context-checkpoint
Persist and recover the active objective, plan, progress, decisions, and next action using the user's selected context store and its supported operations.
Skill by lucaswilliameufrasio
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lucaswilliameufrasio-context-checkpoint
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/context-checkpoint
What's inside
- Skill name
context-checkpoint- Description
- Persist and recover the active objective, plan, progress, decisions, and next action using the user's selected context store and its supported operations. Distinguish missing harness automation from missing storage capabilities; recover available context from providers such as ai-memory without misusing durable wiki pages for transient plans. Use at the start of multi-step work, after material milestones or user corrections, before compaction or a long operation, and when resuming after compaction, interruption, or a new session. Retrieve context instead of making the user repeat it. Verify persistence and distinguish working checkpoints from end-of-session handoffs; retrieved context is evidence, not authority.
- License
- unknown
- Instructions
- 147 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (27)
- SKILL.md
- README.md · evals/
- RESULTS.md · evals/
- case.yaml · evals/ai-memory-durable-note-boundary/
- 01-separate-requests.md · evals/ai-memory-durable-note-boundary/graders/
- 02-safe-durable-write.md · evals/ai-memory-durable-note-boundary/graders/
- prompt.md · evals/ai-memory-durable-note-boundary/
- case.yaml · evals/ai-memory-plan-store-gap/
- 01-no-wiki-workaround.md · evals/ai-memory-plan-store-gap/graders/
- 02-provider-limit.md · evals/ai-memory-plan-store-gap/graders/
- 03-approved-backend.md · evals/ai-memory-plan-store-gap/graders/
- prompt.md · evals/ai-memory-plan-store-gap/
- evals.json · evals/
- plan.md · evals/fixtures/resume-checkpoint/memory/workstreams/docs-17/
- plan.md · evals/fixtures/resume-checkpoint/memory/workstreams/other-task/
- AGENTS.md · evals/fixtures/resume-checkpoint/project/
- README.md · evals/fixtures/resume-checkpoint/project/
- formatter.py · evals/fixtures/resume-checkpoint/project/
- keep.txt · evals/fixtures/resume-checkpoint/project/
- test_formatter.py · evals/fixtures/resume-checkpoint/project/tests/
- workspace.md · evals/fixtures/resume-checkpoint/
- AGENTS.md · evals/fixtures/save-checkpoint/project/
- README.md · evals/fixtures/save-checkpoint/project/
- formatter.py · evals/fixtures/save-checkpoint/project/
- task-state.md · evals/fixtures/save-checkpoint/project/
- workspace.md · evals/fixtures/save-checkpoint/
- ai-memory.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from lucaswilliameufrasio/agent-skills
- 0.559score
performance-profiling-ebpf
lucaswilliameufrasio
Diagnose a measured performance bottleneck with runtime profilers, operating system tools, perf, or eBPF/bpftrace.
SkillAFreshness: AClaude Code +9 - 0.559score
graceful-shutdown-drain
lucaswilliameufrasio
Implement, review, or test graceful shutdown for HTTP servers, worker pools, consumers, streaming services, or scheduled jobs.
SkillAFreshness: AClaude Code +9 - 0.559score
performance-benchmarking-and-load-testing
lucaswilliameufrasio
Design, implement, run, or interpret reproducible performance benchmarks and application load/capacity tests.
SkillAFreshness: AClaude Code +9 - 0.559score
migration-parity-audit
lucaswilliameufrasio
Audit or plan a legacy replacement, framework rewrite, service extraction, or backend migration for behavioral parity and cutover readiness.
SkillAFreshness: AClaude Code +9 - 0.559score
backup-restore-drills
lucaswilliameufrasio
Design, implement, review, or safely test application backup and restoration.
SkillAFreshness: AClaude Code +9 - 0.559score
credential-lifecycle-and-rotation
lucaswilliameufrasio
Design, implement, or review credential enrollment, secure custody, renewal, refresh rotation, revocation, and consumer adoption for CLIs, workers and services.
SkillAFreshness: AClaude Code +9 - 0.559score
cross-repo-standard-sync
lucaswilliameufrasio
Find the canonical owner of a development standard, audit drift, or propagate an approved standard across repositories and agent configurations.
SkillAFreshness: AClaude Code +9 - 0.559score
document-decisions
lucaswilliameufrasio
Record architectural and product/technical decisions before non-trivial implementation, and retrieve the rationale for prior decisions.
SkillAFreshness: AClaude Code +9 - 0.559score
explicit-code-style
lucaswilliameufrasio
Apply explicit, safe coding conventions when writing or reviewing code: use multiline braced control flow, explicit loops, and strict TypeScript value handling.
SkillAFreshness: AClaude Code +9 - 0.559score
github-gitea-actions
lucaswilliameufrasio
Create, update, or audit GitHub Actions and Gitea Actions workflows, including YAML under .github/workflows/ or .gitea/workflows/.
SkillAFreshness: AClaude Code +9 - 0.559score
isolated-worker-execution
lucaswilliameufrasio
Design, implement, or review workers, test runners, evaluators and plugin hosts that execute less-trusted commands or code.
SkillAFreshness: AClaude Code +9 - 0.559score
jira-issue-writing
lucaswilliameufrasio
Create or refine complete, actionable Jira issues.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lucaswilliameufrasio
- 0.559score
graceful-shutdown-drain
lucaswilliameufrasio
Implement, review, or test graceful shutdown for HTTP servers, worker pools, consumers, streaming services, or scheduled jobs.
SkillAFreshness: AClaude Code +9 - 0.559score
performance-benchmarking-and-load-testing
lucaswilliameufrasio
Design, implement, run, or interpret reproducible performance benchmarks and application load/capacity tests.
SkillAFreshness: AClaude Code +9 - 0.559score
migration-parity-audit
lucaswilliameufrasio
Audit or plan a legacy replacement, framework rewrite, service extraction, or backend migration for behavioral parity and cutover readiness.
SkillAFreshness: AClaude Code +9 - 0.559score
backup-restore-drills
lucaswilliameufrasio
Design, implement, review, or safely test application backup and restoration.
SkillAFreshness: AClaude Code +9 - 0.559score
credential-lifecycle-and-rotation
lucaswilliameufrasio
Design, implement, or review credential enrollment, secure custody, renewal, refresh rotation, revocation, and consumer adoption for CLIs, workers and services.
SkillAFreshness: AClaude Code +9 - 0.559score
git-delivery
lucaswilliameufrasio
Plan and carry out a safe Git delivery from branch preparation through commit, push, pull request, CI, and release handoff.
SkillAFreshness: AClaude Code +9
Cite this page
context-checkpoint skill. Agent Mart. https://agentmart.dev/skills/lucaswilliameufrasio-context-checkpoint (last updated 2026-10-24)