ByteLandTechnology/headless-ghidra / headless-ghidra-intake
headless-ghidra-intake
VerifiedP0 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.
| File | Kind | Size |
|---|---|---|
| README.ja-JP.md | markdown | 4.9 KB |
| README.md | markdown | 4.4 KB |
| README.zh-CN.md | markdown | 4.1 KB |
| SKILL.md | skill md | 2.0 KB |
| examples/intake-speckit-handoff.md | markdown | 2.9 KB |
| planning-brief.md | markdown | 4.9 KB |
examples/intake-speckit-handoff.md
View on GitHub# Example: Intake Speckit Handoff
## When To Use This Example
Use this example when the team still needs to normalize the target, define
project initialization expectations, and make the first `speckit` handoff
portable across workspaces.
## Purpose
Show how the intake phase contract is carried into `speckit` without requiring
any downstream extension or constitution edit, and how the same contract is
used immediately afterward for audit.
## Source Contract
- [`../planning-brief.md`](../planning-brief.md)
## Example Context
- Target: `sample-target.bin`
- Goal: define initial scope, setup assumptions, and expected planning outputs
- Known constraint: the workflow must stay headless-only and evidence-backed
## Handoff Pattern
Example request shape:
```md
Use the intake phase planning brief for this request.
Prepare `spec.md`, `plan.md`, and `tasks.md` for a headless-only Ghidra
reverse-engineering workflow.
Target identity:
- sample-target.bin from the reviewed intake bundle
Workflow scope:
- normalize the target
- capture initialization assumptions
- preserve setup details needed for later evidence extraction
Non-negotiable constraints:
- headless-only workflow
- evidence-backed claims
- reproducible setup expectations
- reviewable Markdown outputs
- no downstream speckit extension or constitution change required
Local rule overlay:
- local project rules may require an extra intake summary section
- local project rules may not replace the intake contract with GUI notes or informal
setup steps
```
## Expected Observations
- The generated planning artifacts keep the intake constraints explicit.
- The artifacts remain portable across workspaces.
- A reviewer can understand the target and scope in one pass.
## Audit Walkthrough
- Check `spec.md` for target identity and scope boundaries.
- Check `plan.md` for replayable setup assumptions.
- Check `tasks.md` for Markdown-reviewable deliverables and no GUI-only steps.
- If any generated artifact drops a non-negotiable intake constraint, refine or
regenerate the planning artifacts rather than weakening the phase contract.
## Local Rule Interpretation
- Valid additive overlay: a local project requires one more Markdown checklist
item describing analyst ownership.
- Invalid weakening attempt: a local project says target setup can be captured as
informal GUI notes after planning.
## Next Step Routing
- Stay with intake if target identity, scope, or deliverable definitions are
still moving.
- Move to evidence when replay surfaces, artifact capture, or validation gates
need to become explicit.
- Move to script authoring and review when the plan introduces reusable
headless Ghidra scripts.
## Cross-Links
- Umbrella routing:
[`../../headless-ghidra/SKILL.md`](../../headless-ghidra/SKILL.md)
- Evidence next step:
[`../../headless-ghidra-evidence/SKILL.md`](../../headless-ghidra-evidence/SKILL.md)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |