session-handoff
Skill2 starsChanged 5 months agoMITView on GitHub
Creates a safe en-US handoff markdown file from the current session, including the session timestamp, status, objective, expected result, work done, wins, failures, blockers, related sessions or agents, and next steps. Use when the user asks to create a session handoff or to end the session.
- Reads credentials
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 repository3 other files it gives its agents.
- local-md-mermaid-pdfSkill
- prepare-git-commitSkill
- list-session-filesSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 12 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 117 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Create a concise continuation note for the current session so another agent or future run can pick up the work quickly without reading the …
- Distinctive: line 58
Write in en-US only
- Distinctive: line 59
Never include secrets, environment variables, tokens, cookies, passwords, private URLs, private IDs, or other sensitive data
- Very specific: line 60
Never include raw .env values or anything that looks like a secret or credential
- Distinctive: line 61
Remove or redact any secret-like string before writing
- Very specific: line 62
Create the handoffs/ folder if it does not exist
- Distinctive: line 64
Use lowercase kebab-case for the filename
- Distinctive: line 65
If the objective is too ambiguous to name confidently, ask the user for a title before writing
- Distinctive: line 71
Read the current session and any relevant related sessions or sub-agent results.
- Distinctive: line 77
Remove or redact anything that looks like a secret or sensitive operational detail.
- Distinctive: line 79
Keep the handoff factual and compact.
- Distinctive: line 80
Prefer safe references to files, public links, and completed actions.
- Distinctive: line 127
Create the folder first if needed.
- Distinctive: line 154
No secrets or sensitive data appear in the handoff
“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
Overview
Create a concise continuation note for the current session so another agent or future run can pick up the work quickly without reading the full transcript.
When to Use
Use when
- The user asks to create a session handoff
- The user says session handoff or handoff da sessão
- The user asks to encerrar sessão and preserve context for continuation
Do not use when
- The user only wants a short summary with no continuation file
- The user asks for a public-facing recap instead of an internal handoff
- The task would reveal secrets, env vars, tokens, credentials, or other sensitive data that cannot be safely redacted
Inputs
- The current session transcript
- Any related sessions or agent interactions that affected the outcome
- The active workspace path for the current agent
- A short objective-derived title in lowercase kebab-case
- The session timestamp, if available
Outputs
- A markdown file at
<active-workspace>/handoffs/<objective-summary>.md - A handoff that is safe to share internally and free of sensitive data
Constraints
- Write in en-US only
- Never include secrets, environment variables, tokens, cookies, passwords, private URLs, private IDs, or other sensitive data
- Never include raw
.envvalues or anything that looks like a secret or credential - Remove or redact any secret-like string before writing
- Create the
handoffs/folder if it does not exist - Derive the filename from the session objective, not from sensitive content
- Use lowercase kebab-case for the filename
- If the objective is too ambiguous to name confidently, ask the user for a title before writing
Steps
1. Gather context
- Read the current session and any relevant related sessions or sub-agent results.
- Identify the objective, expected result, completed work, wins, failures, blockers, decisions, and next steps.
- Include other sessions or agents only when they add useful continuation context.
2. Sanitize
- Remove or redact anything that looks like a secret or sensitive operational detail.
- Replace sensitive references with neutral placeholders like
[redacted]. - Keep the handoff factual and compact.
- Prefer safe references to files, public links, and completed actions.
3. Choose the filename
- Build a short title from the session objective.
- Convert it to lowercase kebab-case.
- Examples:
optimize-linkedin-profile.mdsession-handoff.md
4. Write the handoff
Use this structure:
# Session Handoff: <short title>
## Session metadata
- Date/time: <timestamp>
- Status: <completed | partial | blocked>
## Objective
## Expected result
## What was done
## What worked
## What did not work yet
## Blockers and risks
## Decisions made
## Related sessions or agents
## Relevant files or references
## Next steps
## Notes5. Save the file
- Save the markdown file in the current agent workspace under
handoffs/. - Create the folder first if needed.
- Confirm the final file path to the user when the handoff is complete.
- Include a final output line like
Handoff saved to: /absolute/path/to/file.md. - Confirm the main decision points to the user.
Rationalization Traps
| Rationalization | Reality |
| The transcript is enough without a file | The skill exists to create a durable handoff artifact |
| A filename doesn't matter much | The filename is the retrieval handle for future continuation |
| Minor sensitive details are fine | Handoffs must be safe to share internally |
| Related sessions are optional in every case | They matter whenever they change the continuation plan |
Red Flags
- The file is written outside
handoffs/ - The filename is not lowercase kebab-case
- Secrets, env vars, tokens, cookies, passwords, or private IDs appear in the output
- The final reply does not include the file path
- The handoff omits session metadata, status, or next steps
Verification
- The file exists in
<active-workspace>/handoffs/ - The filename is lowercase kebab-case
- The content is in en-US
- No secrets or sensitive data appear in the handoff
- The summary includes the timestamp, status, objective, result, work done, wins, failures, blockers, related sessions or agents, next steps, and relevant references
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.

