ctf-reverse

Provides reverse engineering techniques for CTF challenges. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, game clients, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.

Quality

86%

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

Quality

Content

80%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 SKILL.md body is a well-structured, actionable quick reference with excellent progressive disclosure across many supporting files. Its weakest point is workflow clarity: the problem-solving sequence lacks explicit validation checkpoints and a retry loop.

Suggestions

Add an explicit validation/retry step to the Problem-Solving Workflow (e.g. "If the assumption fails, compare decompiler outputs and re-run") to turn the linear list into a validate→fix→retry loop.

Mark the numbered workflow steps that are checkpoints (e.g. "Verify the flag candidate before submitting") so error recovery is explicit.

De-duplicate the reference index: the "Additional Resources" list and the "Deep-Dive Notes" bullets overlap; consider folding Deep-Dive Notes into the index to trim tokens.

Dimension	Reasoning	Score
Conciseness	The body is a lean reference of commands and snippets with almost no conceptual padding, but the "Additional Resources" index and the "Deep-Dive Notes" section partly restate the same reference list, adding minor redundancy.	4 / 5
Actionability	It provides copy-paste-ready, executable commands covering the common cases — `strings ... \| grep`, `ltrace`, `strace`, `r2 -d`, `aaa`/`afl`/`pdf @ main`, `analyzeHeadless`, and a concrete GDB PIE workflow — with concrete offsets and flags.	5 / 5
Workflow Clarity	The "Problem-Solving Workflow" is a numbered sequence (strings → ltrace/strace → Frida → angr → Qiling → map control flow → automate → validate), but checkpoints are implicit and there is no validate→fix→retry feedback loop; per the rubric, missing validation/checkpoints caps this at 3.	3 / 5
Progressive Disclosure	The body is an overview that points to 16 clearly-signaled, one-level-deep reference files (tools.md, anti-analysis.md, patterns-ctf.md, etc.), each with a markdown link and a one-line scope summary, making navigation easy with no nested references.	5 / 5
	Total	17 / 20 Passed

Description

92%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.

This is a high-quality activation description: it states concrete capabilities, gives explicit "Use when" triggers, and disambiguates from sibling CTF skills. The only minor gap is a few missing natural synonyms/extensions users might say.

Suggestions

Consider adding one or two user-common synonyms like "crackme" or "decompile/disassemble" to broaden natural trigger coverage.

Optionally mention common file extensions (e.g. ELF, .exe, .apk) so the description matches the way users often phrase requests.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete targets — "binaries, APKs, WASM, firmware, custom VMs, bytecode, game clients, malware-like loaders, and anti-debug or anti-analysis logic" — giving comprehensive coverage of the reverse-engineering domain.	5 / 5
Completeness	It explicitly answers both what ("Provides reverse engineering techniques for CTF challenges") and when ("Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works...") with concrete trigger phrases and exclusion guidance.	5 / 5
Trigger Term Quality	Strong natural keyword coverage ("reverse engineering", "CTF", "obfuscated, packed, or virtualized", "binaries", "APKs", "WASM", "firmware"), but it omits a few common variations users say (e.g. "crackme", "RE", "ELF/.exe", "decompile") so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche and adds explicit pivot-away guidance ("use pwn instead", switch to forensics/web/crypto/misc) that minimizes activation for the wrong skill.	5 / 5
	Total	19 / 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
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 19 missing	Warning

	Total	14 / 16 Passed

Repository: ljagiello/ctf-skills
Path: ctf-reverse/SKILL.md
Commit: 36c72e5

Reviewed: 4 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.