skill-factory

Run a full build-and-ship pipeline from a spec — use for hands-off project generation

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-factory/SKILL.md

Quality

Content

70%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 a strong, executable orchestration workflow with excellent sequencing and validation, but it is verbose with repeated prohibition lists and inlines content that would benefit from being split into reference files.

Suggestions

De-duplicate the prohibition list — state it once in the "Prohibited Actions" section and reference it from Step 5 rather than repeating.

Move the long Step 4.5 QA adversary prompt and the ASCII banner into a reference file (e.g., references/scenario-gate.md) and link to it.

Tighten "MANDATORY" / "CANNOT SKIP" emphasis, which is repeated across nearly every step and adds tokens without new information.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but carries notable redundancy — prohibition lists are repeated across Step 5's HARD-GATE, the "Prohibited Actions" section, and "Error Handling", and Step 4.5 inlines a long QA prompt that could be referenced.	3 / 5
Actionability	Concrete, executable bash commands and flags appear throughout (orchestrate.sh factory --spec, find-based report/score discovery, state-manager.sh calls), with only minor gaps from placeholder substitution like <spec_path>.	4 / 5
Workflow Clarity	An explicit 8-step sequence with multiple validation gates (Steps 3, 6, 7), per-step error-handling feedback loops, and a hard gate prohibiting substitution or skipping.	5 / 5
Progressive Disclosure	Headers give some structure, but no bundle reference files exist and the bulk (banner, full QA adversary prompt) is inlined; the one external pointer to codex-host-adapter.md is not clearly signaled as a reference split.	3 / 5
	Total	15 / 20 Passed

Description

62%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 states what the skill does and when to use it, with a reasonably distinct niche. It is held back by limited action specificity and missing common trigger synonyms that would broaden natural invocation.

Suggestions

Add 1-2 more concrete actions to the description (e.g., "generate, test, and ship a project") to raise specificity.

Include natural trigger synonyms users would say, such as "scaffold", "bootstrap", or "generate a project from a spec".

Make the "when" clause more explicit with concrete trigger phrases (e.g., "Use when the user provides an NLSpec and wants hands-off generation").

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ("build-and-ship pipeline from a spec", "hands-off project generation") but only offers 1-2 actions rather than a comprehensive list.	3 / 5
Completeness	Both the "what" (build-and-ship pipeline from a spec) and "when" ("use for hands-off project generation") are present, though the trigger phrasing could be more concrete.	4 / 5
Trigger Term Quality	Relevant keywords like "spec", "build-and-ship pipeline", and "project generation" appear, but common natural synonyms (scaffold, bootstrap, generate project) are missing.	3 / 5
Distinctiveness Conflict Risk	The build-and-ship-from-spec niche is mostly distinct with only minor overlap risk against general scaffolding skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: nyldn/claude-octopus
Path: skills/skill-factory/SKILL.md
Commit: 242e51d

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.