CtrlK
BlogDocsLog inGet started
Tessl Logo

architecture-optimization

Guided journey from a working codebase grown slow and tangled to one measurably fast, cleanly bounded, and readable. Orchestrates eight skills phase by phase - working-with-legacy-code, clean-architecture, software-design-philosophy, refactoring-patterns, system-design, ddia-systems, release-it, pragmatic-programmer - every phase carries its method inline so it runs standalone, asking the user questions at every decision point and recording results in the project docs/ folder (PERFORMANCE.md, ARCHITECTURE.md, ARCHITECTURE-OPTIMIZATION-PLAN.md) so the journey resumes across sessions. Use when the user wants to make an app faster, untangle drifted boundaries, fix slow endpoints and queries, or says 'it works but it is slow and getting worse'. For an untested prototype, improve-code-quality; for an aged codebase you fear to touch, remove-technical-debt; for greenfield structure, design-code-architecture; for marketing-site page speed, improve-website. For one framework in isolation, invoke that skill directly.

73

Quality

90%

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

The canonical home for this skill is architecture-optimization in wondelai/skills

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 a highly actionable, well-sequenced orchestration guide with strong validation checkpoints and clean references to real bundle files. Its main weakness is conciseness: the inline Briefs re-explain known concepts and add length that could be trimmed or moved into the existing methods reference.

Suggestions

Trim the inline Briefs' re-explanation of concepts Claude already knows (Amdahl's law, the USE method, the Dependency Rule direction, N+1 queries, Little's law) down to their task-specific application, since the full method already lives in references/methods.md.

Consider moving the per-phase Briefs into references/methods.md (or a dedicated briefs file) so SKILL.md reads as a leaner orchestration overview, which would also raise the progressive_disclosure score.

Consolidate the repeated 'Done when' phrasing that appears in both the Operating Rules and each phase exit to reduce redundancy across the document.

DimensionReasoningScore

Conciseness

The body is information-dense and largely actionable, but the inline Briefs re-explain concepts Claude already knows (Amdahl's law, the USE method, the Dependency Rule direction, N+1 queries, Little's law), and the overall length could be tightened.

3 / 5

Actionability

Each phase names the constituent skill by slug, lists concrete user decisions with options, specifies exact artifact files and section headings, and gives a concrete install command ('npx skills add wondelai/skills/<slug> --global') with an explicit Brief fallback.

5 / 5

Workflow Clarity

A clearly sequenced eight-phase journey with a Phase 1 GATE, per-phase 'Done when' checkpoints, explicit validation feedback loops (re-measure, revert what doesn't beat baseline, sign-off before writing artifacts, tests green between refactors), and a closing exit checklist.

5 / 5

Progressive Disclosure

Clean one-level-deep references to real bundle files (references/methods.md, references/artifact-templates.md) are well signaled in context, but the body still carries substantial inline per-phase Brief detail that a leaner overview would offload more aggressively to methods.md.

4 / 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 exceptionally strong: it states concrete capabilities, provides natural trigger phrases including a user quote, answers both what and when, and explicitly routes away from related skills. Its only weakness is verbosity for a description field, though no conciseness dimension applies here.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('make an app faster, untangle drifted boundaries, fix slow endpoints and queries') and enumerates the eight orchestrated skills, giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what ('Guided journey ... orchestrates eight skills phase by phase') and when ('Use when the user wants to make an app faster ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user-facing phrases are present, including the verbatim quote 'it works but it is slow and getting worse' plus 'make an app faster' and 'fix slow endpoints and queries', covering synonyms and a direct user utterance.

5 / 5

Distinctiveness Conflict Risk

A clear niche (a working codebase grown slow and tangled) is paired with explicit routing away from siblings (improve-code-quality, remove-technical-debt, design-code-architecture, improve-website), minimizing 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
wondelai/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.