CtrlK
BlogDocsLog inGet started
Tessl Logo

competition-reverse-pwn

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for reverse engineering, malware, DFIR, firmware, pwnable, and native exploit challenges. Use when the user asks to reverse a binary, unpack a sample, inspect a memory dump or PCAP, recover malware behavior, debug a crash, or build or verify an exploit chain under sandbox assumptions. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

68

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-structured, lean methodology playbook that appropriately pushes detail to a one-level-deep reference and gives specific, actionable triage and evidence guidance. The main gaps are the lack of explicit error-recovery feedback loops and concrete tool commands.

Suggestions

Add an explicit validate→fix→retry feedback loop in the Workflow section (e.g., 'If the primitive does not reproduce from a clean baseline, re-check mitigations/loader assumptions before doubting the primitive') to lift workflow_clarity toward 5.

Name the concrete triage commands once in the Quick Start or reference (e.g., `file`, `readelf -a`, `strings`, entropy check) to make the guidance directly executable rather than implied.

De-duplicate the triage item list between the Quick Start step 2 and the Workflow triage section to tighten conciseness.

DimensionReasoningScore

Conciseness

Lean, action-oriented bullets that assume Claude's competence and avoid explaining known concepts; minor redundancy between the Quick Start triage list and the Workflow section keeps it off the lean-and-efficient anchor.

4 / 5

Actionability

Concrete, specific guidance on what to triage, record, and preserve (e.g., "Record the primitive, controllable bytes, leak source, target object, and final artifact separately") is actionable for an instruction-only skill, though no explicit tool commands are given.

4 / 5

Workflow Clarity

A clear 5-step Quick Start with preservation (step 1) and reproduce-from-clean-baseline (step 5) as checkpoints; explicit validate→fix→retry feedback loops are absent, appearing only implicitly via the pitfalls section.

4 / 5

Progressive Disclosure

Well-organized sections plus one clearly-signaled one-level-deep reference ("Load `references/reverse-pwn.md` for triage order, exploit evidence expectations, and common failure modes") that exists as a real file, with content appropriately split between overview and playbook.

5 / 5

Total

17

/

20

Passed

Description

88%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 strong description that clearly states the skill's purpose and trigger conditions with concrete, user-natural language and an explicit downstream-gating clause. Its only weakness is breadth-driven overlap with sibling CTF skills and incomplete synonym/extension coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the domain — "reverse a binary, unpack a sample, inspect a memory dump or PCAP, recover malware behavior, debug a crash, or build or verify an exploit chain" — matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both what ("CTF-sandbox workflow for reverse engineering, malware, DFIR, firmware, pwnable, and native exploit challenges") and when ("Use when the user asks to reverse a binary…") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage (binary, memory dump, PCAP, crash, exploit chain) that users would say, but missing file extensions and some synonyms (decompile, disassemble), so not the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The gating clause ("Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here") makes wrong-skill triggering unlikely, but the broad domain overlaps with sibling specializations, so minor overlap risk remains.

4 / 5

Total

18

/

20

Passed

Validation

100%

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
zhaoxuya520/reverse-skill
Reviewed

Table of Contents

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.