Ready to supercharge your AI agents?

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

Florianbruniaux/Handoff Resume — measured AI agent skill | DecimalAI

florianbruniaux/handoff-resume

NewSkillScoreMaintained

Load a handoff document and resume work from where a previous session left off. Parses scope, file references, completed work, and next steps, then confirms understanding before proceeding.

agent-toolingby florianbruniaux

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

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Project Management pack

decimalai skills pull florianbruniaux-handoff-resume

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/florianbruniaux-handoff-resume/SKILL.md

Raw file: /s/florianbruniaux-handoff-resume/SKILL.md ↗ · machine-readable summary at /s/florianbruniaux-handoff-resume.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

—+10% tokens0% turns23% of whole cases pass with skill (5/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-08	✗→✓	▲ Improved	29%	0%
case-06	✗→✓	▲ Improved	778%	0%
case-14	✗→✓	▲ Improved	187%	0%
case-09	✓→✗	▼ Worse	-23%	0%
case-21	✓→✓	＝ Same ✓	9%	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

florianbruniaux / claude-code-ultimate-guide

examples/skills/handoff-resume/SKILL.md

View on GitHub ↗

License CC-BY-SA-4.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

Read and load the handoff document at $ARGUMENTS[0].

Steps

Read the file at the provided path. If the path does not exist, list files in claudedocs/handoffs/ and ask the user which one to load.

Parse and confirm:

Task and scope
Files involved (with line numbers)
Key discoveries
Work completed so far
Current status
Next steps (ordered)

Confirm understanding: Summarize what you have loaded in 3-5 bullet points. Ask: "Should I proceed with the next step, or do you want to adjust the plan first?"

Do not start working until the user confirms. The confirmation step is mandatory.

Notes

If the handoff file references commits (commit: abc1234), note them but do not re-run the work.
If next steps are unclear or conflicting, flag it before proceeding.
The "Work Done" section is the authoritative record of what has been completed. Trust it.

Want to see if florianbruniaux/handoff-resume 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.