skills/handoff-resume/exports/claude/SKILL.md
Resume repository work from an existing handoff markdown by reading it first, executing pending tasks in order, and marking completed tasks with `Done? = Yes` only when concrete evidence exists.
npx skillsauth add balandongiv/agent-skillbook handoff-resumeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill when the user wants the agent to start from an existing handoff instead of reconstructing context from the full conversation. The handoff becomes the execution checklist, and completed tasks must be marked in the handoff with evidence.
Do not start editing files or relaunching commands until the selected handoff markdown has been read.
The handoff is not only context; it is the list of tasks to execute and close out.
Only mark Done? = Yes when the task is actually complete and the evidence column points to the validating artifact, log, or command.
Update the handoff in place without deleting its prior context. Make the new evidence easy to audit.
Read planning/Project_Execution_Flowchart.md first.
Read the named handoff file. If the user did not specify one, prefer the newest relevant file under handoff/.
Identify:
If the handoff does not already use a markdown table with Task, Done?, and Evidence / Next step, convert it before continuing. Initialize unfinished tasks as No.
If the handoff references long-running processes, check whether they are still alive before starting new ones. If the handoff says something was manually stopped, verify that instead of assuming it.
Work through the pending items in order unless the handoff or current evidence makes a different dependency order clearly correct.
For each completed task:
Done? from No to YesNoIf the resumed work changes artifact contracts or workflow expectations, update planning/Project_Execution_Flowchart.md.
planning/Project_Execution_Flowchart.md before resuming.Done? to Yes.Yes for a task that remains partially complete.tools
One-sentence description of what this skill does and when to use it.
tools
One-sentence description of what this skill does and when to use it.
documentation
Review per-subject performance to identify likely outliers, distinguish bad data from difficult but valid cases, and document whether subject exclusion is justified before any filtered rerun.
documentation
Review per-subject performance to identify likely outliers, distinguish bad data from difficult but valid cases, and document whether subject exclusion is justified before any filtered rerun.