handoff · Skill Details

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger: User-invoked when a branch session is needed (e.g., prototype validation) or when the current context window fills up and work must continue. /ask-matt describes it as "the bridge between context windows."
Mechanism: Compacts current conversation context into a Markdown file in the OS temp directory. Includes a "suggested skills" section for the next agent. Avoids duplicating content from other artifacts (specs, plans, ADRs, issues, commits, diffs) — references them instead. Redacts API keys, passwords, and PII. If arguments are provided, tailors the doc to the described focus.
Output: A Markdown handoff document in the OS temp directory, referencing existing artifacts, suggesting skills, with sensitive information redacted. A new agent reads this file to continue the work.

Use Cases

Two Typical Use Cases

Scenario 01

Handoff after context window exhaustion

An agent session approaches the model's "smart zone" (~120K tokens) but work remains undone. The developer invokes `/handoff`, which compacts key context (decisions made, remaining work, pending items) into a Markdown file in the OS temp directory with a "suggested skills" section. The developer starts a new session referencing this file to continue. Already-captured specs and issues are referenced by link, not duplicated.

Scenario 02

Forking into a prototype session

During a `/grill-with-docs` session, a question arises that needs prototype validation. The current session maintains its reasoning chain. Invoking `/handoff` compacts the context to a new prototype session. `/ask-matt` describes this as step 2 of the main flow: "when a question needs a runnable answer (state/logic/UI), /handoff out, prototype in a fresh session, /handoff back what you learned."

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

ask-mattWorkflow

Tier 2 · Current Skill

handoffWorkflow

Tier 3 · I Use These Skills

No explicit dependency on other Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md50.0%
other50.0%

▸skills/handoff/
▸handoff
- ·SKILL.md
- ▸agents
  - ·openai.yaml

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

Related in Skillset

You May Also Need These Skills

ask-matt

A router skill for the entire skillset: when the user can't remember which skill to use or which flow fits their situation, they invoke this to get a recommendation. It describes the main "idea → ship" flow (grill-with-docs → to-spec/to-tickets → implement), plus on-ramps (triage, diagnosing-bugs, wayfinder), codebase health (improve-codebase-architecture), vocabulary layers (domain-modeling, codebase-design), and standalone skills (grill-me, prototype, research, teach). Following its map leads users to the correct workflow entry point.

Workflow

code-review

A two-axis code review skill: reviews a diff (from a fixed point to HEAD) along both Standards (coding standards + Fowler smell baseline) and Spec (faithful implementation of the originating issue/PRD). Both axes run as parallel sub-agents to avoid context pollution. The report aggregates findings without merging conclusions, ensuring "passes standards but implements the wrong thing" and "implements the right thing but breaks conventions" are both surfaced independently.

Workflow

codebase-design

A shared vocabulary skill for deep module design: provides a precise set of design terms (Module, Interface, Depth, Seam, Adapter, Leverage, Locality) guiding agents and developers to design "deep modules" — a lot of behaviour behind a small interface. Includes design principles (the deletion test, the interface is the test surface) and testability guidelines. A reference skill consumed by other skills (e.g., improve-codebase-architecture, tdd) and invoked directly by engineers.

Style Guide

diagnosing-bugs

A disciplined diagnosis loop for hard bugs and performance regressions. The core idea is to first build a tight feedback loop — no hypothesis phase without one. Six phases: build feedback loop → reproduce + minimise → generate 3-5 falsifiable hypotheses → instrument by prediction → fix + regression test → cleanup + post-mortem. If the codebase architecture can't lock down the bug, it recommends handing off to the improve-codebase-architecture skill.

Workflow