Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Resume Handoff

ASecurity

You are resuming work from a handoff document through an interactive process. Handoffs carry context, learnings, and next steps from a prior session that need to be understood and continued — never assume the handoff's state still matches the codebase; verify first.

20 stars
0 votes
0 copies
1 views
Added 9/3/2026
ai-agentsbash

Works with

claude codecli

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add coalesce-labs/catalyst --skill resume-handoff --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Resume Handoff?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Resume Handoff
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/coalesce-labs-resume-handoff/badge)](https://www.skillsdirectory.com/skills/coalesce-labs-resume-handoff)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: resume-handoff
description:
  "Resume work from a handoff document. **ALWAYS use when** the user says 'resume handoff', 'pick up where we left off', 'continue from handoff', or provides a handoff document path. Verifies current codebase state against handoff, validates changes, and creates an action plan."
disable-model-invocation: false
allowed-tools: Read, Bash, TodoWrite
version: 1.0.0
---

# Resume work from a handoff document

You are resuming work from a handoff document through an interactive process. Handoffs carry context, learnings, and next steps from a prior session that need to be understood and continued — never assume the handoff's state still matches the codebase; verify first.

## Load on demand

| when | read |
| -- | -- |
| finding the handoff to resume from (no path given, path given, ticket given, or the cited path is missing on disk) | [`references/discovery.md`](references/discovery.md) |
| reading the handoff, verifying it against current state, and building the plan | [`references/process.md`](references/process.md) |
| deciding what to do given the codebase's divergence from the handoff | [`references/scenarios.md`](references/scenarios.md) |

## Prerequisites

```bash
# Thoughts must exist for this skill's documents. CTL-2306: the full host setup check (daemon,
# registry, house rules) belongs to the setup-catalyst skill, not to a skill that must run anywhere.
[[ -e thoughts/shared ]] || echo "⚠️ thoughts/shared is missing in $(pwd) — run \`humanlayer thoughts init\` or the setup-catalyst skill; if the prompt names an output path, write there" >&2

# CTL-2306 explicit-input discovery: begin
# Find the handoff to resume on disk for the ticket this run was given: $CATALYST_TICKET under a
# phase, else a ticket named in the skill's argument text (Claude Code substitutes the token in
# the heredoc below; another harness leaves it literal, which names no ticket). Nothing is
# remembered between runs. `[!0-9]` keeps PROJ-1 from matching PROJ-10's documents.
TICKET_ID="${TICKET_ID:-${CATALYST_TICKET:-}}"
if [[ -z "$TICKET_ID" ]]; then
  SKILL_ARGS=$(cat <<'CATALYST_SKILL_ARGS'
$ARGUMENTS
CATALYST_SKILL_ARGS
)
  TICKET_ID=$(printf '%s' "$SKILL_ARGS" | grep -oE '[A-Z]+-[0-9]+' | head -1)
  [[ -n "$TICKET_ID" ]] || TICKET_ID=$(printf '%s' "$SKILL_ARGS" | tr '[:lower:]' '[:upper:]' | grep -oE '[A-Z]+-[0-9]+' | head -1)
fi
RECENT_HANDOFF=""
if [[ -n "$TICKET_ID" ]]; then
  RECENT_HANDOFF=$(find -H thoughts/shared/handoffs -type f -name '*.md' -ipath "*${TICKET_ID}[!0-9]*" -exec ls -t {} + 2>/dev/null | head -1)
elif [[ -z "${CATALYST_PHASE:-}" ]]; then
  RECENT_HANDOFF=$(find -H thoughts/shared/handoffs -type f -name '*.md' -exec ls -t {} + 2>/dev/null | head -1)
fi
# CTL-2306 explicit-input discovery: end
# CTL-2104: guard the discovered path anyway — thoughts/shared is a per-project symlink and a path can vanish mid-run; an unguarded read of a phantom path yields an empty document that reads like an empty handoff.
if [[ -n "$RECENT_HANDOFF" && ! -f "$RECENT_HANDOFF" ]]; then
  echo "⚠️ Cited handoff is not on disk: $RECENT_HANDOFF"
  echo "   The channel is authoritative — recover from the last turn's text, see references/discovery.md."
  RECENT_HANDOFF=""
elif [[ -n "$RECENT_HANDOFF" ]]; then
  echo "📋 Found handoff: $RECENT_HANDOFF"
else
  echo "⚠️ No handoff found on disk for ${TICKET_ID:-this run}"
fi
```

## Configuration note

This skill uses ticket references like `PROJ-123`. Replace `PROJ` with your Linear team's ticket prefix — read it from `.catalyst/config.json` if available, otherwise use a generic `TICKET-XXX` form (`ENG-123`, `FEAT-456`).

## Invariants

- **Read the handoff document completely** — no `limit`/`offset` — and read every research or plan document it references, before proposing anything.
- **Never use sub-agents to read the handoff itself.** Sub-agents are fine for verifying the codebase state it describes ([`references/process.md`](references/process.md)).
- **Get user confirmation** before acting on the analysis, and again before starting implementation.
- **A missing handoff file is not lost work.** The channel/ticket thread is authoritative; recover from there rather than re-doing landed work ([`references/discovery.md`](references/discovery.md)).

## CLI tools

To fetch ticket context from Linear (e.g. a ticket referenced in the handoff), use the Linearis CLI — run `linearis issues usage` or see `/catalyst-dev:linearis` for exact syntax. Do not guess commands.

Attribution

coalesce-labscoalesce-labs
View sourceMore from coalesce-labs →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →