CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

statusline-generator

Installs, configures, customizes, or troubleshoots the Claude Code statusline (cwd, model, token counts). Use when the user wants to set up or change the statusline, switch minimal vs full layouts, show absolute token counts instead of a percentage, add cost via ccusage, or fix a statusline that is blank, silent, stuck, or stopped updating. Trigger phrases: 状态栏, 状态栏不显示, 状态栏空白, "statusline blank", "statusline broken".

77

Quality

97%

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

92%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.

Excellent body: self-verifying install/repair workflows, executable commands with expected outputs, and a well-structured reference layer with per-file load guidance. The only blemish is the narrative length of the Rule 3 performance rationale, which could be tightened without losing its substance.

DimensionReasoningScore

Conciseness

The body is dense and efficient — commands, dependency tables, and rendered output samples with no explanation of concepts Claude already knows. The one trimmable spot is the Rule 3 narrative ("A statusline script looks like UI polish...", the 2026-07 battery-drain anecdote, ~0.4s vs ~0.01s measurements), which is valuable non-obvious guidance but told at story length. Fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the leaner 5 anchor.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout: `bash scripts/health_check.sh`, `bash scripts/install_statusline.sh`, `export CLAUDE_STATUSLINE_LAYOUT=full`, `export CLAUDE_STATUSLINE_DEBUG=1`, `echo '{}' | bash your-script.sh`, plus concrete replay (`cat /tmp/.claude-statusline-last-stdin.json | ~/.claude/statusline.sh`) and per-platform jq install lines. Expected outputs are shown for both layouts.

5 / 5

Workflow Clarity

Clear sequenced workflows with explicit validation and feedback loops: health check runs first and each failure prints a one-line fix command; the installer backs up, copies, chmods, wires settings.json, then mandatorily runs the health check and exits non-zero on failure ('installation is not complete until verification passes'); hand-edits get a mock-test-before-done rule. This matches the validate → fix → retry anchor.

5 / 5

Progressive Disclosure

The body is a clear overview with well-signaled one-level-deep references — context-window-schema, customization, troubleshooting-decision-tree, color_codes, ccusage_integration — all of which exist as real files, each linked with explicit 'load when' guidance, plus a Resources table mapping every bundle file to its purpose. Appropriately split with nothing over-inlined.

5 / 5

Total

19

/

20

Passed

Description

100%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 model description: third-person concrete capabilities, an explicit 'Use when...' clause covering setup, customization, and repair scenarios, and concrete trigger phrases in both English and Chinese. No padding or over-claims.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ("Installs, configures, customizes, or troubleshoots the Claude Code statusline (cwd, model, token counts)") plus specific sub-tasks ("switch minimal vs full layouts", "show absolute token counts instead of a percentage", "add cost via ccusage", "fix a statusline that is blank, silent, stuck, or stopped updating") — comprehensive coverage with no vague filler, matching the top anchor.

5 / 5

Completeness

It clearly answers "what" in third person (installs/configures/customizes/troubleshoots the statusline with cwd, model, token counts) and "when" with an explicit "Use when the user wants to..." clause plus concrete trigger phrases, exactly matching the 5 anchor example pattern.

5 / 5

Trigger Term Quality

Explicit trigger phrases include natural user wording with synonyms ("statusline blank", "statusline broken", "stuck", "stopped updating") plus bilingual variants (状态栏, 状态栏不显示, 状态栏空白) that users would naturally say. Coverage is comprehensive rather than merely good, so it fits the 5 anchor over the 4.

5 / 5

Distinctiveness Conflict Risk

The scope is a single clear niche — the Claude Code statusline — with triggers (blank/broken/stuck statusline, layout switching, token counts) that would not plausibly fire for any other skill. Minimal conflict risk, matching the 5 anchor.

5 / 5

Total

20

/

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

daymade/claude-code-skills

Path

daymade-claude-code/statusline-generator/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.