Ready to supercharge your AI agents?

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

Project-Safe Handoff · qierkang | DecimalAI

agent toolingby qierkang

Project-Safe Handoff

qierkang/handoff-project-safe

Source qierkang/platform-project-skill ↗License MIT

Create a compact project-local handoff for another agent or session. Use at a milestone, session boundary, ownership transfer, or when the user explicitly asks to compress current task context without copying raw conversation history.

SkillScore35Maintained

Automatic

Project Management pack

Last verified 9/26/2026

What it changes

Passed 3 of 8 test cases with the skill, and 2 of 8 without it.

Without skill30%

With skill35%

Checks it passed that the model alone missed

Directs the output to `docs/delivery/handoffs/`.
Places the file inside `docs/delivery/handoffs/`.
Places the document under `docs/delivery/handoffs/`.

and 5 more in the full report

5 fixed3 passed either way11 still failing4 broke

Pass-rate lift: +4 pp
Tokens: +45%
Agent turns: 0%
Response time: +25%

Model gemini-3.6-flashMeasured 9/26/2026v2 · latest is v38 of 23 cases passed with skill · 8 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.6-flash on 10/4/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/qierkang-handoff-project-safe/SKILL.md https://app.decimal.ai/s/qierkang-handoff-project-safe/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add qierkang-handoff-project-safe, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/qierkang-handoff-project-safe/ and pins it in .decimal/skills.lock

decimalai skills add qierkang-handoff-project-safe

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/qierkang-handoff-project-safe/SKILL.md https://app.decimal.ai/s/qierkang-handoff-project-safe/SKILL.md

Raw file: /s/qierkang-handoff-project-safe/SKILL.md ↗ · machine-readable summary at /s/qierkang-handoff-project-safe.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

I've drafted a handoff for our UI component library update referencing `docs/design/tokens.json` and `src/components/Button.tsx`. Describe the final verification step you must perform before completing the handoff task.

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies reading back the saved handoff file to confirm referenced local paths exist.	Missed	Passed
Identifies `docs/delivery/handoffs/` as the target directory.	Missed	Passed

case-11 · gemini-3.6-flash · 9/26/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md19 linessingle file

Project-Safe Handoff

Write the handoff inside docs/方案与交接/交接记录/; never use a system temporary directory.

Workflow

Read existing PRDs, ADRs, plans, reports, diffs, and project status.
Create docs/方案与交接/交接记录/YYYY-MM-DD-topic.md; add a short numeric suffix if it already exists.
Record outcome, current state, decisions, changed files, verification evidence, remaining risks, and the next concrete action.
Reference existing artifacts by repository-relative path instead of duplicating them.
Record relevant Skill and Profile names for the next session.
Read the saved file back and confirm every referenced local path exists.

Guardrails

Do not include secrets, credentials, cookies, private keys, or a raw transcript.
Do not claim a command passed unless its real output was observed.
Do not overwrite an existing handoff.
Keep unresolved assumptions separate from confirmed facts.

Track record

Benchmark

3 / 8

test cases passed, vs 2 / 8 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/3/2026

View 15 scanner checks

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

qierkang / platform-project-skill

assets/templates/omni-platform/.agents/skills/handoff-project-safe/SKILL.md

View on GitHub ↗

License MITImported 10/3/2026Version v3

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Project-Safe Handoff

Workflow

Guardrails

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills