verify

Verify harness changes end-to-end without docker — drive the real pinned CLI against a header-capturing stub server with the exact env resolve_auth_env() produces.

Quality

70%

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/verify/SKILL.md

Quality

Content

86%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 lean, well-structured, and largely executable with a clear sequenced recipe and validation expectations. Its main gap is the env-build step, which is partly pseudocode.

Suggestions

Replace the 'python3 -c ...' ellipsis with a concrete one-liner (or a small complete snippet) that dumps the resolved env to an export-lines file via shlex.quote.

Pin the exact stub-server implementation (a minimal complete script) instead of describing it prose-only, so step 2 is copy-paste ready alongside the rest.

Make the <port> and <cli> placeholders explicit variables set once at the top of the recipe so each downstream command is literal.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence; every line earns its place with no padding or explanation of basic concepts, e.g. the recipe steps and gotchas are terse and purposeful.	5 / 5
Actionability	It gives mostly executable commands (npm install, the timeout run invocation, unset/source steps), but the env-dump step uses a '...' ellipsis and a <port>/<cli> placeholder, leaving minor gaps for copy-paste.	4 / 5
Workflow Clarity	The numbered recipe sequences steps clearly with an expected-result checkpoint ('exit=1 is expected') and a verification step to read the captured JSONL, with only minor validation gaps.	4 / 5
Progressive Disclosure	This is a short single-purpose skill (under 50 lines) with no bundle files and well-organized sections (Recipe, Gotchas), so the simple-skill exception lets progressive disclosure score 5.	5 / 5
	Total	18 / 20 Passed

Description

55%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 specific and clearly distinct but leans heavily on internal jargon and omits any explicit 'when to use' guidance. It would benefit from natural-language trigger phrasing.

Suggestions

Add an explicit 'Use when...' clause stating when this skill applies (e.g., 'Use when verifying harness changes on a host without docker installed').

Soften jargon with at least one natural trigger phrase a user might say, such as 'verifying harness changes' or 'testing CLI auth without docker'.

Spell out the outcome once at a higher level (e.g., 'confirm outbound API auth headers match production') before the mechanism.

Dimension	Reasoning	Score
Specificity	Names concrete actions such as 'drive the real pinned CLI', 'header-capturing stub server', and 'the exact env resolve_auth_env() produces', listing several specific actions with only minor coverage gaps.	4 / 5
Completeness	It clearly states what the skill does but has no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	The description is dominated by internal jargon ('harness changes', 'resolve_auth_env()', 'docker') and lacks the natural phrases a user would actually say when needing this skill.	2 / 5
Distinctiveness Conflict Risk	It targets a narrow niche (docker-less harness verification with a stub server and resolved auth env), with triggers distinct enough to minimize overlap with other skills.	5 / 5
	Total	14 / 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: anthropics/defending-code-reference-harness
Path: .claude/skills/verify/SKILL.md
Commit: d3bea6b

Reviewed: 5 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.