agentleFS
elithrarelithrar/dotfiles/.agents/skills/summarize-work/SKILL.md

summarize-work

Skill222 starsChanged 54 days agoMITView on GitHub

Summarize OpenCode session history into work recaps, commit messages, or PR descriptions. Use when a summary needs past sessions or cross-project history; ordinary commits and summaries fully supported by the current conversation do not need this skill.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the requested project and time range.

    line 8
  2. Distinctive:

    Write the requested recap, commit message, or PR description.

    line 14

≈ “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

OpenCode work summaries

Use the requested project and time range. Default to the current project; expand across projects only when requested or needed to answer an explicit correction. Use the user's timezone for time boundaries.

For the current session, use the conversation and relevant git state without querying OpenCode. For past sessions, read references/api.md to discover the configured server and retrieve only relevant history. Do not silently drop short sessions or truncate their substantive content; even one message can record an important fix.

Reconcile session claims with the relevant diff, commits, or file state when available. Resolve the actual base branch or upstream rather than assuming origin/main or origin/master. Distinguish planned, attempted, implemented, tested, and merged work. Todos and an assistant's success claim alone are not proof of completion.

Write the requested recap, commit message, or PR description. Explain why the change mattered and what it accomplished. Group cross-project work by project and omit empty categories. Keep the output proportional to the meaningful changes, and follow the user's requested structure.

Exclude secrets and sensitive transcript data. If history cannot be retrieved, summarize the available evidence and state the coverage gap. Do not infer missing work or ask for a service setup before completing a summary the visible context already supports.

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.