CtrlK
BlogDocsLog inGet started
Tessl Logo

makefile-generator

Generate GNU Make build systems that define build targets, configure dependencies, set up phony targets, and implement parallel builds. Use when creating make/Makefile/.mk files, implementing compile rules, or building production-ready build automation for C/C++, Go, Python, and Java projects.

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A strong, highly executable skill body with an exemplary staged workflow and validation loop, and a well-organized one-level-deep reference bundle. Its main weakness is token efficiency: the Anti-Patterns section duplicates the Mindset paragraph, and a couple of code examples have small completeness gaps (undefined $(TARGET), stubbed test target).

Suggestions

Deduplicate the Mindset and Anti-Patterns sections — five of the anti-patterns restate points already made in Mindset (.PHONY, subshells/.ONESHELL, env vars, implicit rules); state each once and reference it, cutting substantial tokens.

Define `TARGET` in the Standard Variables block (e.g., `TARGET := $(BUILDDIR)/$(PROJECT)`) so the C/C++ and Go rule snippets are copy-paste runnable, and give the `test:` target a concrete example command instead of '# Add test commands'.

Collapse Stage 2's duplicated lookup guidance (the requirement→doc table appears in both the Read-first step and the workflow example) into a single table.

DimensionReasoningScore

Conciseness

The body is dense and actionable rather than padded, but the Mindset paragraph (.PHONY semantics, per-line subshells, env variables, implicit rules) is restated nearly point-for-point across the five Anti-Patterns, and Stage 2's lookup table appears twice — content a competent model already holds, duplicated. This fits 'mostly efficient but could be tightened' better than the 2 anchor, since there is little conceptual fluff beyond the duplication.

3 / 5

Actionability

Concrete, executable Makefile snippets and commands throughout (modern/traditional headers, language rules, `bash scripts/generate_makefile_template.sh go myservice`, `mbake format`), but `$(TARGET)` is never defined in the Standard Variables block and the `test:` recipe is an empty '# Add test commands' stub — minor gaps that keep it below copy-paste-ready.

4 / 5

Workflow Clarity

The four-stage workflow is clearly sequenced with an explicit validation loop ("Invoke devops-skills:makefile-validator", "Re-validate until checks pass"), error-recovery decision guides (Formatting Decision Guide, false-positive table), and a final Validation Checklist — matching the top anchor's validate→fix→retry pattern.

5 / 5

Progressive Disclosure

The body is an overview with one-level-deep, well-signaled references: every `references/*.md` file named in the body exists, each gets a one-line purpose in the Documentation section, Stage 2 maps requirements to specific files and verified pattern numbers (Pattern 5/7/8), and the scripts are documented with usage examples — easy navigation with no nesting.

5 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities in third person, includes an explicit 'Use when' clause with natural trigger terms, synonyms, and file extensions, and occupies a distinct niche. Both the 'what' and 'when' questions are answered with concrete, non-vague language.

DimensionReasoningScore

Specificity

Lists four concrete, distinct capabilities — "define build targets, configure dependencies, set up phony targets, and implement parallel builds" — within the named GNU Make domain, matching the comprehensive-coverage anchor; unlike the 4 anchor there are no meaningful gaps in the action list.

5 / 5

Completeness

Explicitly answers both what ("Generate GNU Make build systems that define build targets...") and when ("Use when creating make/Makefile/.mk files, implementing compile rules, or building production-ready build automation...") with concrete trigger phrases, exactly matching the top anchor.

5 / 5

Trigger Term Quality

Covers "make/Makefile/.mk files", "compile rules", and "build automation" — natural user phrasings plus synonyms and a file extension — matching the comprehensive-coverage anchor rather than the 4 anchor's 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

A clear niche (GNU Make build system generation) with Make-specific triggers and named languages; it would not plausibly fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pantheon-org/tekhne
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.