scripts-and-automation

caddy-security repository automation, Makefile target selection, local build/test/report/coverage commands, local go-authcrunch go.mod replacement shim workflow, asset and documentation update scripts, release/version workflows, generated artifact handling, and guardrails for dependency, devbuild, cleanup, and release actions. Use when choosing, running, documenting, or updating repository scripts and Make targets; troubleshooting CI/build/test automation; coordinating caddy-security development with local go-authcrunch changes; refreshing Caddyfile/config fixtures; deciding whether generated outputs belong in a change; or preparing releases for this Go/Caddy module.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-sequenced with strong guardrails for risky release operations, but it is a monolithic single file with embedded time-sensitive version numbers. Splitting reference-heavy sections into bundle files and isolating version pins would lift the weaker dimensions.

Suggestions

Move hard-coded version numbers (Go 1.25.0, Caddy v2.11.2, Go 1.25.x) into a dedicated, clearly labeled section (or a referenced file) so time-sensitive details don't penalize conciseness.

Extract the detailed release-target list and CI Notes into referenced bundle files (e.g. RELEASE.md, CI.md) and signal them from the overview, adding one-level-deep progressive disclosure.

Add an explicit validate->fix->retry feedback loop for the go-authcrunch replacement workflow (e.g. 'run make test after sync; if it fails, re-check the replace directive before proceeding') to make the checkpoint explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but it hard-codes time-sensitive version numbers ('Go 1.25.0', 'Caddy v2.11.2', 'Go 1.25.x') outside any deprecated/old-patterns section, which the rubric penalizes.	2 / 3
Actionability	Provides copy-paste-ready commands and exact paths — 'go test ./... ', 'make build', 'go mod edit -replace github.com/greenpau/go-authcrunch@<version>=../go-authcrunch', 'bin/authcrunch', '.coverage/test_output.jsonl' — fully executable guidance.	3 / 3
Workflow Clarity	Multi-step flows are clearly sequenced with validation checkpoints and guardrails: release-git-check requires branch 'main' and a clean worktree, 'make test' fails if any JSON action failed, and the go-authcrunch flow is change-then-sync-then-test.	3 / 3
Progressive Disclosure	Sections are well-organized, but the ~180-line body is monolithic with no bundle files or one-level-deep references; content that could be split (full release-target list, CI notes) is inline, so it does not reach the 'clear overview with well-signaled references' anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, trigger-rich, and clearly distinguishes a narrow repository-automation niche while covering both what the skill does and when to invoke it. It is dense but every clause names a concrete capability or trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'Makefile target selection', 'local build/test/report/coverage commands', 'go.mod replacement shim workflow', 'asset and documentation update scripts', and 'release/version workflows', matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (a long list of automation capabilities) and 'when' via a clear 'Use when choosing, running, documenting, or updating repository scripts and Make targets; ...' clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Includes natural developer-facing terms a user would say — 'repository scripts and Make targets', 'CI/build/test automation', 'Caddyfile/config fixtures', and 'preparing releases' — giving good coverage of natural trigger language.	3 / 3
Distinctiveness Conflict Risk	Targets a clearly bounded niche — the caddy-security Go/Caddy module and its local go-authcrunch dependency — with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 5 missing, 4 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: greenpau/caddy-security
Path: .codex/skills/scripts-and-automation/SKILL.md
Commit: b96087f

Reviewed: 23 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.