solve-challenge

Solves CTF challenges by performing first-pass triage, identifying the dominant category, and routing execution to the right specialized ctf-* skill. Use when the user gives you a challenge bundle, a remote service, a suspicious file, or only a vague challenge description and you must determine where to start. Do not use it when the category is already clear and a specialized skill can be invoked directly; this is the dispatcher and recon entrypoint, not the deepest reference for category-specific techniques.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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 highly actionable, well-sequenced CTF dispatcher body with strong recon commands and a pivot feedback loop. Its main weakness is progressive disclosure: it points to bundle files (notably scripts/install_ctf_tools.sh) that are not present, and inlines catalog content that could be split out.

Suggestions

Ship the referenced scripts/install_ctf_tools.sh (or remove/replace the link) so the "full package lists now live in..." pointer is not a dead-end reference.

Move the long categorization keyword lists and the "Common multi-category patterns" catalog into a references/ file (e.g. categorization.md) and link to it one level deep, keeping only the routing table inline.

Verify the /ctf-misc ctfd-navigation.md reference resolves within the ctf-* skill bundle so Step 0's API navigation pointer is reachable.

Dimension	Reasoning	Score
Conciseness	Mostly lean and command-driven with little basic-concept padding, but the three categorization lists overlap with the Step 3 routing table and the lengthy "Common multi-category patterns" list (e.g., GF(256) Nim, LWE) could be trimmed.	4 / 5
Actionability	Abundant copy-paste-ready commands (file, strings, xxd, binwalk, checksec, nc, curl, grep flag patterns) and a concrete pwntools exploit template cover the common recon cases.	5 / 5
Workflow Clarity	A clearly sequenced Step 0–Step 5 workflow with an explicit pivot/re-examine feedback loop (Step 4) and a concrete flag-validation rule with uniqueness checking before finalizing.	5 / 5
Progressive Disclosure	Section structure and the routing table are well organized, but the body links to scripts/install_ctf_tools.sh (and references ctfd-navigation.md in /ctf-misc) while no scripts/ or references/ bundle exists — a dead-end reference; several inlined keyword/pattern lists could also live in separate files.	3 / 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.

A well-crafted dispatcher description with concrete actions, explicit use/avoid triggers, and clear separation from sibling ctf-* skills. The only minor gap is the absence of file-extension synonyms in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "performing first-pass triage", "identifying the dominant category", and "routing execution to the right specialized ctf-* skill" — which comprehensively describe the dispatcher's behavior.	5 / 5
Completeness	Explicitly answers both what ("Solves CTF challenges by performing first-pass triage...") and when ("Use when the user gives you a challenge bundle..."), plus a negative-trigger clause; uses third person throughout.	5 / 5
Trigger Term Quality	Strong natural triggers ("challenge bundle", "remote service", "suspicious file", "vague challenge description", "determine where to start"), but omits file-extension synonyms a user might name (.pcap, .elf) that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	Carves a clear dispatcher niche and explicitly deconflicts with specialized skills ("Do not use it when the category is already clear and a specialized skill can be invoked directly"), minimizing wrong-skill triggering.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	13 / 16 Passed

Repository: ljagiello/ctf-skills
Path: solve-challenge/SKILL.md
Commit: c332c7b

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.