recall

Files (2)

• LICENSE
• SKILL.md

SKILL.md (first lines)

Read [the native runtime contract](../dav-mode/references/playbook-runtime.md) before executing. It maps the Cursor tools, model examples, configuration paths and cloud placements below to actual native capabilities. Those examples do not authorize unsupported calls, delegation, model campaigns, publication or desktop access. Keep the full method and report an unavailable required capability as a gap.

## Runtime adaptation

The user and project instructions take precedence. Use an authorised history
API or export from the current harness. Cursor transcript paths below are
Cursor examples, not paths to assume on Yuke or Codex. Never search unrelated
projects, credentials, or chats. If history is unavailable, say so and use the
supplied conversation and observed live state; label that as partial context,
not recovered history. Cite actual chat identifiers or exported source paths;
never invent a Cursor UUID for another harness.

Delegate only when the user explicitly requests subagents, delegation, or
parallel work; otherwise mine in-scope history and investigate the shared record
serially using the installed `why` skill. Use configured models and the actual
child API, and follow its start-and-wait lifecycle. Pass complete briefs and the
shared-desktop rules. All searches and live-state checks are read-only. Check for
`.jj/` before version-control commands; in colocated repos use `jj` rather than
Git. Use the installed `unslop` skill for the brief and the installed
`dav-mode/playbooks/session-pickup.md` for a specific session handoff.
Use the installed [automate-me](../automate-me/SKILL.md) only when the user
requests a personal-mode workflow, not as an automatic part of recall.

# Recall

**Before you start or resume work, you rebuild the user's recent working context and hand back a tight capsule of where things stand now and what to do next.**

Keep it tight and on-topic. Read only what the in-scope threads need, then stop.

Your context lives in two records. Your own chat history holds what you did and decided. The shared record holds everything that happened around the same code under other names: the symptoms users keep reporting, the fixes that shipped and got reverted, the errors still firing in prod. That second record is what the **why** skill searches, across source control, the issue tracker, chat and issue channels, long-form docs, and error tracking. A feature with a long bug tail keeps most of its story there, so don't reconstruct it from your transcripts alone.

Transcripts live at `~/.cursor/projects/<slug>/agent-transcripts/<uuid>/<uuid>.jsonl`, where `<slug>` is the workspace path with the leading slash dropped and each "/" turned into "-" (so `/Users/you/proj` becomes `Users-you-proj`). Every line is one chat message.

1. Classify, then route. One specific prior chat to resume is the `session-pickup` playbook, not this. Turning habits into a durable skill is `automate-me`. A human-readable summary of your work is a different task. Recall loads working context across recent chats before you act. If the user already gave you a full state capsule (paths, branch, the change), use it and skip the mining.
2. Lock the scope before searching. Pin the window ("recent" is a real range, default the last 7 days), the topic if named, and the workspace (default the active one. Never read another project's transcripts without being asked). State the scope back. Never quietly turn "all" into "recent N".
3. Fan out across your chat history. Spawn parallel subagents on a fast, cheap model, each taking a slice of the corpus. Tell every subagent to order candidates by real modification time (`ls -t`) and never by UUID name, grep the topic first and then read only the matching chats and only their relevant regions, and skip the current chat plus obvious noise (subagent, eval, and test chats). Each returns the same schema, one block per chat: topic, the user's goal, decisions, open threads, struggles and corrections, and artifacts (PRs, tickets, branches), each citing the chat UUID. For one or two chats, skip the fan-out and search directly. The raw transcripts stay in the subagents. The main thread gets only their findings. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **dav-mode** skill.
4. Sweep the shared record whenever the topic names a feature, file, subsystem, area, or bug. This is the default, not a judgment call, and "my work on X" does not exempt it. Hand it to the **why** skill's source investigators, but steer their question from "why was this built this way" to "what's the current state, what's been tried and didn't hold, and what are users still reporting". Reuse its per-source playbooks, run the investigators in parallel with the chat-history mining, and inherit its posture: one investigator per source, null results are findings, skip an unavailable MCP and say so. Fold what comes back into the brief. Skip this step only for pure activity recall with no named target ("what did I do this week"), where your own history and live state are the entire answer.
5. Verify against live state. Take the PRs, branches, and tickets that the mining and the sweep surfaced and check them with `jj` and `gh`. When the answer hinges on what an agent actually did (the tools it ran, files it read, errors it hit), read the full transcript, not just a trimmed local copy.
6. Write the brief to the contract below. Group by thread. Stay on the named topic.

## Output contract

Lead with the capsule, then the thread status, then the problems, then the next move. Deeper detail goes below or gets cut.

- **Capsule.** At most 5 bullets. What this work is and where it stands overall.
- **Threads.** One line each, prefixed with exactly one status tag: `[merged #N]`, `[open PR #N]`, `[in flight <branch>]`, `[verified, uncommitted]`, `[reverted #N]`, or `[planned, not started]`. A thread with no tag is not done yet, so tag it.
- **Problems.** At most 5, the recurring ones. Include the symptoms users keep reporting and any fix that shipped and was reverted, so the next attempt starts where the last one failed.
- **Next move.** The single most useful next action, concrete.

An adjacent feature or ticket stays out unless it blocks this one. When the capsule and thread lines outgrow a screen, cut detail before you cut threads. Write the brief through the **unslop** skill, cite chat findings by UUID and shared-record findings by their source (PR #, ticket ID, chat permalink, error-tracker issue), and sanitize private context before any public output.

**Reply:** the brief, to the contract above.

From davafons/dotfiles, MIT.

More from davafons/dotfiles