Orca CLI
stablyai/orca
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…
Resume work from handoff document with context analysis and validation
$ npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 resume-handoff --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/resume_handoff .claude/skills/resume-handoff && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "resume-handoff" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/resume_handoff into .claude/skills/resume-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-handoff", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/resume_handoffType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 resume-handoff --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/resume_handoff .agents/skills/resume-handoff && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "resume-handoff" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/resume_handoff into .agents/skills/resume-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-handoff", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 resume-handoff --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/resume_handoff .cursor/skills/resume-handoff && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "resume-handoff" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/resume_handoff into .cursor/skills/resume-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-handoff", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/parcadei/Continuous-Claude-v3.git --path .claude/skills/resume_handoff--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 resume-handoff --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/resume_handoff .gemini/skills/resume-handoff && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "resume-handoff" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/resume_handoff into .gemini/skills/resume-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-handoff", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install parcadei/Continuous-Claude-v3 resume-handoffInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/resume_handoff .github/skills/resume-handoff && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "resume-handoff" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/resume_handoff into .github/skills/resume-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-handoff", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 resume-handoff --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/resume_handoff .opencode/skills/resume-handoff && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "resume-handoff" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/resume_handoff into .opencode/skills/resume-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-handoff", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
resume-handoffResume work from handoff document with context analysis and validation
Resume Handoff is an agent skill from parcadei/Continuous-Claude-v3. Resume work from handoff document with context analysis and validation
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Session handoff. The repository describes itself as: Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit d07ff4b. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Resume Handoff loads about 2.6k tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 925 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from parcadei/Continuous-Claude-v3 at commit d07ff4b, republished under its MIT licence (© parcadei). 925 words, ~2,574 tokens.
.claude/skills/resume-handoff/SKILL.md (or your agent's skills folder).You are tasked with resuming work from a handoff document through an interactive process. These handoffs contain critical context, learnings, and next steps from previous work sessions that need to be understood and continued.
When this command is invoked:
If the path to a handoff document was provided:
thoughts/shared/plans or thoughts/shared/research. do NOT use a sub-agent to read these critical files.If a ticket number (like ENG-XXXX) was provided:
thoughts/shared/handoffs/ENG-XXXX where ENG-XXXX is the ticket number. e.g. for ENG-2124 the handoffs would be in thoughts/shared/handoffs/ENG-2124/. List this directory's contents.YYYY-MM-DD_HH-MM-SS in 24-hour time format), proceed with the most recent handoff document.thoughts/shared/plans or thoughts/shared/research; do NOT use a sub-agent to read these critical files.If no parameters provided, respond with:
I'll help you resume work from a handoff document. Let me find the available handoffs.
Which handoff would you like to resume from?
Tip: You can invoke this command directly with a handoff path: `/resume_handoff `thoughts/shared/handoffs/ENG-XXXX/YYYY-MM-DD_HH-MM-SS_ENG-XXXX_description.md`
or using a ticket number to resume from the most recent handoff for that ticket: `/resume_handoff ENG-XXXX`Then wait for the user's input.
Read handoff document completely:
Spawn focused research tasks: Based on the handoff content, spawn parallel research tasks to verify current state:
Task 1 - Gather artifact context:
Read all artifacts mentioned in the handoff.
1. Read feature documents listed in "Artifacts"
2. Read implementation plans referenced
3. Read any research documents mentioned
4. Extract key requirements and decisions
Use tools: Read
Return: Summary of artifact contents and key decisionsWait for ALL sub-tasks to complete before proceeding
Read critical files identified:
Present comprehensive analysis:
I've analyzed the handoff from [date] by [researcher]. Here's the current situation:
**Original Tasks:**
- [Task 1]: [Status from handoff] → [Current verification]
- [Task 2]: [Status from handoff] → [Current verification]
**Key Learnings Validated:**
- [Learning with file:line reference] - [Still valid/Changed]
- [Pattern discovered] - [Still applicable/Modified]
**Recent Changes Status:**
- [Change 1] - [Verified present/Missing/Modified]
- [Change 2] - [Verified present/Missing/Modified]
**Artifacts Reviewed:**
- [Document 1]: [Key takeaway]
- [Document 2]: [Key takeaway]
**Recommended Next Actions:**
Based on the handoff's action items and current state:
1. [Most logical next step based on handoff]
2. [Second priority action]
3. [Additional tasks discovered]
**Potential Issues Identified:**
- [Any conflicts or regressions found]
- [Missing dependencies or broken code]
Shall I proceed with [recommended action 1], or would you like to adjust the approach?Get confirmation before proceeding
Use TodoWrite to create task list:
Present the plan:
I've created a task list based on the handoff and current analysis:
[Show todo list]
Ready to begin with the first task: [task description]?CRITICAL: Do NOT implement directly. Always spawn via Task tool.
