Offsec Debrief
Post-CTF debrief: structured writeup with a failure-analysis track and MEMORY.md lessons
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 9e0de23
Prompt-only CTF debrief generator: on a mock HackTheBox Linux scenario (SNMP leak to creds to sudo misconfig) it turned a flat what-I-did log into a structured post-mortem with a Failure Track — trigger signal, missed stop signal, a rabbit-hole taxonomy, and a one-line rule per dead end — plus a generalized MEMORY.md update, clearly richer than the no-skill baseline for extracting reusable lessons. Self-contained SKILL.md with no bundled scripts, installs with a plain directory copy from a bare HOME. Documentation matches behavior with no overselling.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 5/5
What Offsec Debrief does
Generates a structured writeup after a CTF or pentest, documenting both the successful attack chain and every failed approach with a rabbit-hole taxonomy, then distills generalized lessons into MEMORY.md. Triggers after finishing a HackTheBox/CTF challenge or documenting a penetration test. Turns a flat activity log into a reusable post-mortem.
How to install Offsec Debrief
git clone https://github.com/d0gesec/pownie
mkdir -p ~/.claude/skills
cd pownie && cp -r skills/offsec-debrief ~/.claude/skills/offsec-debrief
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Offsec Debrief
-
/offsec-debriefPost-CTF debrief: structured writeup with a failure-analysis track and MEMORY.md lessons
It also activates on plain-language prompts like these:
-
Write up a debrief for the HTB box I just finished -
Document my failed approaches and lessons from this pentest -
Turn my CTF activity log into a proper post-mortem
Frequently asked questions
- Is the Offsec Debrief skill free?
- Yes. The skill itself is free from d0gesec/pownie. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Offsec Debrief work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Prompt-only CTF debrief generator: on a mock HackTheBox Linux scenario (SNMP leak to creds to sudo misconfig) it turned a flat what-I-did log into a structured post-mortem with a Failure Track — trigger signal, missed stop signal, a rabbit-hole taxonomy, and a one-line rule per dead end — plus a generalized MEMORY.md update, clearly richer than the no-skill baseline for extracting reusable lessons. Self-contained SKILL.md with no bundled scripts, installs with a plain directory copy from a bare HOME. Documentation matches behavior with no overselling.
- What is the Offsec Debrief SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
- How do I install Offsec Debrief?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Offsec Debrief with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.