CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-probe-dev

Develop, test and ship the Go agent probe (apps/agent) — build/test commands, protocol versioning, the nekoagent service wrapper, and constraints of router environments (OpenWrt/tmpfs). Use for any change under apps/agent.

76

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

87%Weight 40%Scale 1-3

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

A concise, highly actionable dev guide with executable verification gates and well-organized sections. Its main gap is workflow clarity: constraints and a validation gate are present but not assembled into an explicit end-to-end change sequence with feedback loops.

Suggestions

Add a short numbered change workflow (e.g. 1. make change, 2. run the Verify gate, 3. fix and re-run until clean, 4. bump protocol version if payload changed) so the existing rules and gate form an explicit sequence.

Add a feedback loop after the Verify section: what to do when `go vet`/`sh -n` fails (fix and re-run, do not proceed) to lift workflow clarity to level 3.

Make the protocol-versioning release coupling a mini-checklist (bump AgentProtocolVersion + collector minimum + ship in one commit) rather than a prose rule, so the multi-step contract is sequenced.

DimensionReasoningScore

Conciseness

Lean and dense with substance — concrete file paths, commands, and constraints — without explaining concepts Claude already knows (e.g. what Go or systemd is). Every section earns its tokens.

3 / 3

Actionability

Provides copy-paste-ready executable commands (go vet/build/test, sh -n syntax gate, curl timeout flags, git tag/release flow) and exact file paths, fully meeting the level-3 anchor.

3 / 3

Workflow Clarity

An explicit Verify validation gate exists, but the body is organized as rules plus a gate rather than a clearly sequenced change workflow with feedback loops for error recovery, so it sits at level 2 rather than 3.

2 / 3

Progressive Disclosure

Under 50 lines, single-purpose, and well-organized into sections (Layout, Verify, Hard rules, Release) with one-level-deep pointers to repo docs (docs/agent/release.en.md, deep-review note), matching the simple-skill allowance for level 3.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 strong, tightly-scoped description that states concrete capabilities and an explicit path-based usage trigger, cleanly answering both what and when. It is concise without fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Develop, test and ship") plus enumerated sub-areas (build/test commands, protocol versioning, nekoagent service wrapper, router constraints), matching the level-3 anchor of several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (develop/test/ship the Go agent probe with the listed sub-areas) and when ("Use for any change under apps/agent"), satisfying the level-3 anchor with an explicit trigger.

3 / 3

Trigger Term Quality

Includes the natural path-based trigger "Use for any change under apps/agent" alongside domain terms (Go agent probe, nekoagent, OpenWrt/tmpfs) a contributor would actually say, giving good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to apps/agent and the Go agent probe with a path-qualified trigger, giving it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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
foru17/neko-master
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.