CtrlK
BlogDocsLog inGet started
Tessl Logo

linux-speed-optimizer

Use when the user asks to optimize, speed up, tune, or make a Linux system faster — laptops, desktops, or servers. Analyzes hardware, kernel and boot parameters, memory/swap/zram, storage, services, GPU, desktop environment, and network; proposes a prioritized, risk-labeled optimization plan; applies ONLY user-approved changes; verifies every change and documents rollback. Idempotent: re-running on the same system converges, never duplicates config, never re-installs. Analyze-only mode is available. Do NOT use for application code, containers, or website performance.

72

Quality

88%

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

85%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 operational content: executable, idempotent recipes with guards and readback verification, and a well-sequenced approval-gated workflow. The main weakness is structure — everything lives in one long file where per-distro deep-dive material (custom kernels, distribution matrix) should be offloaded to reference files.

Suggestions

Move section 4.7 (custom kernel) and section 8 (distribution matrix) into a references/ file (e.g., references/distro-matrix.md) and keep only a pointer plus the guard rules in SKILL.md.

Deduplicate the safety rules: the analyze-only-until-approved and ask-per-service rules appear in sections 0, 3, and 9; state them once and cross-reference.

Trim the opening paragraph, which restates the frontmatter description without adding operational value.

DimensionReasoningScore

Conciseness

The body is command-dense and assumes Claude's competence (e.g., 'ROTA=0 = SSD' as a terse note, no library tutorials), but the analyze-only/approval rule is restated across sections 0, 3, and 9, and the intro repeats the frontmatter — minor trimming opportunities.

4 / 5

Actionability

Nearly every section gives copy-paste-ready bash with concrete guards (grep -q, systemctl is-enabled, dpkg -s), exact sed edits, and a verification matrix mapping each change type to a readback command — fully executable across the common cases.

5 / 5

Workflow Clarity

A clear numbered sequence (preflight → read-only analysis → approval gate → guarded apply → verification matrix → report → idempotency re-check) with explicit validation checkpoints and feedback loops ('readback MUST match', 'verify AFTER every change'), satisfying the destructive/batch validation requirement.

5 / 5

Progressive Disclosure

The skill is a ~300-line monolithic SKILL.md with no bundle files at all: content that clearly belongs in separate reference files — the per-distro custom-kernel instructions (4.7) and the distribution matrix (8) — is inlined rather than split into one-level-deep references.

3 / 5

Total

17

/

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 description: concrete capabilities in third person, an explicit trigger clause, and a well-drawn boundary including what not to use it for. The only gap is a few natural trigger synonyms (e.g., 'slow', 'performance').

DimensionReasoningScore

Specificity

The description lists many concrete, third-person actions ('Analyzes hardware, kernel and boot parameters, memory/swap/zram, storage, services, GPU', 'proposes a prioritized, risk-labeled optimization plan', 'applies ONLY user-approved changes', 'verifies every change and documents rollback') with comprehensive domain coverage — no generic filler.

5 / 5

Completeness

It explicitly answers 'when' with a concrete trigger clause ('Use when the user asks to optimize, speed up, tune...') and 'what' with the full analyze/plan/apply/verify/rollback capability list, plus idempotency and analyze-only mode.

5 / 5

Trigger Term Quality

'optimize, speed up, tune, or make a Linux system faster' covers the main natural phrases well, but common user phrasings like 'slow', 'laggy', or 'performance' are absent, so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Clear Linux-system-performance niche with an explicit negative boundary ('Do NOT use for application code, containers, or website performance'), which sharply separates it from code-profiling and web-performance skills.

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
administrakt0r/pro-skills-repo-administraktor
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.