Agent Skills

---

name: fable-judge

description: Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite TARGET".

---

name: fable-loop

description: End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.

---

name: fable-method

description: A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no task-specific skill covers. Subcommands - plan (stop after the plan), audit (grade finished work against the loop), report (rewrite an answer outcome-first).

---

name: release-helper

description: Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.

---

name: install-agentic-stack

description: Install or update the agentic-stack portable brain in the current project, then verify it. Read by an agent; no human steps required.

---

name: dstack

description: dstack is an open-source control plane for GPU provisioning and orchestration across GPU clouds, Kubernetes, and on-prem clusters.

---

name: dstack-presets

description: Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serving a model.

---

name: dstack-prototyping

description: Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final dstack service with a model request.

---

name: skill-creator

description: Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.

---

name: rev-dex-dumper

description: Dump DEX files from a running Android app for unpacking/deobfuscation. Activate when the user wants to unpack an Android APK, dump DEX from memory, extract decrypted DEX files, or defeat class-loading packing.

---

name: rev-frida

description: Generate Frida hook scripts using modern Frida API. Activate when the user wants to write Frida scripts, hook functions at runtime, trace calls or arguments or return values, intercept native or ObjC or Java methods, dump memory or exports, or handle native module load timing for Android and other targets.

---

name: rev-idapython

description: IDAPython and IDALib script reference for reverse engineering. Activate when the user needs to write IDAPython scripts in IDA, use IDALib for headless analysis, operate on IDB databases, debug with IDA, manipulate memory/registers, traverse functions/blocks/instructions, work with Hex-Rays decompiler API, handle obfuscation, or batch-process binaries.

---

name: rev-struct

description: Reconstruct data structures by analyzing memory access patterns across functions

---

name: rev-symbol

description: Restore function symbols by analyzing code patterns, strings, constants, and cross-references

---

name: rev-u3d-dump

description: Dump Unity IL2CPP symbols from iOS/Android builds. Extract method names, addresses, and type info from IL2CPP binaries and global-metadata.dat, then generate IDA/Ghidra import scripts.

---

name: rev-unicorn-debug

description: Debug and emulate specific code fragments or functions using the Unicorn engine. Activate when the user wants to emulate a function with Unicorn, trace binary execution without running the full program, decrypt or decode data by emulating the algorithm, or bypass environment dependencies (JNI, syscalls, libc) during emulation.

---

name: prp-bro

description: Restates the previous response in plain language, with no jargon. Use when the user says "bro", asks to "say that plainly", says "explain it simply", or invokes /prp-bro.

---

name: prp-codebase-question

description: Research codebase questions using parallel agents - documents what exists, not what should change. Use when the user asks how the codebase works, where something lives, or invokes /prp-codebase-question.

---

name: prp-commit

description: Creates Git commits for completed work. Always use when committing changes, when the user explicitly asks to commit the work, when another PRP workflow reaches its commit step, or when the user invokes /prp-commit.

---

name: prp-companion

---

name: prp-debug

description: Diagnoses a bug, error, stack trace, regression, or unexplained behavior and publishes the evidence-backed root cause to GitHub. Use when the user says "debug this", "find the root cause", provides a bug report or stack trace, asks to investigate a GitHub issue, or invokes /prp-debug. Defaults to commenting on the matching open issue or creating one when none exists.

---

name: prp-deliver

description: This is an experimental skill. Never use it unless the user explicitly tells you to invoke /prp-deliver.

---

name: prp-implement

description: Implements and validates existing PRP plans and corrects reviewed or failing-CI pull requests. Always use when executing an implementation plan, implementing an issue that already has a local or published plan, correcting a PR from a PRP review report or CI failure, when another PRP workflow reaches its implementation or correction step, or when the user invokes /prp-implement.

---

name: prp-issue

description: Autonomously owns one workstream from an issue, PRD, document, existing plan, or free-form request through planning, implementation, pull request, independent review, corrections, and green CI. Always use when the user asks to implement or ship work end to end, take an issue or idea to a reviewed PR, run plan to PR, invokes /prp-issue, or when prp-orchestrate needs an end-to-end delivery engine.