handoff
Use when the user ends a session, asks for a session summary, or needs to create a handoff document for another agent to continue the work.
Skill by ThorStarlord
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thorstarlord-handoff
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/handoff
What's inside
- Skill name
handoff- Description
- Use when the user ends a session, asks for a session summary, or needs to create a handoff document for another agent to continue the work.
- License
- MIT
- Instructions
- 165 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Handoff Produce a professional Feature Completion Summary from the current session's git history and conversation context. The output is a markdown file saved to `docs/handoffs/YYYY-MM-DD-feature-name.md` that the next session (or another agent) can read to resume work without replaying the entire conversation. Data sources in priority order: 1. **Git log** — `git log --oneline -20` (commit history) 2. **Git diff** — `git diff --stat HEAD~N` (changed files) 3. **Conversation context** — what the agent remembers from this session 4. **Test results** — `python -m pytest tests -q --tb=no` (final pass/fail count) ## Output Format Write the output file to `docs/handoffs/YYYY-MM-DD-feature-name.md`. Create `docs/handoffs/` if it doesn't exist. Use this template: ```markdown --- type: handoff session: [feature-name] date: [YYYY-MM-DD] status: GREEN | RED next_task: [single next technical task, 5-8 words] --- # Session Summary — [Feature Name] ## Commits [Numbered list of commits on the working branch, newest first. Include short hash + message for each.] ## Files Modified/Created [Bold each file path; one-line description of what changed.] ## Verification [Exact command the next agent should run to confirm the repository is green before starting work.] ```bash python -m pytest tests -q --tb=no ``` [Expected output: X passed, Y failed.] ## Global Status Ran full test suite: X passed, Y failed, Z warnings. Global status: GREEN | RED ## Architectural Decisions [Bullet list of key decisions with the choice, rationale, AND the alternative considered. Format: - **Decision**: [what was decided] **Why**: [rationale, trade-offs, constraints] **Alternative**: [the rejected option and why it was rejected] ] ## Locked ADRs [Explicit list of ADRs that govern this architecture. No deviations permitted without a new ADR.] - ADR-0001: [title] — [one-sentence scope] - ADR-0002: [title] — [one-sentence scope] ## Frontier [The single next technical task for the next session. Be specific enough that the next agent can start without context. Include file paths, function names, and the expected approach.] ## Blockers (if any) [Things that are stuck, why, and what would unblock them.] ## Agent Re-hydration Block [3-sentence paragraph. Copy-paste this into a brand-new chat session to instantly restore context.] I am starting a new session. Load the `handoff` skill and read `docs/handoffs/YYYY-MM-DD-feature-name.md` to understand the current state and the Frontier, then begin the next task on the list. Before making any changes, run `python -m pytest tests -q --tb=no` to confirm the repository is GREEN. ``` ## Workflow ### 1. Gather Evidence Run in parallel where possible: - `git log --oneline -20` — recent commits on current branch - `git diff --stat HEAD~1` — changed files in the latest commit (or HEAD~N for N commits) - `git status --short` — any uncommitted changes - `python -m pytest tests -q --tb=no` — final test count If the session spans multiple branches, run `git branch --show-current` first. ### 2. Extract Architectural Decisions Scan the conversation context for moments where a trade-off was made and a specific choice was locked. Look for: - "We decided X instead of Y because..." - "The trade-off is..." - "The alternative considered was..." - Explicit "Decision" markers from ADRs or grilling sessions For each decision, explicitly name the **Alternative Considered** and why it was rejected. This prevents the next agent from re-suggesting the rejected option. Aim for 3-5 decisions per session. ### 3. Identify Locked ADRs Scan the conversation and `docs/adr/` directory for ADR files. List every ADR that governs the area being handed off. The "Locked ADRs" section makes it explicit to the next agent: "These decisions are frozen. Do not deviate without a new ADR." ### 4. Identify the Frontier The frontier is the single next concrete task. It must name: - The file to modify (or create) - The function or class to implement - The expected approach (one sentence)
From ThorStarlord/interface-skills, MIT.
More from ThorStarlord/interface-skills
- 0.502score
problem-framer
ThorStarlord
analyze a vague idea or repository fog to produce a structured problem frame.
SkillCFreshness: C★ 1Claude Code +9 - 0.502score
repo-sensemaker
ThorStarlord
analyze a repository to produce a repository sensemaking brief.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
prompt-handoff
ThorStarlord
convert a sensemaking artifact into a ready-to-copy prompt for the next specialized skill.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
setup-interface-skills
ThorStarlord
Configure a repository for Interface Skills.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
ui-brief
ThorStarlord
Turn a vague UI idea into a structured product and design brief before any layout, component, or code work begins.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
sensemaking-docs-reconciler
ThorStarlord
challenge the sensemaking repository's architecture against its documentation, registries, templates, and examples.
SkillCFreshness: C★ 1Claude Code +9 - 0.477score
git-guardrails-claude-code
ThorStarlord
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
SkillCFreshness: C★ 1Claude Code +9 - 0.477score
diagnose
ThorStarlord
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
improve-codebase-architecture
ThorStarlord
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
grill-with-docs
ThorStarlord
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as…
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
caveman
ThorStarlord
Ultra-compressed communication mode.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill-me
ThorStarlord
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 9
- Last commit (this folder)
- May 13, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ThorStarlord/interface-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ThorStarlord
- 0.570score
change-impact-analysis
ThorStarlord
analyze a bounded contemplated or completed repository change to identify decision-relevant affected…
SkillAFreshness: AClaude Code +9 - 0.529score
customer-journey
ThorStarlord
Map a bounded customer journey for a named persona or segment across relevant stages, touchpoints, actions, questions, emotions, pain points, opportunities…
SkillBFreshness: BClaude Code +9 - 0.529score
acceptance-criteria
ThorStarlord
Turn a bounded user story, feature rule, or delivery requirement into explicit testable acceptance scenarios covering happy paths, edge cases, errors, state…
SkillBFreshness: BClaude Code +9 - 0.529score
battlecard
ThorStarlord
Create an evidence-aware competitive battlecard for a named product, competitor, and segment using current market, product, pricing, review, and win-loss…
SkillBFreshness: BClaude Code +9 - 0.529score
competitive-analysis
ThorStarlord
Compare a product with named direct or indirect alternatives using source-dated market evidence, identify parity, gaps, strengths, weaknesses, threats, and…
SkillBFreshness: BClaude Code +9 - 0.529score
discovery
ThorStarlord
Frame an uncertain product problem into evidence-aware problem hypotheses, learning questions, validation approaches, and decision criteria.
SkillBFreshness: BClaude Code +9
Cite this page
handoff skill. Agent Mart. https://agentmart.dev/skills/thorstarlord-handoff (last updated 2026-10-24)