CtrlK
BlogDocsLog inGet started
Tessl Logo

spec-generator

Prompt template and output format for the Repository OS /spec command — generates structured specification summaries of indexed source files using retrieved code context from ChromaDB.

63

Quality

72%

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 ./tile-source/skills/spec-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured, actionable skill that clearly explains how to implement the /spec command. The workflow is explicit and the code examples are executable. The main weakness is some verbosity in the example output section and quality criteria that could be tightened without losing clarity.

Suggestions

Trim the example output to show just one function/class entry instead of three, since the pattern is clear from the prompt template

Consider moving the full prompt template to a separate file and referencing it, keeping only a brief summary inline

DimensionReasoningScore

Conciseness

The skill is mostly efficient but includes some redundancy. The example output section is quite lengthy and could be trimmed since the prompt template already shows the expected format. The quality criteria section restates some obvious points.

2 / 3

Actionability

Provides fully executable Python code for chunk retrieval, a complete prompt template ready for use, and a detailed example output. Claude can implement this command directly from the provided content.

3 / 3

Workflow Clarity

The 6-step workflow is clearly numbered and sequenced. Error handling is explicit (what to do when no chunks found). The process from user invocation to output/save is unambiguous.

3 / 3

Progressive Disclosure

Content is well-organized with clear sections, but everything is inline in a single file. The lengthy example output and prompt template could potentially be referenced externally, though for a skill of this size it's borderline acceptable.

2 / 3

Total

10

/

12

Passed

Description

67%Scale 1-3

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 technically precise and clearly identifies a specific command within a named system (Repository OS /spec). It excels at distinctiveness and specificity but falls short on completeness by lacking an explicit 'Use when...' clause, and uses technical jargon that may not match natural user language.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user invokes /spec or asks for code specifications, file summaries, or repository documentation.'

Include more natural trigger terms users might say, such as 'spec', 'specification', 'summarize code', 'document files', or 'code summary'.

DimensionReasoningScore

Specificity

Lists specific concrete actions: 'generates structured specification summaries of indexed source files using retrieved code context from ChromaDB'. Describes the exact mechanism (prompt template, output format) and data source (ChromaDB).

3 / 3

Completeness

Clearly answers 'what' (generates specification summaries using ChromaDB context), but lacks an explicit 'Use when...' clause. The trigger conditions are only implied through mentioning '/spec command'.

2 / 3

Trigger Term Quality

Includes '/spec command' and 'Repository OS' as trigger terms, but uses technical jargon like 'ChromaDB' and 'indexed source files' that users may not naturally say. Missing common variations like 'spec', 'specification', 'summarize code'.

2 / 3

Distinctiveness Conflict Risk

Highly distinctive with specific references to 'Repository OS', '/spec command', and 'ChromaDB'. Very unlikely to conflict with other skills due to the unique combination of system name and command.

3 / 3

Total

10

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
tombrewsviews/repository-os-mvp
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.