Topic: skills
17,247 skills in this topic.
-
technical-writing
Use this skill when writing, reviewing, or structuring technical documentation for software projects. Triggers on API documentation, tutorials, architecture decision records (ADRs), runbooks, onboarding guides, README files, or any developer-facing prose. Covers documentation structure, writing style, audience analysis, and doc-as-code workflows for engineering teams.
AbsolutelySkilled/AbsolutelySkilled 116
-
account-management
Use this skill when managing key accounts, planning expansions, running QBRs, or mapping stakeholders. Triggers on account management, expansion playbooks, QBR preparation, stakeholder mapping, renewal strategy, upsell, cross-sell, and any task requiring strategic account planning or relationship management.
AbsolutelySkilled/AbsolutelySkilled 116
-
sales-enablement
Use this skill when creating battle cards, competitive intelligence, case studies, or ROI calculators for sales teams. Triggers on battle cards, competitive analysis, case studies, sales collateral, ROI calculators, sales training, product positioning, and any task requiring sales enablement content or strategy.
AbsolutelySkilled/AbsolutelySkilled 116
-
skill-audit
Use this skill when auditing AI agent skills or agent definitions for security vulnerabilities, prompt injection, permission abuse, supply chain risks, or structural quality. Triggers on skill review, security audit, skill safety check, prompt injection detection, skill trust verification, skill quality gate, agent audit, agent security review, subagent safety check, and any task requiring security analysis of AI agent skill files or agent definition files.
AbsolutelySkilled/AbsolutelySkilled 116
-
interview-design
Use this skill when designing structured interviews, creating rubrics, building coding challenges, or assessing culture fit. Triggers on interview design, rubrics, scoring criteria, coding challenges, behavioral interviews, system design interviews, culture fit assessment, and any task requiring interview process design or evaluation criteria.
AbsolutelySkilled/AbsolutelySkilled 116
-
api-testing
Use this skill when testing REST or GraphQL APIs, implementing contract tests, setting up mock servers, or validating API behavior. Triggers on API testing, Postman, contract testing, Pact, mock servers, MSW, HTTP assertions, response validation, and any task requiring API test automation.
AbsolutelySkilled/AbsolutelySkilled 116
-
api-monetization
Use this skill when designing or implementing API monetization strategies - usage-based pricing, rate limiting, developer tier management, Stripe metering integration, or API billing systems. Triggers on tasks involving API pricing models, metered billing, per-request charging, quota enforcement, developer portal tiers, overage handling, and Stripe usage records.
AbsolutelySkilled/AbsolutelySkilled 116
-
ip-management
Use this skill when managing patents, trademarks, trade secrets, or open-source licensing. Triggers on intellectual property, patents, trademarks, trade secrets, open-source licensing, copyright, IP strategy, license compliance, and any task requiring IP protection or licensing decisions.
AbsolutelySkilled/AbsolutelySkilled 116
-
find-oep
Smart trace-based OEP finder for packed/protected PE executables. Traces through packer stubs using intelligent stepping, anti-debug evasion, and heuristic OEP detection, then captures a state snapshot at the original entry point.
dariushoule/x64dbg-skills 109
-
state-snapshot
Capture a full debuggee state snapshot (all committed memory regions + processor state) to disk for offline analysis
dariushoule/x64dbg-skills 109
-
shellcode-analyzer
Load, unpack, and analyze shellcode in x64dbg. Use this skill when the user wants to analyze shellcode, load a shellcode blob into a debugger, unpack encoded/encrypted shellcode, or perform static/dynamic analysis of shellcode payloads.
dariushoule/x64dbg-skills 109
-
vuln-hunter
Hunt for vulnerabilities in a running debuggee by analyzing imports/exports, triaging attack surface, and iteratively testing for bugs with PoC generation.
dariushoule/x64dbg-skills 109
-
tracealyzer
Trace execution (into or over calls) for N steps or until a condition, then analyze the recorded instruction log
dariushoule/x64dbg-skills 109
-
state-diff
Compare two state snapshots to identify register and memory changes between two points in time
dariushoule/x64dbg-skills 109
-
yara-sigs
Scan a state snapshot's memory dumps with YARA signatures to detect packers, crypto constants, malware, and more
dariushoule/x64dbg-skills 109
-
decompile
Decompile a function to C-like pseudocode using angr
dariushoule/x64dbg-skills 109
-
paper-review
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.
agentscope-ai/OpenJudge 538
-
openjudge
Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating graders from data, and analyzing results (pairwise win rates, statistics, validation metrics). Use when the user wants to evaluate LLM outputs, compare multiple models, design scoring criteria, or build an automated evaluation system.
agentscope-ai/OpenJudge 538
-
find-skills-combo
Discover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two recommendation strategies — **Maximum Quality** (best skill per subtask) and **Minimum Dependencies** (fewest installs). Use this skill whenever the user wants to find skills, asks "how do I do X", "find a skill for X", or describes a task that likely requires multiple capabilities working together. Also use when the user mentions composing workflows, building pipelines, or needs help across several domains at once — even if they only say "find me a skill". This skill supersedes simple single-skill search by decomposing the task into subtasks and assembling an optimal skill portfolio.
agentscope-ai/OpenJudge 538
-
ref-hallucination-arena
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
agentscope-ai/OpenJudge 538
-
rl-reward
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.
agentscope-ai/OpenJudge 538
-
bib-verify
Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for fake citations, validate references in a paper, or audit bibliography entries for accuracy.
agentscope-ai/OpenJudge 538
-
auto-arena
Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.
agentscope-ai/OpenJudge 538
-
claude-authenticity
Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.
agentscope-ai/OpenJudge 538