project-tasks
Maintains shared human-agent continuation briefs in the task surface explicitly configured in applicable AGENTS.md (including tasks/backlog/ for deferred…
Skill by chingfhen
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/chingfhen-project-tasks
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: writing, productivity, agent-building
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/project-tasks
What's inside
- Skill name
project-tasks- Description
- Maintains shared human-agent continuation briefs in the task surface explicitly configured in applicable AGENTS.md (including tasks/backlog/ for deferred work), so unfinished discussion, planning, investigation, implementation, or validation can continue without the prior conversation. Load before creating, editing, moving, deleting, or managing task files; not needed merely to read an explicitly identified task file. Rewrites tasks toward current truth while preserving permission boundaries, consequential decisions, blockers, verification state, and the next permitted action.
- License
- unknown
- Instructions
- 342 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 chingfhen/agent-core
- 0.587score
workspace-setup
chingfhen
Establish or refresh the workspace resource map and personal workflow in a managed section in root AGENTS.md.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
knowledge-base
chingfhen
Preserve and retrieve reusable context in a Markdown knowledge base.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
agent-lessons
chingfhen
On explicit request, learn from the current agent work or conversation and autonomously maintain a concise Durable Agent Lessons section in applicable…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
engineering
chingfhen
Implements, debugs, fixes, refactors, and reviews code.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
human-unblock
chingfhen
Use during execution when progress is blocked, or likely to stall, on an action or information only the human can provide—for example access approval…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
project-docs
chingfhen
Maintains settled project understanding in the documentation surface explicitly configured in applicable AGENTS.md, and stable agent behavior in explicitly…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
learning
chingfhen
Help a human learn or understand a topic, technical system, code change, error, agent output, or source material.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
manage-python-env
chingfhen
Manage and execute Python through reusable, independent uv purpose projects under the Python Environment Root explicitly configured in AGENTS.md.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
readability
chingfhen
Improve human readability for readability-focused requests: rewrite a hard-to-read response or document, review its readability, or make a new answer or…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
reasoned-advocacy
chingfhen
Evaluate, strengthen, and communicate a position through sound reasoning, evidence, alternatives, and counterarguments.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
ml-architecture-review
chingfhen
Perform a decision-focused ML architecture investigation with evidence, alternatives, trade-offs, risks, and a leading recommendation.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
document-text-extraction
chingfhen
Extract text from a specified PDF or image into local temporary Markdown and a quality report only when the human explicitly requests extraction.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/chingfhen/agent-core
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from chingfhen
- 0.587score
workspace-setup
chingfhen
Establish or refresh the workspace resource map and personal workflow in a managed section in root AGENTS.md.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
knowledge-base
chingfhen
Preserve and retrieve reusable context in a Markdown knowledge base.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
project-docs
chingfhen
Maintains settled project understanding in the documentation surface explicitly configured in applicable AGENTS.md, and stable agent behavior in explicitly…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
human-unblock
chingfhen
Use during execution when progress is blocked, or likely to stall, on an action or information only the human can provide—for example access approval…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
engineering
chingfhen
Implements, debugs, fixes, refactors, and reviews code.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
agent-lessons
chingfhen
On explicit request, learn from the current agent work or conversation and autonomously maintain a concise Durable Agent Lessons section in applicable…
SkillAFreshness: A★ 1Claude Code +9
Cite this page
project-tasks skill. Agent Mart. https://agentmart.dev/skills/chingfhen-project-tasks (last updated 2026-10-24)