work-management
Coordinate a substantial assignment, progress update or session handoff with a private working plan and shared issue/PR; preserve acceptance, feedback…
Skill by atstaeff
Chalk Labs
Need help deploying work-management?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/atstaeff-work-management
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 and code. Checked Oct 26, 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/work-management
What's inside
- Skill name
work-management- Description
- Coordinate a substantial assignment, progress update or session handoff with a private working plan and shared issue/PR; preserve acceptance, feedback, evidence and ownership. Skip separate planning records for clear small edits.
- License
- MIT
- Instructions
- 33 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- openai.yaml · agents/
- progress-sync.md · references/
SKILL.md (first lines)
# Work Management 1. Reuse applicable project/process instructions and locate the actual assignment. Keep scope, acceptance, dependencies and progress at that shared work home. Record collaborative execution steps there when others depend on them or the project requires a shared plan. Use the designated plan home when one exists; avoid a second tracker. Optional personal steps and experiments stay in the permitted private Second Brain. If it is unavailable, label personal planning unsaved and continue authorized work. Missing shared access means a proposed unapplied update, not invented synchronization. 2. State outcome, scope, observable acceptance, accountable human, bounded writer scope, dependencies and integration owner. Pull a complete increment within review capacity. Coordinate shared contracts and overlapping writes before parallel implementation. 3. Preserve required plan approval and feedback for the current revision. Proceed with routine reversible choices in scope; resolve consequential conflicts with their owner. A proposal does not revoke an accepted decision. Record significant reasons as they arise. 4. Update the same assignment after material progress or a blocker. Lead with outcome, evidence, blocker/owner and next action. Preserve human wording; reread/version-check before writes. After a timeout, inspect existing effects before retrying. 5. Link checks to criteria and tested revisions. Reassess affected evidence/approval after material changes. Distinguish verified, accepted, integrated, deployed and measured benefit; cancelled or duplicate work is not delivery. Keep blocked flow position visible. 6. Before pausing, update private resume state and shared result/evidence at their proper homes. Preserve source revisions, blockers, pending writes and one next action. On resuming, compare current sources with that handoff. Keep accepted reasons and reusable knowledge at their project-owned homes. Keep private paths, vault links and raw personal plans out of shared artifacts. An authorized, sanitized plan extract may support required review; record the reviewed revision and actual feedback at the designated review home. Share the coordination facts collaborators need without copying private scratch work. ## Load only when needed - [Plan review](../../../toolkit/PLAN-REVIEW.md): when the project requires approval. - [Recovery contract](../../../toolkit/CONTEXT-RECOVERY.md): interruption, conflicting or stale state. - [Local records](../../../toolkit/WORK-RECORDS.md): only for the optional Markdown workbench. - [Progress examples](references/progress-sync.md): audience-specific reporting.
From atstaeff/ai-agents, MIT.
More from atstaeff/ai-agents
- 0.606score
product-discovery
atstaeff
Clarify a product or feature with uncertain user value, compare minimal solutions and define a measurable experiment or delivery slice.
SkillAFreshness: A★ 3Claude Code +9 - 0.603score
project-management
atstaeff
Organize delivery, technical debt or release work without excessive process overhead.
SkillAFreshness: A★ 3Claude Code +9 - 0.603score
architecture-planning
atstaeff
Produce a concise architecture plan with boundaries, alternatives, delivery steps and verification.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
repository-contribution
atstaeff
Resolve contribution rules and source ownership for an unfamiliar repository or changed process before substantial work.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
pr-crafting
atstaeff
Prepare a reviewable pull request description, scope and validation evidence for a code change.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
technical-debt
atstaeff
Assess a maintainability problem and prioritize a safe, incremental repayment plan.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
clean-code
atstaeff
Improve readability and changeability of code while preserving behavior and project conventions.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
cloud-native
atstaeff
Plan or review cloud deployment, managed services, runtime configuration and operational resilience.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
creative-app-patterns
atstaeff
Implement document models, undo/redo, real-time feedback or media processing in a creative application.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
design-patterns
atstaeff
Choose or simplify a design pattern at a real variation, lifecycle or integration boundary.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
devops-cicd
atstaeff
Build or repair CI, deployment, release, rollback or reproducible development workflows.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
game-architecture
atstaeff
Structure an existing or new game for clear state ownership, engine integration and testable mechanics.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/atstaeff/ai-agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from atstaeff
- 0.606score
product-discovery
atstaeff
Clarify a product or feature with uncertain user value, compare minimal solutions and define a measurable experiment or delivery slice.
SkillAFreshness: A★ 3Claude Code +9 - 0.603score
project-management
atstaeff
Organize delivery, technical debt or release work without excessive process overhead.
SkillAFreshness: A★ 3Claude Code +9 - 0.603score
architecture-planning
atstaeff
Produce a concise architecture plan with boundaries, alternatives, delivery steps and verification.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
repository-contribution
atstaeff
Resolve contribution rules and source ownership for an unfamiliar repository or changed process before substantial work.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
pr-crafting
atstaeff
Prepare a reviewable pull request description, scope and validation evidence for a code change.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
domain-driven-design
atstaeff
Model business rules, aggregates, bounded contexts or domain terminology in an existing or new application.
SkillAFreshness: A★ 3Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get work-management running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
work-management skill. Agent Mart. https://agentmart.dev/skills/atstaeff-work-management (last updated 2026-10-24)