CtrlK
BlogDocsLog inGet started
Tessl Logo

snb-worktime-webui

Work on the `snb-worktime-webui` project in the SNB repository: a Go application with an embedded web UI for calculating employee worktime from Windows session snapshots and workstation or network activity windows. Use when adding features, fixing bugs, adjusting parsing rules, changing calculation logic, refining the web UI, updating Windows build flow, or integrating new telemetry sources for this specific project.

75

Quality

94%

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

SKILL.md
Quality
Evals
Security

Quality

Content

93%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.

An exemplary lean skill body: concrete commands and paths, project rules that capture non-derivable constraints, and a clean one-level reference split. The only gap is the absence of an explicit failure-handling loop around the test/build verification step.

DimensionReasoningScore

Conciseness

The ~40-line body contains only project-specific knowledge Claude cannot infer: paths ("/home/igor/SNB/snb-worktime-webui", "internal/web/static"), architecture constraints, category names ("worked, confirmed, unconfirmed, idle, disconnected, unknown"), and exact build commands. No padding and no explanation of concepts Claude already knows; every token earns its place, matching the 5 anchor.

5 / 5

Actionability

Guidance is concrete and copy-paste ready: "go test ./..." and "GOOS=windows GOARCH=amd64 go build -o dist/snb-worktime-webui.exe ./cmd/snb-worktime-webui", plus specific packages ("internal/worktime") and file locations. Per the rubric's instruction-only-skill note, the absence of code samples is not penalized because the guidance is directly actionable; matches the 5 anchor.

5 / 5

Workflow Clarity

A clear 5-step sequence exists with an explicit validation gate ("Before finishing, run: go test ./... [and the] GOOS=windows ... go build"), and tests are required for parser/calculation changes. It is 4 rather than 5 because there is no explicit error-recovery feedback loop (e.g., what to do when tests or the build fail), and the read-README/confirm-map steps lack checkpoints.

4 / 5

Progressive Disclosure

The body is a lean overview with well-organized sections (Overview, Workflow, Project Rules, Typical Tasks, References) and a single clearly-signaled, one-level-deep reference: "Read references/project-map.md before substantial changes", repeated in the References section. The referenced file exists and itself contains no nested references, matching the 5 anchor.

5 / 5

Total

19

/

20

Passed

Description

92%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 strong project-scoped description: concrete what, explicit multi-trigger when-clause, and distinctive project identifiers. The only weakness is slight keyword redundancy in phrasing variants a user might employ.

DimensionReasoningScore

Specificity

The description states a concrete capability ("a Go application with an embedded web UI for calculating employee worktime from Windows session snapshots and workstation or network activity windows") and lists multiple specific actions: "adding features, fixing bugs, adjusting parsing rules, changing calculation logic, refining the web UI, updating Windows build flow, or integrating new telemetry sources". This matches the 5 anchor (multiple specific concrete actions, comprehensive coverage) rather than 4, since the action list covers all major subsystems of the project; only the generic verbs "adding features, fixing bugs" keep it from being perfectly precise.

5 / 5

Completeness

It explicitly answers both questions: what it does (Go application with embedded web UI computing employee worktime from session snapshots and activity windows) and when to use it via a concrete "Use when adding features, fixing bugs, adjusting parsing rules..." clause. This is the 5 anchor — clear what AND when with concrete trigger phrases; the explicit 'Use when' clause also avoids the 3-cap.

5 / 5

Trigger Term Quality

Natural trigger terms are present: "snb-worktime-webui", "parsing rules", "calculation logic", "web UI", "Windows build", "telemetry sources", "session snapshots", "activity windows" — phrases a user of this project would naturally say. It sits at 4 rather than 5 because a few natural synonyms are missing (e.g., "work time", "hours", "attendance", "collector"), though for a project-scoped skill the repo name is the dominant trigger.

4 / 5

Distinctiveness Conflict Risk

It names the exact project ("snb-worktime-webui"), the repository ("SNB"), and project-specific subsystems (Windows session snapshots, Windows build flow), ending with "for this specific project". Minimal conflict risk with any other skill; matches the 5 anchor (clear niche with distinct triggers).

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
igor04091968/SNB
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.