Skip to content
Development
Skill

/recall

Reconstruct recent working context from local plans, memory, transcripts, and the shared record into a current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', or 'where did I leave off'.

BOOST
From plugin
khanelinix
34750 skills10 agents6 commands
Install
$ npx -y skills add khaneliman/khanelinix --skill recall --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/recall

Context preview

The summary Claude sees to decide when to auto-load this skill.

Reconstruct recent working context from local plans, memory, transcripts, and the shared record into a current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', or 'where did I leave off'.

SKILL.md

recall.SKILL.md
name: recall
description: "Reconstruct recent working context from local plans, memory, transcripts, and the shared record into a current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', or 'where did I leave off'."

Recall

Rebuild the user's recent working context before starting or resuming work. Hand back a capsule of where things stand now and what to do next.

Keep the sweep tight and on-topic. Read only what the in-scope threads need, then stop. Fan the heavy reading out to parallel read-only subagents. The main thread keeps their findings and the final brief.

Context lives in three records: durable local state (the plan and lessons already written down), chat history (what you did and decided), and the shared record (what happened around the same code under other names).

Steps

1. Classify, then route. One specific prior chat to resume needs no fan-out; open that chat and read it directly. Turning habits into a durable skill is `skill-creator` work. When the user already gave a full state capsule (paths, branch, the change), use it and skip the mining. 2. Check durable local state before mining transcripts. Read active planning-with-files artifacts (`task_plan.md`, `findings.md`, `progress.md`) and `okf-memory` durable notes. When they answer the question, verify against live state and write the brief. 3. 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). State the scope back. Never quietly turn "all" into "recent N". 4. Fan out across chat history. Read [chat-mining.md](references/chat-mining.md) for the store layout, the subagent instructions, and the findings schema. 5. Sweep the shared record when the topic names a feature, file, subsystem, area, or bug. Read [shared-record.md](references/shared-record.md) for the default rule, the `why` handoff, and the question to steer. 6. Verify against live state. A transcript or a stale ticket is history, not current truth. Check the PRs, branches, and tickets the mining and the sweep surfaced with `git` and `gh`. 7. Write the brief using the structure below. Group by thread. Stay on the named topic.

Brief structure

Lead with the capsule, then thread status, then problems, then the next move. Put deeper detail below or cut it.

  • **Capsule.** A short summary of what this work is and where it stands overall.
  • **Threads.** Give each relevant thread a concise current status and its

artifact or branch when available. Tags such as `[merged #N]`, `[open PR #N]`, `[in flight <branch>]`, `[verified, uncommitted]`, `[reverted #N]`, or `[planned, not started]` are examples, not an exhaustive vocabulary. Describe blocked, paused, partially verified, or uncertain work as it actually stands; do not force it into a completion state the evidence does not support.

  • **Problems.** Include relevant blockers, recurring problems, 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.

Leave an adjacent feature or ticket 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 session ID and shared-record findings by their source (PR number, ticket ID, chat permalink, error-tracker issue). Sanitize private context before any public output.

**Reply:** the concise, thread-oriented brief above.

Read more
Ships withkhanelinix

Run packages directly with: Or install from the packages output. For example:

Get the whole plugin

Other skills on khanelinix.