graphics-api-hooking

Analyze Direct3D/DXGI, OpenGL, and Vulkan rendering, presentation, composition, and capture evidence. Use to distinguish API samples, PresentMon event metrics, Tracy instrumentation, compatibility translation, frame images, and validation diagnostics; review swap chains, overlays, resource lifetime, and synchronization. Select repository tools by the observation required and report API/backend, driver, compositor, tool version, measurement coverage, and benign alternatives.

Quality

73%

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/graphics-api/SKILL.md

Quality

Content

67%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 body delivers strong executable guidance and a well-sequenced source-selection workflow with on-demand references. Its main weakness is conciseness: significant inline prose and reference-style material bloat the main file that could live in the referenced guide.

Suggestions

Move the bulk of the per-API hook code and overlay technique catalogs into references/ and keep SKILL.md as a concise overview with one representative example, to improve token efficiency and progressive disclosure.

Replace non-executable placeholders in code (e.g., 'return invalid', '// Render overlay here') with concrete or clearly-justified snippets so examples are fully copy-paste ready.

Make the source-selection workflow an explicit numbered checklist with a verify-and-fallback step (verify upstream revision; if missing, fall back to README original URL) to add a clear feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is large and includes padded explanatory prose and concept walkthroughs (e.g., the World-to-Screen derivation, OBS capture mode explanations) that assume Claude needs hand-holding; it is mostly efficient but could be tightened substantially.	3 / 5
Actionability	Provides concrete, copy-paste-ready code for vtable hooking, ImGui setup, WndProc, and WorldToScreen, plus a clear data-source lookup recipe; minor gaps include placeholders like 'return invalid' and commented '// Render overlay here'.	4 / 5
Workflow Clarity	The 'Data Source' and 'Choose and Verify the Source' sections sequence a clear path with verification of upstream revisions and current-source checks, though not framed as an explicit validate->fix->retry feedback loop.	4 / 5
Progressive Disclosure	References are mostly one level deep and clearly signaled (the real references/repository-resources.md, plus shared navigation/overview and wiki links), with detailed resource selection pushed to the reference file; however a lot of API reference material remains inlined in the main body.	4 / 5
	Total	15 / 20 Passed

Description

80%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 concrete, third-person, and distinct, with a clear what-and-when structure anchored by a 'Use to' trigger clause. It is strong but slightly verbose and the trigger conditions are framed more as capabilities than crisp user-facing scenarios.

Suggestions

Tighten the 'when' clause to concrete user phrasing (e.g., 'Use when investigating overlay or capture evidence, frame pacing, or hook artifacts across Direct3D/OpenGL/Vulkan').

Trim the trailing reporting checklist ('report API/backend, driver, compositor, tool version, measurement coverage, and benign alternatives') which inflates the description without adding trigger value.

Add common synonyms or surface terms users naturally say (e.g., 'frame capture', 'screen capture', 'ESP/aimbot overlays') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Analyze...rendering, presentation, composition, and capture evidence', 'distinguish API samples, PresentMon event metrics, Tracy instrumentation', 'review swap chains, overlays, resource lifetime') with specific objects, though reporting of benign alternatives is broad.	4 / 5
Completeness	Clearly states what ('Analyze...rendering, presentation, composition, and capture evidence') and provides an explicit 'Use to...' trigger clause, but the 'when' could be more sharply delimited to concrete user scenarios.	4 / 5
Trigger Term Quality	Strong coverage of natural technical terms users would say ('Direct3D', 'DXGI', 'Vulkan', 'swap chains', 'overlays', 'PresentMon', 'Tracy'), though it leans on jargon and omits some common synonyms.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (graphics API hooking and rendering evidence) with distinct API/backend/compositor vocabulary, making overlap with unrelated skills minimal.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (556 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 8 suspicious	Warning

	Total	14 / 16 Passed

Repository: gmh5225/awesome-game-security
Path: .claude/skills/graphics-api/SKILL.md
Commit: c7e4d3f

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.