CtrlK
BlogDocsLog inGet started
Tessl Logo

application-performance-performance-optimization

Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating performance optimization across the stack.

75

1.71x
Quality

66%

Does it follow best practices?

Impact

89%

1.71x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/application-performance-performance-optimization/SKILL.md

The canonical home for this skill is application-performance-performance-optimization in rmyndharis/antigravity-skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

A well-structured, actionable phased workflow that is weakened by a redundant extended-thinking preamble, missing validation checkpoints between destructive phases, and a monolithic single-file layout with no progressive disclosure.

Suggestions

Remove or drastically shorten the 'Extended thinking' paragraph; it restates the workflow in conceptual prose without adding executable guidance.

Add explicit validate-before-proceeding checkpoints between phases (e.g., confirm baseline metrics before optimizing, verify load-test results before declaring success) since load testing and DB/backend changes are destructive/batch operations.

Move the 13 detailed per-step prompts and the configuration/success-criteria blocks into one-level-deep reference files (e.g., PHASES.md, CONFIG.md) and keep SKILL.md as a concise overview with clearly signaled links.

DimensionReasoningScore

Conciseness

The body is mostly efficient structurally, but the 'Extended thinking' paragraph restates the workflow in padded, conceptual prose that adds no actionable value and could be trimmed.

3 / 5

Actionability

Each phase provides concrete Task prompts naming specific tools (k6/Gatling/Artillery, DataDog/New Relic, Redis/Memcached) and subagent types, giving mostly executable guidance with minor gaps around verifying those agents exist.

4 / 5

Workflow Clarity

A clearly sequenced 5-phase process exists, but destructive/batch operations (production load testing, DB/backend changes) lack explicit validate-before-proceeding checkpoints, capping this at 3 per the rubric.

3 / 5

Progressive Disclosure

Sections are well-organized, but the skill is monolithic: all 13 step prompts, configuration, and success criteria are inlined with no external reference files despite being long enough to benefit from them.

3 / 5

Total

13

/

20

Passed

Description

75%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 solid, third-person description that answers both what and when with an explicit trigger clause. It is slightly held back by a broad 'when' condition and the generic word 'tuning' in place of more concrete actions.

DimensionReasoningScore

Specificity

Names several concrete action areas — 'profiling, observability, and backend/frontend tuning' — though 'tuning' is somewhat generic, leaving minor coverage gaps.

4 / 5

Completeness

Clearly states the 'what' (optimize end-to-end performance via profiling/observability/tuning) and an explicit 'Use when coordinating performance optimization across the stack' clause, though the 'when' is broad rather than trigger-specific.

4 / 5

Trigger Term Quality

Includes natural phrases a user would say ('application performance', 'performance optimization', 'across the stack') but misses common synonyms like 'speed up' or 'latency'.

4 / 5

Distinctiveness Conflict Risk

The end-to-end stack-wide performance optimization niche is mostly distinct, with only minor overlap risk against generic optimization or single-layer tuning skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.