CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

76%

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 ./.tessl/tiles/repository-os/mvp/skills/spec-generator/SKILL.md

The canonical home for this skill is spec-generator in tombrewsviews/repository-os-mvp

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 content is highly actionable with executable code, an exact prompt template, and a complete worked example, organized into clear sections with a sensible error checkpoint. Minor gains are available from tightening redundancy and adding a spec-format validation checkpoint.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's knowledge (no explanation of ChromaDB or specs), but the full worked example output and slight overlap between 'How /spec Works' and 'Retrieval Method' could be trimmed slightly.

4 / 5

Actionability

Provides copy-paste-ready Python retrieval code, the exact prompt to send to Claude, the precise output format template, and a complete worked example — fully executable guidance covering the common case.

5 / 5

Workflow Clarity

A clear 6-step numbered sequence with an explicit error checkpoint for missing/unindexed files; only minor validation gaps remain (no explicit verification that the generated spec conforms to the format).

4 / 5

Progressive Disclosure

Well-organized into clear ## sections in a single self-contained file with no bundle files to reference; scored 4 rather than 5 because the >50-line monolithic body inlines the full prompt and example rather than splitting deeper detail into reference files.

4 / 5

Total

17

/

20

Passed

Description

58%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 clearly communicates what the skill does and its distinct niche, but lacks an explicit 'when to use it' trigger clause and natural user-facing trigger phrases. Adding a 'Use when...' sentence would lift both completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when ...' clause naming natural user phrases, e.g. 'Use when the user runs /spec, asks for a specification summary of a source file, or wants a Tessl-style spec tile.'

Broaden trigger terms with user-natural synonyms like 'summarize this file', 'spec this file', and 'spec tile' so the skill surfaces on common phrasings.

Trim the implementation detail ('retrieved code context from ChromaDB') in favor of outcome-focused language to keep the description outcome-oriented and concise.

DimensionReasoningScore

Specificity

Names several concrete actions — 'generates structured specification summaries of indexed source files using retrieved code context from ChromaDB' and frames it as the 'Prompt template and output format for the /spec command' — with only minor coverage gaps.

4 / 5

Completeness

The 'what' is clear (generates structured spec summaries via ChromaDB retrieval), but there is no explicit 'Use when...' trigger clause, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords like '/spec command', 'specification summaries', and 'source files' appear, but natural user phrasings and synonyms (e.g. 'spec', 'summarize this file') are sparse.

3 / 5

Distinctiveness Conflict Risk

The /spec command niche tied to the Oracle and ChromaDB retrieval is a clear, distinct trigger with only minor overlap risk against general documentation skills.

4 / 5

Total

14

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

tombrewsviews/repository-os-mvp

Path

.tessl/tiles/repository-os/mvp/skills/spec-generator/SKILL.md

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.