ByteLandTechnology

Rust CLI reference for the headless-ghidra pipeline. Covers command syntax, flags, output contract, artifact paths, and workspace layout for all ghidra-agent-cli subcommands. Load when: constructing a ghidra-agent-cli command, interpreting its output, resolving a flag or artifact path question, or debugging CLI behavior. Do not load for P0–P4 workflow sequencing — use the headless-ghidra skill family instead.

Thoroughly analyze a single function by first recovering its type definitions, constant definitions, vtables, function name and signature, then producing the final decompilation. Use when the user wants a complete per-function analysis following the strict recovery order: types → constants → vtables → function identity → decompilation.

Entry skill for the Headless Ghidra YAML-first reverse-engineering pipeline. Use when the user asks to analyze, decompile, triage, resume, or iterate on a binary target with Ghidra/headless-ghidra. Reads artifacts/<target>/pipeline-state.yaml, routes P0–P4 phase skills, runs gate checks, and manages review pauses. Performs zero analysis work itself.

P1 phase skill for Headless Ghidra baseline and runtime evidence. Use after P0 when the target must be imported into Ghidra, auto-analyzed, exported to baseline YAML, and given reproducible runtime or hotpath observations without decompiling function bodies.

P4 phase skill for Headless Ghidra selected function substitution. Use after P3 when an approved batch of functions should have metadata applied, be decompiled through Ghidra, and be recorded as per-function capture/substitution YAML.

P3 phase skill for Headless Ghidra metadata discovery. Use after P2, or after a P4 batch exposes missing context, to enrich function names, signatures, types, constants, strings, and hotpath metadata in YAML before serialized CLI apply.

P2 phase skill for Headless Ghidra third-party evidence. Use after P1 to review baseline/runtime artifacts, identify or rule out third-party code, record pristine sources, classify functions, and capture evidence before metadata recovery.

P0 phase skill for Headless Ghidra intake. Use when a target binary/archive needs identity confirmation, workspace initialization, Ghidra discovery, binary inspection, or analysis scope setup before any Ghidra analysis runs.

Use when the task requires operating or validating the package-local `spec-forge-cli` Rust command surface for initializing workspaces, resolving interactions, mutating YAML artifacts, recording approvals, selecting focus batches, checking gates, advancing stages, or validating UX contracts.

Use when you need to turn approved framing into a top-level solution shape, journey list, and component list before refining detailed flows or implementation contracts.

Use when you need to define component-level contracts in reviewable batches, including responsibilities, interfaces, state, data models, and implementation constraints.

Use when you need to execute an approved implementation spec, record what changed, capture validations, and track whether any blockers still prevent completion.

Use when you need to turn a rough request into a clear spec framing by defining the problem, stakeholders, scope boundaries, and non-negotiable constraints before solution design begins.

Use when you need to refine user journeys or process flows step by step in small review batches, including states, alternate paths, edge cases, and acceptance detail.

Use when you need to consolidate prior stage artifacts into an implementation-ready spec, confirm completeness, record open assumptions, and decide whether the work is ready to build.

Router for the spec-forge skill family: initialize a multi-spec `.spec-forge/` YAML collection, detect the earliest incomplete phase for the targeted `spec_id`, enforce hard stage gates, and route broad-to-fine, role-based spec refinement from problem framing through readiness and implementation.

Scaffold stage for the cli-forge skill family: create a new Rust CLI Skill project from the authoritative templates and prepare it for validation.

Plan stage for the cli-forge skill family: define the detailed CLI contract including commands, flags, output formats, stream/repl/daemon capability scope, the daemon app-server contract, and runtime behavior before scaffold or extend stages proceed.

Publish stage for the cli-forge skill family: manage the GitHub Release and multi-package npm publication automation for a generated skill.

Design stage for the cli-forge skill family: define or refresh the generated skill's high-level identity, purpose, positioning, and description contract before downstream stages proceed.

Router for the cli-forge skill family: classify the request, detect missing contract baselines, check filesystem state, and route to the earliest incomplete or takeover stage.

Validate stage for the cli-forge skill family: run the 47-check compliance ruleset against a scaffolded, takeover-adopted, or extended skill project and compare any daemon surface against the declared CLI plan.

Extend stage for the cli-forge skill family: add stream or repl features to an existing scaffolded skill project or to a takeover-adopted project that already matches the scaffold-compatible layout.

Recovery stage for the cli-forge skill family: adopt an existing Rust CLI Skill project that lacks cli-forge contracts by reconstructing design/plan artifacts from the current implementation, enforcing gates, and stopping for user decisions on ambiguity.

Umbrella guide for the rust-cli skill family: route Rust CLI Skill work through intake, description, scaffolding, feature extension, validation, and publish/release while preserving the constitution, package layout contract, and packaging boundaries.

Description stage for the rust-cli skill family: define or refresh the generated skill description contract before downstream stages change scaffold, feature, validation, or packaging surfaces.

Extension stage for the rust-cli skill family: add the supported stream or repl feature to an existing scaffolded project while preserving the shared runtime contract.

Triage stage for the rust-cli skill family: classify the request as description, scaffold, extend, validate, or publish, confirm required inputs, load the shared rules, and hand off to the correct next phase.

Publish stage for the rust-cli skill family: close the workflow with repository-owned packaging and release actions, including report-only summaries, dry runs, exact-mirror rehearsals, destination configuration checks, and the supported GitHub Actions publication path.

Scaffold stage for the rust-cli skill family: create a new Rust CLI Skill project from the package templates and prepare it for validation.

Validation stage for the rust-cli skill family: run the documented compliance checks for an existing project and report whether it is constitution-compliant, usable with warnings, or blocked by errors.

Internal helper contract for calling the Gemini-backed gemini-companion runtime from Claude Code

Internal guidance for composing Gemini prompts for coding, review, diagnosis, and research tasks inside the Gemini Claude Code plugin

Internal guidance for presenting Gemini helper output back to the user

Terminal client for Jellyfin media servers — browse libraries, control playback, manage users, run admin tasks, and automate workflows from the command line. Use this skill whenever the user mentions Jellyfin, media servers, streaming, home theater automation, or asks to interact with a Jellyfin instance programmatically. Also use when the user is working in this repository (jellyfin-agent-cli) — building, testing, debugging, or extending the CLI itself. Triggers on: "jellyfin", "media server", "jellyfin cli", "jellyfin-agent-cli", "streaming automation", "home theater cli", "jellyfin e2e", "jellyfin api", "browse my movies", "play media from terminal".

Telegram automation CLI with structured output, runtime-state inspection, interactive REPL, scenario testing, and MCP server for AI agents