task-reconstruction
Use when tasks need to be reconstructed after a session fork, when TaskList returns empty but conversation history contains task references, or when user asks…
Skill by luutuankiet
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/luutuankiet-task-reconstruction
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
Use cases: productivity
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/task-reconstruction
What's inside
- Skill name
task-reconstruction- Description
- Use when tasks need to be reconstructed after a session fork, when TaskList returns empty but conversation history contains task references, or when user asks about current tasks, todos, or work items and the task list appears stale or empty. Also triggers on "reconstruct tasks", "rebuild tasks", "what are our todos", "what tasks do we have", or "where were we".
- License
- unknown
- Instructions
- 34 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from luutuankiet/context-lab
- 0.578score
codebase-map
luutuankiet
Where behaviour lives in this repo — a per-area map of which files and line ranges own what, so you can open the right file instead of searching for it.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
context-lab-audit
luutuankiet
Audit this host against what the context-lab repository intends — the installed plugin, the owned settings keys, the statusline dispatcher and its…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bq-tile-verification
luutuankiet
Autonomous BQ verification of Tableau tile parity.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
dashboard-merge
luutuankiet
Merge multiple individual Looker LookML dashboards into a single tabbed dashboard.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
docs-with-mermaid
luutuankiet
Create excellent technical documentation with Mermaid diagrams.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
progress-check
luutuankiet
Session navigator for Tableau-to-Looker migrations.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
proxy-tools
luutuankiet
Discover and call tools through an mcpproxy-go MCP proxy — the retrieve/call pipeline, read vs destructive variants, truncated-response handling, and upstream…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
twb-deep-extraction
luutuankiet
Autonomous TWB XML extraction.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
handoff-loop
luutuankiet
Use this when user shows intention that you work autonomously without human in the loop.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
webfetch-fallback
luutuankiet
Use when WebFetch fails, returns an error, times out, or returns incomplete/blocked content, or fetching URLs that are known to be geo-restricted.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
long-running-jobs
luutuankiet
Run and track remote jobs that could outlast the 1-hour proxy deadline — backgrounding, watcher subagents, ScheduleWakeup pacing, and completion sentinels.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
mcp-daemon
luutuankiet
MCP daemon API reference and troubleshooting.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 10
- Last commit (this folder)
- Aug 17, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/luutuankiet/context-lab
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from luutuankiet
- 0.578score
codebase-map
luutuankiet
Where behaviour lives in this repo — a per-area map of which files and line ranges own what, so you can open the right file instead of searching for it.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
context-lab-audit
luutuankiet
Audit this host against what the context-lab repository intends — the installed plugin, the owned settings keys, the statusline dispatcher and its…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
dashboard-merge
luutuankiet
Merge multiple individual Looker LookML dashboards into a single tabbed dashboard.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bq-tile-verification
luutuankiet
Autonomous BQ verification of Tableau tile parity.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
webfetch-fallback
luutuankiet
Use when WebFetch fails, returns an error, times out, or returns incomplete/blocked content, or fetching URLs that are known to be geo-restricted.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
docs-with-mermaid
luutuankiet
Create excellent technical documentation with Mermaid diagrams.
SkillBFreshness: B★ 1Claude Code +9
Cite this page
task-reconstruction skill. Agent Mart. https://agentmart.dev/skills/luutuankiet-task-reconstruction (last updated 2026-10-24)