CtrlK
BlogDocsLog inGet started
Tessl Logo

ralph-prompt-project

Generate Ralph-compatible prompts for entire projects from scratch. Creates comprehensive prompts with architecture phase, implementation phases, testing, and documentation. Use when building complete applications, libraries, CLI tools, or any greenfield project requiring end-to-end development.

61

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ralph-prompt-project/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%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 workflow sequencing and actionable examples, but the body is padded with marketing material and inlines large content (worked example, repeated templates) that would benefit from separate reference files for token efficiency and navigation.

Suggestions

Remove the 'Real-World Success' and 'Ralph Philosophy' sections — they are marketing padding that does not help Claude execute and consume context budget.

Move the full REST API worked example (~195 lines) into a separate references/ file and link to it from the body, keeping only a brief inline sketch.

Collapse the six near-identical generic phase templates into a single parameterized template plus a phase table, rather than repeating Objective/Tasks/Deliverables/Verification/Checkpoint scaffolding six times.

DimensionReasoningScore

Conciseness

Noticeably verbose: the 'Real-World Success' and 'Ralph Philosophy' sections ('Geoffrey Huntley used Ralph...', '$50k contract completed for $297') are marketing padding, and the generic six-phase template repeats with non-executable `[build command]`/`[lint command]` placeholders that could be tightened.

2 / 5

Actionability

Provides concrete executable guidance — the REST API example includes real curl/npm commands and the Ralph-loop integration command '/ralph-wiggum:ralph-loop "..." --completion-promise "YOUR_PROMISE" --max-iterations 100' — but the generic phase templates rely on `[command]` placeholders, leaving minor gaps.

4 / 5

Workflow Clarity

Clear 4-step generation workflow plus six sequenced phases, each with Objective/Tasks/Deliverables/Verification/Checkpoint ('PHASE 0 COMPLETE: ... → Continue to Phase 1'), an 'If Stuck' error-recovery feedback loop, and a final verification checklist — explicit validation checkpoints throughout.

5 / 5

Progressive Disclosure

Internally well-sectioned with headers, but it is a monolithic 650-line file with no bundle/reference files (references/, scripts/, assets/ absent); the ~195-line REST API worked example and repeated phase templates are inlined where separate reference files would aid navigation.

3 / 5

Total

14

/

20

Passed

Description

83%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 that clearly states both capability and explicit 'Use when' triggers with concrete, natural phrases. Minor room to improve via added synonyms and tighter distinctiveness against sibling Ralph skills.

DimensionReasoningScore

Specificity

Names several concrete actions — 'architecture phase, implementation phases, testing, and documentation' — but describes prompt structure rather than a fully comprehensive action set, leaving minor gaps.

4 / 5

Completeness

Explicitly answers both what ('Generate Ralph-compatible prompts...Creates comprehensive prompts with architecture phase, implementation phases, testing, and documentation') and when ('Use when building complete applications, libraries, CLI tools, or any greenfield project...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'building complete applications, libraries, CLI tools, or any greenfield project requiring end-to-end development' gives good natural keyword coverage, though it lacks synonyms and concrete signal terms users might also say.

4 / 5

Distinctiveness Conflict Risk

'Ralph-compatible prompts for entire projects from scratch' and 'greenfield project' carve a clear niche, but the broad trigger phrases overlap with sibling Ralph skills (single-task, multi-task, research) and general project-building skills.

4 / 5

Total

17

/

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

skill_md_line_count

SKILL.md is long (654 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.