

3 / 5

Completeness

It explicitly answers both: what ('Best practices for working with Go codebases... including reading dependency sources and documentation') and when ('Use when writing, debugging, or exploring Go code') with a concrete 'Use when' trigger clause. It is not the anchor-4 case because the when-clause is already explicit and specific with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases users would say are present ('Go codebases', 'Go code', 'writing', 'debugging'), but common variants like 'golang', '.go files', and 'Go modules' are missing from the description itself (they only appear in metadata triggers). Good coverage with a few natural terms missing — matches the anchor-4 example.

4 / 5

Distinctiveness Conflict Risk

'Go codebases' / 'Go code' is a clear language-specific niche with distinct triggers and minimal overlap risk with other skills — matches the anchor-5 'clear niche with distinct triggers'.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Skills/agent-ops/go/SKILL.md

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.