skill-factory

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

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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 a tightly engineered execution contract: fully executable commands, explicit sequencing, hard validation gates, and per-step error handling with recovery paths. Its only real costs are duplicated prohibition lists and repeated emphasis phrasing, plus the oversized inline optional gate.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean imperative prose with executable commands, but prohibitions are duplicated between the Step 5 HARD-GATE block and the trailing "Prohibited Actions" section, "MANDATORY / DO NOT" phrasing repeats heavily, and Step 4.5 carries justificatory padding ("it adds ~30 seconds but can save a $2.00 factory run"). Fits anchor 3: mostly efficient with unnecessary material that could be tightened.	3 / 5
Actionability	Every step supplies copy-paste-ready bash with exact paths, flags, find predicates, and fallbacks (e.g. the orchestrate.sh invocation, the -mmin -60 report lookup, the provider detection one-liners), plus a concrete AskUserQuestion script. Fully executable guidance matching anchor 5.	5 / 5
Workflow Clarity	An explicit 8-step contract with mandatory validation gates, per-step error handling, and feedback loops (STOP on missing spec/report; FAIL verdict → refine spec or re-run with --max-retries). This matches anchor 5's clear sequence with validation steps, error-recovery guidance, and a checklist-like contract.	5 / 5
Progressive Disclosure	A single-file skill (~200 lines) with well-organized step sections and no nested references; the optional Step 4.5 adversarial-coverage gate is bulky inline material that would sit better in a reference file. Good structure with a minor organization gap, matching anchor 4 rather than the well-split anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

57%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 cleanly states what the skill does and includes an explicit use clause, with a distinct niche. Its weaknesses are minimal action specificity (a single generic "run") and thin trigger-term coverage, leaving a user to guess the natural phrases that invoke it.

Suggestions

Enumerate 2-3 concrete pipeline actions in the description, e.g. "Parse a spec, generate scenarios, run multi-provider build/holdout evaluation, and produce a scored report".

Add natural trigger phrases to the use clause, e.g. "Use when the user asks to build/generate a project from a spec, hands-off, or autonomously from a specification".

Include the spec format or file terms users would mention (e.g. "NLSpec", "spec file") to sharpen trigger matching.

Dimension	Reasoning	Score
Specificity	"Run a full build-and-ship pipeline from a spec" names the domain, but the only action is a generic "run" — no concrete sub-actions (parsing specs, generating scenarios, holdout evaluation, reporting) appear until the body. Not anchor 3, which requires 1-2 concrete named actions in the description itself.	2 / 5
Completeness	Both "what" ("Run a full build-and-ship pipeline from a spec") and "when" ("use for hands-off project generation") are explicitly present, but the trigger clause is generic rather than citing concrete phrases a user would say. Falls between anchor 4 and the fully explicit anchor 5.	4 / 5
Trigger Term Quality	Relevant keywords like "spec", "build-and-ship", "hands-off", and "project generation" are present, but common user variations ("build from a spec", "generate a project", "scaffold", "autonomous build") and any file-type markers are missing. Anchor 4 requires good coverage with only a few natural terms missing.	3 / 5
Distinctiveness Conflict Risk	"Build-and-ship pipeline from a spec" and "hands-off project generation" carve a reasonably distinct niche with clear triggers; only minor overlap risk with general code-generation or build skills, matching anchor 4.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-factory/SKILL.md
Commit: 0093dab

Reviewed: 5 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.