hopper-debugger

Hopper debugging: macOS/iOS binaries, ObjC/Swift symbols, dyld, LLDB.

Quality

81%

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

Quality

Content

88%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.

An excellent, highly actionable skill body with executable commands, a clear validated workflow, and a feedback loop for regression conclusions. Its main weakness is embedded time-sensitive version/license details that bloat conciseness and a dense single-file structure with minor split-out opportunities.

Suggestions

Move time-sensitive details (license order id and 2027-05-17 expiry, the 'as of 2026-08' snapshot caveat, macOS 26.6/27.0 version notes) into a clearly labeled 'Version-sensitive' or 'Deprecated' section, or a reference file, so they don't bloat the core path.

Consider extracting the Licensing and Apple-frameworks provenance detail into a reference file (e.g. references/licensing.md) to let the core SKILL.md stay a lean overview.

Keep the gotcha-driven structure ('the one that bites', 'do not misdiagnose') — it is the strongest part of the skill and earns its tokens.

Dimension	Reasoning	Score
Conciseness	Lean and opinionated throughout, assuming Claude's competence with no padding, but embeds time-sensitive version/license details (2027-05-17, 'as of 2026-08', macOS 26.6/27.0) inline rather than in a deprecated section, which the guidelines penalize.	4 / 5
Actionability	Copy-paste-ready executable commands cover setup, verification, the critical --args gotcha, raw stdio JSON-RPC fallback, licensing lookup, opening/polling, dialog dismissal, and daemon recovery across common cases.	5 / 5
Workflow Clarity	The numbered Query workflow has an explicit validation checkpoint ('Validate the hypothesis with LLDB/logging/repro before editing app code') and the runtime-evidence section adds a control-run feedback loop before concluding regression.	5 / 5
Progressive Disclosure	Well-sectioned single-file SKILL.md with clear headers and no nested reference chains, but it is a fairly dense monolith where licensing specifics and snapshot provenance could plausibly be split into reference files.	4 / 5
	Total	18 / 20 Passed

Description

75%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.

A tight, domain-specific description that clearly conveys what the skill does and is highly distinctive, but it omits an explicit 'when to use' trigger clause, capping completeness. Adding a 'Use when...' sentence would raise the score.

Suggestions

Add an explicit trigger clause, e.g. 'Use when debugging macOS/iOS binaries in Hopper, resolving ObjC/Swift symbols, walking dyld, or driving Hopper from LLDB.'

Include natural synonyms/variations (e.g. 'disassembly', 'reverse engineering', '.hop files') to broaden trigger-term coverage.

Keep the current third-person, concrete-target style; it reads as the natural phrases a user would say.

Dimension	Reasoning	Score
Specificity	Names the Hopper-debugging domain and lists multiple concrete targets (macOS/iOS binaries, ObjC/Swift symbols, dyld, LLDB) with comprehensive coverage rather than vague actions.	5 / 5
Completeness	The 'what' is clear (Hopper debugging of Apple binaries via symbols/dyld/LLDB) but there is no 'Use when...' trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural domain terms a user would say (Hopper, ObjC/Swift symbols, dyld, LLDB) but lacks synonyms, file extensions, and is a terse comma list rather than comprehensive phrasing.	4 / 5
Distinctiveness Conflict Risk	A sharply defined niche (Hopper + Apple platforms + named low-level toolchain) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 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: steipete/agent-scripts
Path: skills/hopper-debugger/SKILL.md
Commit: 15bcfe3

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.