research-agent/skills/resume/SKILL.md
Resume an interrupted research-agent run. Re-launches the researcher with instructions to read .research/state.md and log.md, reorient, and continue from the documented current focus. Use after a context compression, session restart, or explicit pause.
npx skillsauth add queelius/claude-anvil 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.
Continue a paused or interrupted research-agent run.
Use the Read tool on .research/state.md. If the file does not exist, tell the user there is no research to resume here and suggest /research-agent:research to start fresh.
Use Read tool to load .research/state.md and the last 5 entries from .research/log.md. Show the user a one-paragraph preview of what the researcher will pick up:
Resuming research on "{goal}". Current focus: {from state.md}. Last cycle was {N} on {date}: {modality} -> {result}. Outstanding sub-problems: {count open}. Untested hypotheses: {count untested}.
Spawn the researcher agent (Agent tool, subagent_type research-agent:researcher) with this prompt:
<mode>resume</mode>
<working_directory>
{absolute path to current working directory}
</working_directory>
Resume your research from disk. Do NOT recreate .research/ or
overwrite goal.md.
Step 1: Read .research/state.md in full to reload current beliefs,
sub-problem statuses, hypothesis statuses, and current focus.
Step 2: Read the last 15 entries of .research/log.md to recall recent
activity, including any failed attempts and pivots.
Step 3: Continue your research loop from the documented "Current
focus" in state.md. Run cycles as normal: DECOMPOSE if needed,
HYPOTHESIZE, ATTEMPT, EVALUATE, REFLECT. Append to log.md after
every cycle.
If state.md indicates the goal has been concluded (synthesis.md
exists), do NOT run new cycles; tell the orchestrator the research
is already complete and point at synthesis.md.
After launching, tell the user:
Researcher resumed. It has reloaded state from .research/state.md and is continuing from the current focus. Use
/research-agent:statusto check progress, or/research-agent:synthesizeto force conclusion.
tools
This skill should be used when the user asks about research directions, open problems, future work, or follow-up research from the academic literature. Trigger phrases include "open problems in X", "what's next for Y", "future work for paper Z", "research directions on T", "salient follow-up research", "what should I work on next in", "find me follow-up research unrelated to my prior work", "broad survey of W", "neglected directions in V". Routes the request to the right Vista MCP tool, reads back the structured paper sections, and synthesizes research directions in the conversation.
testing
Discover latent themes in the metafunctor corpus. Use when the user wants to find implicit through-lines across their blog posts, surface recurring ideas they have not consciously framed as a series, or get candidate themes for a synthesis post. Reads titles, descriptions, and tags; proposes 3 themes that connect 4+ posts each, each with a single-sentence through-line. Output is a proposal, not a draft. Trigger phrases include "find themes in my posts", "what threads connect my writing", "latent themes in my corpus", "scribe".
development
Use when drafting prose sections for a bookwright (technical non-fiction) project. Encodes the Bernoulli-textbook workflow: atom-outward design, deferral discipline, running threads, page budgets, Path A subagent pattern, header comment block convention.
testing
Use when drafting or executing a paired notebook for a bookwright chapter. Covers when notebooks are required vs optional, numerical-sanity-target convention, exec-from-fresh-kernel requirement, and stack-specific execution commands (Jupyter/R Markdown/Quarto).