CtrlK
BlogDocsLog inGet started
Tessl Logo

competition-browser-persistence

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for browser cookies, localStorage, sessionStorage, IndexedDB, Cache Storage, service workers, offline caches, and client-side session persistence. Use when the user asks to inspect browser state, replay cached auth or session behavior, explain why a page behaves differently after load, or trace how stored client state changes requests, rendering, or access. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

80

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 a well-structured, lean investigative workflow that assumes competence, gives concrete surfaces and methods, sequences its steps with verification checkpoints, and cleanly offloads detail to a single real reference. It avoids concept-padding and verbosity while remaining actionable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what cookies, IndexedDB, or service workers are, and every line earns its place ("Record origin, scope, domain, path, expiry, and key names before mutating state"). The only mild redundancy (restating the orchestrator gate) is load-bearing routing context, so it stays at the efficient anchor rather than the padded 2.

3 / 3

Actionability

For an instruction-only investigation skill the guidance is concrete and specific: it names exact surfaces and attributes to inspect, prescribes "Compare clean-state and mutated-state runs with one variable changed at a time", and gives a precise reduction pattern ("initial page or login -> state persisted -> subsequent request or render branch -> resulting capability"). The scoring note explicitly does not penalize absence of code when guidance is this actionable.

3 / 3

Workflow Clarity

A clear sequenced workflow (Quick Start 1–5 plus Map → Tie → Reduce) with verification checkpoints — "Compare clean-state and mutated-state runs with one variable changed at a time" and "Reproduce the smallest stateful sequence that reaches the decisive branch" — plus a "What To Preserve" checklist. This is a read-mostly inspection task, so the destructive/batch feedback-loop cap at 2 does not apply.

3 / 3

Progressive Disclosure

SKILL.md is a concise overview with a clearly signaled one-level-deep reference ("Load `references/browser-persistence.md` for the browser-state checklist, service-worker checklist, and evidence packaging"), and that reference file exists and is self-contained without further nesting. Content is appropriately split and easy to navigate.

3 / 3

Total

12

/

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 precise, complete, and well-gated: it names concrete surfaces and actions, gives explicit natural-language triggers, and scopes itself to a distinct downstream niche. It is concise without fluff and avoids over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete persistence surfaces ("browser cookies, localStorage, sessionStorage, IndexedDB, Cache Storage, service workers, offline caches") and concrete actions ("inspect", "replay", "explain", "trace"), matching the anchor for multiple specific concrete actions rather than the partial coverage at 2.

3 / 3

Completeness

Explicitly states what ("CTF-sandbox workflow for browser cookies, localStorage, ... client-side session persistence") and when ("Use when the user asks to inspect browser state, replay cached auth or session behavior, explain why a page behaves differently after load, or trace how stored client state changes requests"), satisfying both halves with an explicit trigger clause.

3 / 3

Trigger Term Quality

Natural phrases a user would say are well covered ("inspect browser state", "explain why a page behaves differently after load", "trace how stored client state changes requests, rendering, or access"), with domain-appropriate technical terms for the CTF target audience. Not a 2 because the triggers go beyond a single keyword to several natural user phrasings.

3 / 3

Distinctiveness Conflict Risk

A clear niche (browser-held client state within CTF-sandbox) with a hard gate ("Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here"), making conflict with other skills unlikely.

3 / 3

Total

12

/

12

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.

Validation16 / 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.