Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

/debrief — measured AI agent skill | DecimalAI

davepoon/debrief

NewSkillScoreMaintained

Alias for `/origin:handoff` — symmetric brief/debrief naming. Same behavior: end-of-session ritual that writes session log + project status + granular MCP captures. Invoked as `/debrief`. Use when the user prefers the brief/debrief pair over brief/handoff.

agent-toolingby davepoon

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Knowledge Management pack

decimalai skills pull davepoon-debrief

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/davepoon-debrief/SKILL.md

Raw file: /s/davepoon-debrief/SKILL.md ↗ · machine-readable summary at /s/davepoon-debrief.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4h ago

—-50% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	7%	0%
case-04	✗→✓	▲ Improved	-55%	0%
case-05	✗→✓	▲ Improved	-60%	0%
case-06	✗→✓	▲ Improved	-51%	0%
case-07	✗→✓	▲ Improved	-70%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

davepoon / buildwithclaude

plugins/origin/skills/debrief/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

/debrief

Alias for /handoff. Identical behavior — full end-of-session ritual: git context grab (if repo), narrative session log at ~/.origin/sessions/, project status update, granular MCP captures.

Run the steps in /origin:handoff exactly. Same artifacts, same guardrails. The only reason this skill exists is the symmetric naming — /brief (session start) ↔ /debrief (session end). Pick whichever verb feels natural; both invoke the same flow.

When to use

User says "wrapping up", "let's call it", "we're done", "debrief".
Session about to close and useful state would otherwise be lost.

When NOT to use

Mid-flow capture during work → use /capture (single memory).
Search / lookup → use /recall.

Want to see if davepoon/debrief would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.