CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

makefile-validator

Comprehensive toolkit for validating, linting, and optimizing Makefiles. Use when working with Makefiles (Makefile, makefile, *.mk files), validating build configurations, checking for best practices, identifying security issues, or debugging Makefile problems. Concrete capabilities include detecting missing .PHONY declarations, validating tab indentation in recipes, checking variable expansion safety, identifying hardcoded credentials, and flagging missing prerequisites or syntax errors.

Quality

91%

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

78%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 actionable skill body: copy-paste commands, documented exit codes, worked scenarios, and clean one-level-deep disclosure into real bundle files. Its main weakness is token efficiency — a verbose Mindset section, a duplicated scenario, and a long sample-output block could be trimmed without losing anything Claude does not already know or cannot infer.

Suggestions

Cut the Mindset paragraph to its two non-obvious points (verify the dependency graph with make -n; report findings as line + risk + fix) and drop the shell-quoting analogy that re-teaches knowledge Claude already has.

Delete Scenario 1 (Pre-commit Validation), which repeats the Quick Start command verbatim, and reduce the Example Output block to the summary/error-count portion that shows how to interpret results.

Trim the Directory Structure section (or fold it into the References list) since every file it lists is already introduced where it is used.

DimensionReasoningScore

Conciseness

Mostly efficient but padded in places: the Mindset paragraph re-teaches shell knowledge Claude already has ("unquoted $(VAR) inside rm, sudo, or curl is exactly as dangerous as unquoted $VAR in bash"), Scenario 1 ("bash scripts/validate_makefile.sh Makefile") duplicates the Quick Start command verbatim, and the ~30-line sample output block and Directory Structure listing add bulk without proportional value. Not a 2 — the padding is localized, and most sections (Anti-Patterns, Exit Codes, Installation) are tight; not a 4 — the redundant scenario, the oversized output block, and the known-concept explanation are more than minor trims.

3 / 5

Actionability

Every workflow is copy-paste executable: "bash scripts/validate_makefile.sh Makefile", "mbake format --diff Makefile", "go install github.com/checkmake/checkmake/cmd/checkmake@latest", with exit codes 0/1/2 mapped to outcomes and sample output showing exactly what to expect. Common cases (pre-commit, formatting, legacy conversion, security audit) are each covered with concrete commands.

5 / 5

Workflow Clarity

Scenario 3 gives a clear numbered validate → fix → format → re-validate sequence and Scenario 2 includes re-validation, and the skill's core loop (run validator, read exit code, act) is itself a checkpoint. Not a 5: no explicit error-recovery branch ("if validation fails, do X") and Scenario 1/4 are single-shot commands without any sequencing guidance; not a 3: checkpoints are present and explicit in the multi-step scenarios.

4 / 5

Progressive Disclosure

Clear overview with well-signaled, one-level-deep references: the body points to references/best-practices.md, references/common-mistakes.md, and references/bake-tool.md with purpose descriptions, plus scripts/validate_makefile.sh and assets/good-bad examples; all cited paths exist in the bundle and the reference files themselves contain only anchors and external links (no nested .md pointers). Anti-Patterns inline is core working knowledge, appropriately kept in the main file.

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.

An exemplary description: it states a concrete, comprehensive capability list in third person and pairs it with an explicit 'Use when' trigger clause covering file-name variants and extensions. The only nitpick is the mild buzzword 'Comprehensive toolkit', which the concrete detail fully earns.

DimensionReasoningScore

Specificity

"Concrete capabilities include detecting missing .PHONY declarations, validating tab indentation in recipes, checking variable expansion safety, identifying hardcoded credentials, and flagging missing prerequisites or syntax errors" lists six specific concrete actions with comprehensive coverage, in third-person voice. The mild buzzword "Comprehensive toolkit" is immediately substantiated by the capability list, so this does not sink to anchor 4's 'minor gaps in coverage'.

5 / 5

Completeness

Both halves are explicit: the 'what' is the capability list ("validating, linting, and optimizing Makefiles" plus the concrete checks) and the 'when' is the explicit "Use when working with Makefiles (Makefile, makefile, *.mk files), validating build configurations..." clause. This mirrors the anchor 5 example's structure exactly.

5 / 5

Trigger Term Quality

"Use when working with Makefiles (Makefile, makefile, *.mk files), validating build configurations, checking for best practices, identifying security issues, or debugging Makefile problems" covers case variants, the file extension pattern *.mk, and natural verb phrases users would say (validate, lint, check best practices, security issues, debug). Matches anchor 5's pattern of comprehensive natural terms including synonyms and extensions.

5 / 5

Distinctiveness Conflict Risk

Makefile validation/linting is a clear niche with distinct triggers (Makefile, *.mk, .PHONY, tab indentation, credentials) and minimal conflict risk; the body further disambiguates against a sibling makefile-generator skill. No anchor-4 'minor overlap' concern rises to the level of a real conflict.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

pantheon-org/tekhne

Path

skills/development/scripting/makefile/validator/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.