Analyze task type and select specialist agent:
Leads (can spawn workers):
| Agent | Domain | Use For |
|---|---|---|
kraken | implement | Large features, new systems, major components |
architect | plan | Feature design, system architecture, implementation planning |
phoenix | plan | Refactoring plans, migrations, codebase restructuring |
herald | deploy | Releases, deployments, publishing |
maestro | orchestrate | Complex multi-agent workflows |
Workers (focused specialists):
| Agent | Domain | Use For |
|---|---|---|
spark | implement | Quick fixes, patches, minor tweaks |
scribe | document | Documentation, guides, explanations |
sleuth | debug | Bug investigation, tracing, root cause analysis |
aegis | debug | Security audits, vulnerability scanning |
profiler | debug | Performance optimization, bottleneck analysis |
arbiter | validate | Unit tests |
atlas | validate | E2E/integration tests |
oracle | research | External docs, best practices, how-to |
scout | research | Codebase exploration, finding existing code |
pathfinder | research | Repository structure analysis |
plan-reviewer | review | Feature plan review, design validation |
plan-reviewer | review | Migration review, refactoring validation |
chronicler | session | Session analysis, history summaries |
Spawn the specialist via Task tool:
Use Task tool with:
- subagent_type: [selected agent from above]
- prompt: [task description + relevant handoff context + learnings]Include handoff context in the prompt:
Wait for agent completion, then proceed to next task
Be Thorough in Analysis:
Be Interactive:
Leverage Handoff Wisdom:
Track Continuity:
Validate Before Acting:
User: /resume_handoff specification/feature/handoffs/handoff-0.md
Assistant: Let me read and analyze that handoff document...
[Reads handoff completely]
[Spawns research tasks]
[Waits for completion]
[Reads identified files]
I've analyzed the handoff from [date]. Here's the current situation...
[Presents analysis]
Shall I proceed with implementing the webhook validation fix, or would you like to adjust the approach?
User: Yes, proceed with the webhook validation
Assistant: This is a bugfix task, so I'll route to the `spark` agent.
[Uses Task tool with subagent_type="spark" and prompt containing:
- The webhook validation fix task
- Key learnings from handoff
- Relevant file:line references
- Patterns to follow]
[Waits for spark agent to complete]
The spark agent has completed the webhook validation fix. Moving to the next task...© parcadei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/resume_handoff of parcadei/Continuous-Claude-v3.
Open the folder on GitHubat commit d07ff4b
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in parcadei/Continuous-Claude-v3, which our catalogue first saw on October 7, 2026.
Resume Handoff next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Resume Handoff this skillparcadei/Continuous-Claude-v3 | 3.9k | 1 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Orca CLIstablyai/orca | 89k | 2 repos | ~593 | Automated safety check: Pass | MIT | |
| Beads Task Memorygastownhall/beads | 28k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Session History Searchslopus/happy | 24k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Paseo Agent Handoffgetpaseo/paseo | 20k | 1 repos | ~606 | Automated safety check: Pass | Custom licence | |
| Memori Long-Term MemoryMemoriLabs/Memori | 17k | — | ~2k | Automated safety check: Notes | Custom licence |
stablyai/orca
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
getpaseo/paseo
Hands off the current task, including context, decisions and failed attempts, to a fresh agent through Paseo by writing a self-contained briefing prompt and launching that agent.
MemoriLabs/Memori
Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.
liwp/again
A skill your agent uses when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory.
parcadei/Continuous-Claude-v3
Transform session learnings into permanent capabilities (skills, rules, agents).
parcadei/Continuous-Claude-v3
Systematic hook debugging workflow. An agent skill from parcadei/Continuous-Claude-v3.
parcadei/Continuous-Claude-v3
Full 5-layer analysis of a specific function. An agent skill from parcadei/Continuous-Claude-v3.
parcadei/Continuous-Claude-v3
Problem-solving strategies for gradient methods in optimization
parcadei/Continuous-Claude-v3
Unified math capabilities - computation, solving, and explanation.
parcadei/Continuous-Claude-v3
Routes problems to appropriate mathematical frameworks using expert heuristics
Categories
Resume work from handoff document with context analysis and validation. Resume Handoff is an agent skill from parcadei/Continuous-Claude-v3.
Resume Handoff fits situations like: tasks that involve Session handoff.
Run `npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a claude-code`. Or copy the skill folder (.claude/skills/resume_handoff in parcadei/Continuous-Claude-v3) into .claude/skills/resume-handoff in your project. Claude Code loads it when a task matches its description.
Run `npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a codex`. Or copy the skill folder (.claude/skills/resume_handoff in parcadei/Continuous-Claude-v3) into .agents/skills/resume-handoff in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add parcadei/Continuous-Claude-v3 --skill resume-handoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resume-handoff, .gemini/skills/resume-handoff, .github/skills/resume-handoff and .opencode/skills/resume-handoff in your project.
SKILL.md names no scripts, command-line tools or credentials: Resume Handoff is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Resume Handoff is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Resume Handoff: Orca CLI (stablyai/orca, 89k stars), Beads Task Memory (gastownhall/beads, 28k stars), Session History Search (slopus/happy, 24k stars) and Paseo Agent Handoff (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
parcadei (a GitHub user) maintains it in parcadei/Continuous-Claude-v3, which has 3,943 GitHub stars. The repository holds 141 skills in this directory. The repository was last updated on January 26, 2026.
Source: parcadei/Continuous-Claude-v3 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.