Name: running-make-to-build
Rating: 56.00000000000001 (1 reviews)
Author: stellar

Blog Docs Log in Get started

running-make-to-build

how to run make correctly to get a good build, and otherwise understand the build system

Quality

62%

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/running-make-to-build/SKILL.md

Quality

Content

76%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 highly actionable and token-efficient, full of concrete commands and project-specific detail Claude would not know. Its main gap is the absence of an explicit build-verification checkpoint in the workflow, which caps workflow clarity.

Suggestions

Add an explicit verification step after building, e.g. 'Confirm the build succeeded: check that src/stellar-core exists and that make exited 0.'

Frame 'make check' or a smoke command as the validation checkpoint that follows a build, turning the recovery loop into a validate-then-proceed flow.

Tighten minor over-explanation such as 'The integration is quite subtle. You should always let src/Makefile.am handle invoking cargo.' to a direct imperative.

Dimension	Reasoning	Score
Conciseness	The body is lean and project-specific (stellar-core build, make-mks, xdrpp, cargo integration) — material Claude would not already know — with only minor over-explanation such as 'The integration is quite subtle.' that could be trimmed.	4 / 5
Actionability	It provides concrete, executable commands throughout — 'make -j $(nproc)', '2>&1 \| tail -N', 'git add <somefile> && ./make-mks', 'make clean', and a concrete target list (all, check, clean, format) — covering the common build cases with appropriately parameterized placeholders.	5 / 5
Workflow Clarity	A rough sequence and a recovery loop exist ('If anything goes wrong ... run make clean and trying again'), but building is a batch/destructive-context operation with no explicit verify-the-build-succeeded checkpoint, so workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	The skill is a single self-contained file with well-organized sections (Overview, Targets, Rust build, Generated files, Editing the makefiles) and no nested references; it sits just over the ~50-line simple-skill threshold, so it does not reach a clean 5.	4 / 5
	Total	16 / 20 Passed

Description

48%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 domain-specific and reasonably distinct, but it states generic goals rather than concrete capabilities and omits any 'when to use' trigger guidance, which caps completeness. It reads as a terse topic label more than an actionable, trigger-rich description.

Suggestions

Add concrete actions instead of goals, e.g. 'Run make with parallelism from the top level, add new files via ./make-mks, and rebuild after clean.'

Append an explicit trigger clause, e.g. 'Use when building or modifying the stellar-core make build, running targets, or adding source files to the build.'

Include natural synonyms users might say such as 'compile', 'Makefile', and 'rebuild' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('run make', 'build', 'build system') but the stated actions are minimal and generic goals rather than discrete capabilities — 'get a good build' and 'understand the build system' do not enumerate concrete actions.	2 / 5
Completeness	It gives a clear 'what' (run make to build, understand the build system) but provides no 'Use when...' or equivalent trigger guidance, so completeness is capped at 3 per the rubric.	3 / 5
Trigger Term Quality	It includes natural terms a user would say ('make', 'build', 'build system') but lacks common synonyms and variations such as 'compile', 'Makefile', or 'build the project'.	3 / 5
Distinctiveness Conflict Risk	The make-build niche is mostly distinct with specific triggers, with only minor overlap risk against generic build or deploy skills; it does not reach 5 because 'build system' is still somewhat broad.	4 / 5
	Total	12 / 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: stellar/stellar-core
Path: .claude/skills/running-make-to-build/SKILL.md
Commit: 457f20b

Reviewed: 2 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.