rev-struct

Reconstruct data structures by analyzing memory access patterns across functions

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/rev-struct/SKILL.md

Quality

Content

80%

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

The body is lean, concrete, and well-sequenced with strong executable examples and a clear output format. Its main gaps are the absence of explicit validation/verification checkpoints in the aggregation step and a monolithic single-file layout that could offload reference material.

Suggestions

Add a validation step after Step 5: check for overlapping or conflicting offsets, sanity-check inferred size against any observed malloc/alloca size, and re-examine conflicting fields before finalizing.

Move the offset-pattern catalog and/or the output-format template into a reference file (e.g. references/patterns.md) referenced one level deep, keeping SKILL.md as the overview.

Add a confidence feedback loop: when confidence is Low, explicitly loop back to traverse additional callers/callees before emitting the struct.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — sections are code patterns, a file-format spec, and a concrete output template with no padding or re-explanation of concepts Claude already knows.	3 / 3
Actionability	Provides concrete offset-access patterns to search for, the decompile/*.c file format, and a copy-ready struct output template with per-field annotations.	3 / 3
Workflow Clarity	The five recovery steps are clearly sequenced, but there are no explicit validation checkpoints (e.g. checking for overlapping offsets, sanity-checking size against malloc) or a fix-and-retry feedback loop.	2 / 3
Progressive Disclosure	A single well-organized file with no bundle references; the output template and pattern catalog are inline and could be split out for a ~200-line skill.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 occupies a distinct niche, but it states only the 'what' without an explicit usage trigger and relies on fairly technical phrasing rather than the natural terms a user would say. Adding a 'Use when...' clause and more colloquial trigger terms would raise it.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when recovering struct definitions from a binary, reverse-engineering data types, or figuring out unknown structures.'

Include natural trigger terms users would actually say ('recover structs', 'figure out this struct', 'reverse engineer data types') alongside the technical phrasing.

List the distinct concrete actions separately (e.g. 'read decompiled functions, collect offset accesses across callers/callees, infer field types and size') to broaden specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('data structures', 'memory access patterns') and a concrete action ('Reconstruct... by analyzing... across functions'), but lists a single composite workflow rather than multiple distinct concrete actions.	2 / 3
Completeness	Clearly states what the skill does but has no explicit 'Use when...' trigger clause, so the 'when' guidance is only implied (capped at 2 per guidelines).	2 / 3
Trigger Term Quality	Contains relevant domain terms ('data structures', 'memory access patterns') a reverser might use, but omits common natural variations like 'struct', 'recover', or 'reverse engineer'.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche — binary reverse-engineering structure recovery — with specific triggers unlikely to collide with other skills.	3 / 3
	Total	9 / 12 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: P4nda0s/reverse-skills
Path: skills/rev-struct/SKILL.md
Commit: a2baa31

Reviewed: about 2 hours 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.