CtrlK
BlogDocsLog inGet started
Tessl Logo

prompt-architect

Create and enhance prompts, system instructions, and principle files. Capabilities: transform verbose prompts, add patterns/heuristics, optimize token usage, structure CLAUDE.md principles, improve agent/persona definitions, apply prompt engineering techniques (CoT, few-shot, ReAct). Actions: create, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, system prompt, CLAUDE.md, principle files, instruction optimization, agent prompt, persona prompt, token efficiency, prompt structure, workflow prompts, rules, constraints, few-shot, chain-of-thought, soul, tensions, dialectic. Use when: creating new prompts, enhancing principle files, improving system instructions, optimizing CLAUDE.md, restructuring verbose prompts, adding patterns to workflows, defining agent behaviors.

92

1.28x
Quality

90%

Does it follow best practices?

Impact

95%

1.28x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

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 highly actionable with concrete templates, decision tables, and validation checkpoints, and it assumes Claude's intelligence without over-explaining basics. The main weakness is conciseness, with the soul example and several transformation examples repeated across sections.

Suggestions

De-duplicate the <soul> content: keep the template in <building_blocks> and shorten the top example to a reference or a single tension, rather than reproducing it verbatim twice.

Consolidate the repeated few-shot-to-taxonomy before/after blocks in <key_transformations> into one representative pair plus a list of domains where the pattern applies.

Consider moving the large building_blocks templates and key_transformations examples into a separate reference file (e.g. references/templates.md) to improve progressive disclosure and reduce the monolithic body.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence, but the full <soul> example is duplicated in <building_blocks>, and several before/after few-shot-to-taxonomy blocks repeat the same point, adding padding that could be trimmed.

3 / 5

Actionability

Provides copy-paste-ready templates, decision tables (detect_mode, technique_selection, diagnosis), concrete building-block code blocks, and a fully worked YAML example covering common cases.

5 / 5

Workflow Clarity

Clear sequenced flow from mode detection through diagnosis, technique selection, output formatting, and explicit validation tests (Key/Dialectic/Compression/Taxonomy) with a summary checklist and feedback guidance.

5 / 5

Progressive Disclosure

Well-organized single-file skill with clearly signaled section headers and no nested references, but no bundle files exist and substantial template/example content that could live in separate reference files is inlined.

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 comprehensive and well-structured, covering concrete capabilities, an explicit keyword list, and clear trigger conditions in third person. It directly mirrors the strongest reference examples.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('create, enhance, optimize, refactor, compress prompts', 'transform verbose prompts', 'add patterns/heuristics', 'structure CLAUDE.md principles', 'apply prompt engineering techniques') with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (Capabilities and Actions sections) and 'when' (a concrete 'Use when:' clause with multiple trigger phrases).

5 / 5

Trigger Term Quality

Extensive natural keyword coverage including synonyms and abbreviations ('prompt engineering, system prompt, CLAUDE.md, principle files, instruction optimization, agent prompt, persona prompt, token efficiency, few-shot, chain-of-thought').

5 / 5

Distinctiveness Conflict Risk

Clear niche around prompt architecture with distinct triggers (CLAUDE.md, principle files, persona/agent prompts); minimal overlap risk with other skills.

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
majiayu000/claude-skill-registry
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.