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.

75

Quality

92%

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

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.

The body is highly actionable with a well-sequenced, validation-rich workflow, but it is a dense single-file monolith with no progressive disclosure via reference files, and carries minor conciseness redundancy.

Suggestions

Split the monolithic body into progressive disclosure: keep overview, operating principles, the workflow, and the verification matrix in SKILL.md, and move the distribution matrix, custom-kernel install recipes, and detailed per-distro sysctl/zram config into one-level-deep reference files (e.g. references/distro-matrix.md, references/custom-kernel.md) linked from SKILL.md.

Consolidate the idempotency guidance, which is currently repeated in Operating Principle 2, the Section 4 intro, and Section 7, into one authoritative statement and cross-reference it elsewhere.

Trim asides that restate widely-known facts (e.g. "ROTA=0 = SSD (fstrim/discard relevant)") and keep only the tuning rationale, relying on Claude's competence for basics.

DimensionReasoningScore

Conciseness

Mostly lean and command-dense, assuming competence, but with minor trimmable asides (e.g., "ROTA=0 = SSD") and light redundancy on idempotency across Operating Principle 2, Section 4 intro, and Section 7, fitting the "efficient; minor over-explanation" anchor rather than the fully-lean 5.

4 / 5

Actionability

Provides copy-paste-ready guard/apply/verify bash recipes with exact paths, specific sysctl values, per-distro config locations, and readback checks (e.g., "/sbin/sysctl vm.swappiness # readback MUST match"), matching the fully-executable anchor covering common cases.

5 / 5

Workflow Clarity

A clearly sequenced Preflight → Analysis → Approval gate → Apply → Verify → Report pipeline with explicit validation checkpoints (the verification matrix table), guard→apply→verify feedback loops, and idempotency re-checks, matching the anchor for clear sequencing with explicit validation and checklists; the destructive-operation validation cap is satisfied.

5 / 5

Progressive Disclosure

The 313-line body is well-sectioned internally but is a monolithic single file with no external references, and content that could be split (the distribution matrix, custom-kernel install recipes, detailed per-distro sysctl/zram config) is inlined, fitting the anchor for some structure with content that should be separate kept inline rather than the well-split 4 or 5.

3 / 5

Total

17

/

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.

The description is exemplary: concrete, comprehensive, third-person, with a natural trigger clause and explicit boundaries. It answers what, when, and what-not with minimal padding.

DimensionReasoningScore

Specificity

Lists many concrete actions across a comprehensive scope: "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," matching the anchor for multiple specific concrete actions with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (analyze, propose, apply, verify, document rollback, idempotent) and when ("Use when the user asks to optimize, speed up, tune, or make a Linux system faster"), and adds an explicit out-of-scope clause, matching the anchor for clearly answering both with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Use when the user asks to optimize, speed up, tune, or make a Linux system faster" supplies several natural synonyms a user would actually say, plus target platforms (laptops, desktops, servers), matching comprehensive natural-term coverage including synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Linux system performance tuning) and the explicit exclusion "Do NOT use for application code, containers, or website performance" sharply reduces overlap with adjacent skills, matching the anchor for a clear niche with minimal conflict risk.

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.

Validation16 / 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.