session-resume

Étoiles5

Forks0

Mis à jour5 juin 2026 à 03:14

Use when starting a session that should continue prior work — phrases like "resume the session", "pick up where we left off", "continue from where we stopped", "where were we", "load the continuation file". Consumes the .claude/CONTINUE.md written by session-save: verifies it against the repo, re-hydrates context, briefs, then acts. Not for mid-session checkpoints (use grounding) or recalling stored facts (use repo-memory).

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Source

uhstray-io

uhstray-io/huhhb

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name

session-resume

description

Session Resume

Overview

Consume the continuation file written by session-save: verify it against reality, re-hydrate full context, brief the user, then start on the recorded next action.

Core principle: trust the file's pointers, but verify its claims — the repo may have moved since the save.

Procedure

Locate .claude/CONTINUE.md. Also check the repo root for a legacy CONTINUE.md or HANDOFF.md. If none exists, say so plainly and fall back to git log plus repo memory — never invent a prior state.
Verify against reality. Compare the file's stamp and claims to the actual repo:
- Does the recorded branch still exist? Is it checked out?
- Has HEAD moved past the recorded sha? If so, summarize the intervening commits.
- Are the recorded dirty files still dirty? Stashes still present?
- Were the recorded PRs merged or closed in the interim? (gh pr view <n>)
- Staleness: warn if the save is more than 7 days old. Report any drift to the user before acting.
Re-hydrate fully:
- Load repo memory (.claude/memory/MEMORY.md and the relevant entries) if present.
- Re-read the 1–3 links under "How to resume".
- Re-run the baseline command recorded under "Environment & commands"; report pass/fail either way.
Brief the user in a few lines: where we were · what changed since · the next action.
Delete the continuation file — only after the brief is delivered and verification passed. If verification failed or the drift is severe, leave the file in place and explain why.
Act. Start on the recorded next action.

Common mistakes

Acting on the next action before reporting drift — the user decides what drift means.
Deleting the file when verification failed — a failed resume must keep its source.
Pretending to resume when no continuation file exists.
Re-reading the whole codebase instead of trusting the file's pointers.
Skipping the baseline command — "it passed last session" is not evidence it passes now.

Plus depuis ce dépôt

même dépôt

repo-kickstart

uhstray-io/huhhb

Use when bootstrapping a repository — greenfield or brownfield — into Uhstray's standard development conventions, OpenSpec, and the two-store memory setup. Idempotent and non-destructive: safe to re-run, never overwrites existing docs. Triggers on "repo kickstart", "bootstrap this repo", "set up our conventions", "conform this repo", "initialize plans/openspec/memory", "initialize this repo for openspec and memory", "set up two-store memory here", "index this repo and create its memory bank".

2026-08-025

memory-onboarding

uhstray-io/huhhb

Use when checking or setting up the four-strata memory system on this machine and in the current project — "is my memory set up right", "memory onboarding", "set up memory", "check my memory setup", after a fresh machine/repo, when repo-kickstart or buhhdy's preflight reports memory degradation, or when .claude/memory / MemPalace / evolve looks misconfigured.

2026-08-025

pr-shepherd

uhstray-io/huhhb

Use when any orchestrating agent's development workflow — buhhdy's Workflow 2 is the canonical caller — has open PRs that need driving from creation through merge and cleanup — the terminal step once PRs are open. Triggers on "shepherd this PR", "drive the PR to merge", "babysit the PRs", "monitor the PR to merge", and post-merge close-out (close linked issues, archive the change, remove the worktree, janitor stale branches in the orchestrator's own prefix (buhhdy/* canonical)). Also load to verify PR-lifecycle preconditions (branch protection, CodeRabbit) before shepherding.

2026-08-025

repo-memory

uhstray-io/huhhb

Use when the user says "remember", "don't forget", "save that", "keep that in mind", "recall", "what do we know about", "look that up", or any request to persist or retrieve project knowledge — stores memories in .claude/memory/ using the Claude Code memory format, committed to git so the whole team shares context.

2026-08-025

core-workflows

uhstray-io/huhhb

Use when starting new planning/research on a project or picking up development against an existing plan — buhhdy's two standard, repeatable sequences: Planning & Research (fresh problem to a validated plan — an OpenSpec change where the repo has adopted the conventions — plus issues) and Development (fanout, audit, docs, and pr-shepherd).

2026-07-215

routing-guide

uhstray-io/huhhb

Reference skill for buhhdy's provider routing logic — the decision tree, model tier table, per-provider strengths, skill-to-provider affinity, and cross-review pairings. Load when reasoning about which provider to use and why, or when a task doesn't clearly match the main routing tree.

2026-07-215

name

session-resume

description

Session Resume

Overview

Consume the continuation file written by session-save: verify it against reality, re-hydrate full context, brief the user, then start on the recorded next action.

Core principle: trust the file's pointers, but verify its claims — the repo may have moved since the save.

Procedure

Locate .claude/CONTINUE.md. Also check the repo root for a legacy CONTINUE.md or HANDOFF.md. If none exists, say so plainly and fall back to git log plus repo memory — never invent a prior state.
Verify against reality. Compare the file's stamp and claims to the actual repo:
- Does the recorded branch still exist? Is it checked out?
- Has HEAD moved past the recorded sha? If so, summarize the intervening commits.
- Are the recorded dirty files still dirty? Stashes still present?
- Were the recorded PRs merged or closed in the interim? (gh pr view <n>)
- Staleness: warn if the save is more than 7 days old. Report any drift to the user before acting.
Re-hydrate fully:
- Load repo memory (.claude/memory/MEMORY.md and the relevant entries) if present.
- Re-read the 1–3 links under "How to resume".
- Re-run the baseline command recorded under "Environment & commands"; report pass/fail either way.
Brief the user in a few lines: where we were · what changed since · the next action.
Delete the continuation file — only after the brief is delivered and verification passed. If verification failed or the drift is severe, leave the file in place and explain why.
Act. Start on the recorded next action.

Common mistakes

Acting on the next action before reporting drift — the user decides what drift means.
Deleting the file when verification failed — a failed resume must keep its source.
Pretending to resume when no continuation file exists.
Re-reading the whole codebase instead of trusting the file's pointers.
Skipping the baseline command — "it passed last session" is not evidence it passes now.