agentleFS
HadiFrt20HadiFrt20/deepresearch/dr-resume/SKILL.md

dr-resume

Skill4 starsChanged 7 months agoMITView on GitHub

Resume research after a crash or new session. Reads changelog to find last completed task, shows what was done and what remains, then offers to continue.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 1 is distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .research/CHANGELOG.md.

    line 12
  2. Very specific:

    If last 3+ entries are FAIL, warn: "Last session had consecutive failures.

    line 51
  3. Distinctive:

    If there's a CHECKPOINT with "stop" recommendation, show it.

    line 52
  4. Very specific:

    If todo.md has tasks marked [!], note: "{N} failed tasks could be retried."

    line 53
  5. Very specific:

    All done → "Run /dr-report to synthesize findings."

    line 60
  6. Very specific:

    If CHANGELOG.md is empty or missing, tell the user: "No previous session found.

    line 64
  7. Very specific:

    If todo.md is missing, tell the user to run /dr-new first.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are helping the user resume a research project after a session break, crash, or context window reset.

Steps

1. Read Changelog

Read .research/CHANGELOG.md. Find the last entries to determine:

  • Timestamp of last activity
  • Last completed task ID
  • Last status (DONE, FAIL, CHECKPOINT)
  • Any session-end summary

2. Find Current Position

Read todo.md. Find:

  • The last task marked [x] or [!]
  • The first unchecked task [ ]
  • Count remaining unchecked tasks

3. Check Phase Status

Read .research/ROADMAP.md. Identify:

  • Which phase was in progress
  • How many phases are complete
  • How many phases remain

4. Print Resume Summary

## Research Resume

Last session: {timestamp of last changelog entry}
Last completed: {task_id} — {task description}
Phase: {phase number} ({phase status})

Progress:
  Completed: {count}
  Failed: {count}
  Remaining: {count}

Next task: {first unchecked task_id} — {task description}

5. Check for Issues

  • If last 3+ entries are FAIL, warn: "Last session had consecutive failures. Consider /dr-improve before continuing."
  • If there's a CHECKPOINT with "stop" recommendation, show it.
  • If todo.md has tasks marked [!], note: "{N} failed tasks could be retried."

6. Suggest Next Action

  • Tasks remain in current phase → "Run /dr-run to continue from {next task_id}."
  • Phase just completed → "Run /dr-review to validate, then /dr-run for next phase."
  • Many failures → "Run /dr-improve to analyze failures and optimize the researcher."
  • All done → "Run /dr-report to synthesize findings."

Error Handling

  • If CHANGELOG.md is empty or missing, tell the user: "No previous session found. Run /dr-new to start a new project or /dr-run to begin execution."
  • If todo.md is missing, tell the user to run /dr-new first.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.