skill-factory

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

Quality

63%

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

63%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 tightly sequenced, actionable factory pipeline with strong validation gates and per-step error handling. Its weaknesses are verbosity (decorative banners, repeated prohibition blocks, a long optional Step 4.5) and the absence of any progressive disclosure split despite the length.

Suggestions

Trim redundant emphasis and decoration: collapse the repeated Prohibited Actions / HARD-GATE blocks into one and shorten the decorative octopus banner to save tokens.

Split the lengthy optional Step 4.5 (adversarial scenario coverage gate) into a reference file (e.g. references/coverage-gate.md) and keep a one-line pointer plus the skip condition inline, improving progressive disclosure.

Replace inline placeholders (<spec_path>, <verdict>, <score>/<target>) with a short note showing how they are interpolated, so the examples are copy-paste executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-driven, but recurring emphasis ("MANDATORY", repeated HARD-GATE/Prohibited blocks, a decorative octopus banner, and the verbose Step 4.5 prose) adds padding that could be tightened without losing meaning.	3 / 5
Actionability	Concrete, executable bash is supplied throughout (orchestrate.sh factory, state-manager.sh, find report) with only minor gaps such as placeholders like <spec_path> and <verdict> the user must fill.	4 / 5
Workflow Clarity	An explicit 8-step sequence with validation gates (Steps 3 and 6) and per-step error handling plus feedback loops is present and consistent; because destructive/batch operations DO have validation, the skill is not capped at 3, but optional/RECOMMENDED gates keep it just below a fully locked-down 5.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the entire ~185-line flow is inlined in SKILL.md with no one-level-deep references; sections are organized, but content like the Step 4.5 coverage gate is verbose material that could be split out.	3 / 5
	Total	14 / 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 is concise, third-person, and conveys both what the skill does and a use-case trigger, but it leans on jargon ("spec") and offers only one minimally-specified action. Expanding the trigger terms and adding concrete action verbs would raise specificity and trigger quality.

Suggestions

Replace jargon like "spec"/"from a spec" with natural user phrasing such as "Use when the user wants hands-off project generation from a written specification or NLSpec file."

List concrete actions in the description (e.g., "parses a spec, generates scenarios, runs multi-provider build + holdout evaluation, and reports a satisfaction verdict") to improve specificity.

Add natural trigger synonyms (e.g., "spec", "specification", "NLSpec", "autonomous build", "generate project") so users' varied phrasing reliably activates the skill.

Dimension	Reasoning	Score
Specificity	Names the domain ("build-and-ship pipeline from a spec") and one concrete action ("hands-off project generation"), but the action phrasing is minimal and fairly generic rather than listing multiple concrete operations.	3 / 5
Completeness	Provides a clear "what" (run a full build-and-ship pipeline from a spec) and an explicit "use for... hands-off project generation" trigger, though the "when" could be more specific with concrete trigger phrasing.	4 / 5
Trigger Term Quality	Contains relevant keywords ("build-and-ship pipeline", "from a spec", "hands-off project generation") but relies on jargon-heavy terms ("spec") and lacks common synonyms or file extensions.	3 / 5
Distinctiveness Conflict Risk	"build-and-ship pipeline from a spec" carves a clear autonomous-build niche with minimal overlap risk against generic skills, though closely related build/orchestration skills could overlap.	4 / 5
	Total	14 / 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: 1bee725

Reviewed: ~11 hours 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.