agentleFS
MoeenNehzatiMoeenNehzati/famulus/skills/find-handoff-candidates/SKILL.md

find-handoff-candidates

Skill4 starsChanged 4 months agoMITView on GitHub

Use when `wrap-up` needs to identify recent work sessions that may still require a handoff. Do not invoke directly for transcript review, interpretation, or summarization.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Do not open, read, or summarize flagged transcripts.

    line 43
  2. Distinctive:

    Treat an absent transcript source as an empty source, not an error.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
<!-- BEGIN BLUEPRINT INTERFACES -->

Generated from blueprint.yaml. Do not edit this block by hand.

Executable Interfaces:

Send the required caller (caller skill), interface, version, and arguments; optional dry_run defaults to false. Compact uses ordered positionals plus an option mapping; ordered raw argv uses positionals: [] plus every argv token in list options. Never mix forms.

  • find-handoff-candidates._rtx.interface.calibrate — Re-derive reference median/p75/p90 gap-size statistics per host from real transcripts in a lookback window, to check whether scan's default thresholds still make sense. Diagnostic only -- does not modify any parser file; read the output and edit the relevant parser's default_threshold by hand if it suggests new numbers.
    • Caller: find-handoff-candidates
    • Version: 1
    • Security level: 0
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--days": "N"}, "positionals": [], "stdin": null} Required options: []; positional arity: 0..0; stdin: forbidden
  • find-handoff-candidates._rtx.interface.scan — Scan session transcripts across every configured host (default: trailing 2 days), and report sessions whose conversation since their last completed handoff exceeds a per-host threshold, using mechanical extraction only (no LLM judgment).
    • Caller: find-handoff-candidates
    • Version: 1
    • Security level: 0
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--date": "YYYY-MM-DD", "--days": "N", "--min-gap-chars": "N"}, "positionals": [], "stdin": null} Required options: []; positional arity: 0..0; stdin: forbidden

Instruction Interfaces:

These are LLM-readable instruction surfaces. Read and follow them directly; do not invoke the MCP server for them.

  • prepare-handoff.interface.default@1 — Review recent work, obtain approval, encode project-local continuity, and close with exact machine-readable sentinels.
<!-- END BLUEPRINT INTERFACES -->

Find Handoff Candidates

Invoke scan to identify sessions with substantial conversation since their last completed handoff without opening or semantically judging transcript content.

  • Relay every returned record verbatim. Do not re-judge candidates or filter by handoff_status; a complete session can be returned when substantial work followed its last completed handoff.
  • Do not open, read, or summarize flagged transcripts. Use the returned project, timestamps, gap_net_chars, handoff_status, and resume_hint fields to present or persist each candidate. Follow resume_hint to resume the session and invoke prepare-handoff.interface.default there.
  • Treat an absent transcript source as an empty source, not an error.

Invoke calibrate when the default thresholds appear too sensitive or too permissive. Its output is diagnostic guidance only; it does not change the thresholds.

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.