competition-relay-coercion-chain

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for forced-auth coercion, relay chains, target selection, NTLM or related acceptance paths, and coercion-to-privilege transitions. Use when the user asks to trace a coercion primitive, follow a relay path, analyze forced authentication, determine which service accepts relayed auth, or connect a coercion step to resulting privilege, enrollment, or code execution. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Quality

93%

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

87%Weight 40%Scale 1-3

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, specific, and well-structured with a clearly signaled one-level reference, but the multi-step relay chain workflow lacks an explicit verification checkpoint that the decisive acceptance step was actually proven rather than assumed.

Suggestions

Add an explicit verification checkpoint in the workflow — e.g., after 'Reduce To The Decisive Relay Chain', require confirmation that 'relay acceptance' (not just capture/replay) was demonstrated with an acceptance response before declaring the chain complete.

Make the 'reproduce the smallest coercion-to-acceptance path' step a hard validation gate (reproduce -> confirm acceptance response -> only then record as proven) rather than a passive Quick Start item.

Cross-link the 'Common Pitfalls' (stopping at forced auth, proving acceptance without showing capability) from the body into the workflow steps so the failure modes are enforced as checks, not just listed.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no concept-explanation padding (no 'what is NTLM' or library tutorials); every line gives actionable direction, assuming Claude's competence.	3 / 3
Actionability	Concrete, specific guidance throughout — 'Record source host, coerced principal, transport', 'Distinguish capture-only, replay-only, and actual relay acceptance', and an explicit minimal chain template 'coercion trigger -> relayed auth -> accepted service -> resulting privilege'. As an instruction-only skill, the absence of executable code is not penalized.	3 / 3
Workflow Clarity	The three-stage workflow and numbered Quick Start are clearly sequenced, but there is no explicit verification checkpoint confirming that relay acceptance (vs. mere capture) has actually been demonstrated — the 'prove the decisive edge' step is only implied rather than enforced as a validation gate.	2 / 3
Progressive Disclosure	A concise overview body with one clearly-signaled, one-level-deep reference ('Load `references/relay-coercion-chain.md`') that exists and contains the detailed checklist, matching the well-organized overview-plus-reference anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, trigger-rich, complete, and clearly scoped as a downstream specialization with an explicit activation gate. It names concrete actions and natural user phrases rather than relying on vague jargon.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'trace a coercion primitive, follow a relay path, analyze forced authentication, determine which service accepts relayed auth, or connect a coercion step to resulting privilege, enrollment, or code execution' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('CTF-sandbox workflow for forced-auth coercion, relay chains...') and when ('Use when the user asks to trace a coercion primitive, follow a relay path...'), satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'forced-auth coercion, relay chains, NTLM... acceptance paths, trace a relay path, analyze forced authentication, determine which service accepts relayed auth' — with good breadth rather than only jargon.	3 / 3
Distinctiveness Conflict Risk	A clear niche with an explicit routing gate — 'Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here' — making it unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 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: zhaoxuya520/reverse-skill
Path: CTF-Sandbox-Orchestrator/competition-relay-coercion-chain/SKILL.md
Commit: 6aa1362

Reviewed: 7 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.