session-handoff
Skill0 starsChanged 4 months agoMITView on GitHub
Produce a tight handoff summary so the user can clear the current session and resume in a fresh one without losing context. Use whenever the user says 'handoff', 'session handoff', 'wrap this up so I can clear', 'I'm running out of context', 'summarize for a new session', 'before I /clear', 'the context is getting big', or any variation that signals they want to dump current state and start clean. Faster than a full auto-compaction, preserves the cache better than continuing into a long session, and lets the next session start with a focused prefix.
139 other projects use a version of this.
Adopted by
Most recently taken up by
- aktsmm/Agent-Skillstheir own version, first seen Nov 8, 2026
- wanshuiyin/HERO-Anti-OverDefensetheir own version, first seen Nov 8, 2026
- alapha888/session-handoff-kittheir own version, first seen Nov 8, 2026
- zedarvates/frugal-skillstheir own version, first seen Nov 8, 2026
- Sirius-Ji/dsh-disciplinary-skills-for-greenhandstheir own version, first seen Nov 8, 2026
- maideps/ai-harness-frameworktheir own version, first seen Nov 8, 2026
Used with
Projects with it also use ascii-diagram, research-fleet and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SethGammonSkillascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
Also in 4 projects that use this
SethGammonSkillresearch-fleet
Parallel research using Fleet wave mechanics. Spawns multiple scout agents, each investigating a different angle of the same question. Findings are compressed between waves. Produces a unified research brief from multiple independent perspectives.
Also in 3 projects that use this
vicoa-aiSkilllive-preview
Start a local app in the current user project, expose it through a tunnel, and return preview details in structured Markdown. Use when the user asks for a preview URL, public URL, shareable localhost, mobile/web preview, or tunnel setup.
Also in 4 projects that use this
botlearn-aiSkilldoc-gen
Also in 4 projects that use this
flyingobsidianSkillterminology
Read a codebase, find terminology, create/update definitions into a markdown document.
Also in 3 projects that use this
Dizzy-TenSkillbug-diagnosis
Diagnose bugs and product issues without modifying code. Use when the user explicitly invokes $bug-diagnosis or asks for diagnosis, root-cause analysis, issue classification, or fix strategy for code bugs, failing tests, configuration/dependency problems, deployment issues, performance regressions, data anomalies, or frontend/user-experience problems described through screenshots, annotations, logs, errors, or natural-language reports. Prioritize analysis and recommendations only; do not edit files.
Also in 3 projects that use this
- +1 more from SethGammon
Other versions139 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 139
- rohitg00/pro-workflow★ 2.9ksame name
- SethGammon/Citadel★ 927same name
- wanshuiyin/HERO-Anti-OverDefense★ 805same name
- OneWave-AI/claude-skills★ 378same name
- ai-analyst-lab/ai-analyst★ 304same name
- entireio/skills★ 239same name
- Innei/SKILL★ 92same name
- yuzushi-dev/session-handoff★ 67same name
- Hive-Academy/ptah-extension★ 34same name
- Hive-Academy/PtahCode★ 34same name
129 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- construct-validity-screen/CLAUDE.mdCLAUDE.md
- role-bleed-probe/CLAUDE.mdCLAUDE.md
- adversarial-hardenSkill
- ai-proofSkill
- construct-validity-screenSkill
- divergent-solveSkill
- forgeSkill
- gate-canariesSkill
- grill-meSkill
- heavy-task-plannerSkill
- overnightSkill
- parallel-researchSkill
- premise-gateSkill
- prompt-architectSkill
- role-bleed-probeSkill
- scope-firstSkill
- stakes-gateSkill
- voice-profileSkill
- witnessSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 117 edited versions we read keep these.
5
Distinctive
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
- Distinctive: line 14
Write the summary in this exact structure (skip sections that don't apply):
- Distinctive: line 43
One screen max: If it spills past ~40 lines, you're padding.
- Distinctive: line 45
Don't re-explain what the project does: if the project files already say it.
- Distinctive: line 51
After writing the handoff, tell the user:
- Distinctive: line 56
Do not write any files. The handoff is a chat message, not a file — writing it as a file would itself add to the context you're trying to …
“Common” is measured: kept by at least 6 in 10 of the 117 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Session Handoff
The user wants to close out the current session, start fresh, and pick up where they left off without losing momentum. Your job: produce a single self-contained markdown block they can paste into the next session as the first message.
A good handoff is shorter than an automatic compaction, sharper, and easier to cache — because the next session reads it once as a single message instead of replaying a long history.
What to include
Write the summary in this exact structure (skip sections that don't apply):
# Session handoff — <one-line topic>
## What we're doing
<2-4 sentence framing of the project / task and why>
## State of play
- <bullet of what's been decided>
- <bullet of what's been built / written / changed>
- <bullet of any constraint or preference the user has expressed this session>
## Key files / artifacts
- `<path>` — <one line on what it is and its current state>
- `<path>` — <one line>
## Open decisions
- <thing the user hasn't decided yet> — <options on the table>
## Next step
<the single most important next action when the new session opens>
## Quick context for the new session
<anything else the next session needs to know that isn't obvious from the files — e.g. "the draft has already been voice-checked", "the user prefers no emoji", "tests are green as of the last run">Rules
- One screen max. If it spills past ~40 lines, you're padding. Cut.
- Concrete file paths and decisions, not vibes. "We discussed the structure" is useless. "Decided 5 sections, intro is drafted in
outputs/draft.md" is useful. - Don't re-explain what the project does if the project files already say it. Point at them.
- Preserve user-stated preferences from this session — these are the things that would otherwise vanish when the context is cleared.
- No filler — no "great progress!", no recap of what they already know they did.
Output
After writing the handoff, tell the user:
- Copy the block above.
- Clear the session (
/clear, or open a fresh session). - Paste it as the first message.
Do not write any files. The handoff is a chat message, not a file — writing it as a file would itself add to the context you're trying to keep small.
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
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.

