Skip to content
Agentmart
Submit a tool

scrum-activity

Append work-log entries or authored comments to Scrum Studio tasks and read their paginated activity history with minimal context.

Skill by martiin3d

IndexedMIT
Write a review

Chalk Labs

Need help deploying scrum-activity?

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.

Book a call

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/martiin3d-scrum-activity

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.

We use your email only for this newsletter. Privacy

About

Append work-log entries or authored comments to Scrum Studio tasks and read their paginated activity history with minimal context.

No 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/scrum-activity

What's inside

Skill name
scrum-activity
Description
Append work-log entries or authored comments to Scrum Studio tasks and read their paginated activity history with minimal context.
License
MIT
Instructions
15 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Use the scrum-studio MCP, the intended project, and a registered actor ID. If given a task code, resolve it with `task_get(project,code)` once. Keep stored entries in English.

- Record actual work with `task_activity(project,id,actor,token,text,kind="work")`. State the meaningful change, evidence/result, or next step in at most 2000 characters. Use concise entries per milestone, not per tool call or thought.
- Prefer `task_update(...,log="Implemented X; relevant check passed")` when also changing status, category or checklist. This records work in the same transaction and saves a call. `task_create` also accepts actor+log when initial context is useful.
- Use `task_activity(...,kind="comment",text)` for questions, decisions or human feedback. Comments require a registered actor and can be added while another worker holds the lock; they do not extend that worker's lease. Work-log writes need the claiming session's token on active locks; reclaim an expired In Progress task before recording work.
- Author IDs and UTC timestamps are stored automatically. Never fabricate attribution or include private lock tokens in text. Append corrections rather than rewriting history. System-generated creation/state/lock/resolution events already exist; do not duplicate them manually.
- History is excluded from `next_work`, `task_get` and `snapshot`. Read `task_activity(project,id)` only when needed: the default is the latest 20 entries, max 50. Use `before=oldest` for older pages, or `after=latest` for new entries. Do not supply both. Reuse cursors; never reread unchanged history or poll while idle.

Task history records progress within a task. Project Review notes still hold human handoffs; session Retrospective notes still hold process improvements.

Use the web Updates & comments section or task_activity for progress after creation. Keep the original description and acceptance criteria as the task contract. If scope actually changes, edit the contract and record why in a separate authored update.

Prefer the task continuity summary over reconstructing history on resume. Update it only for meaningful handoff/context changes through task_update(continuity,actor,token); max2000 characters covering result, relevant files, verification and next step. It is authored in activity and exported. continuity_stale warns of changed task context; do not treat it as current without checking. Use version_seen for unchanged task reads and incremental activity cursors only when history is necessary.

From martiin3d/scrumstudio, MIT.

More from martiin3d/scrumstudio

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 19, 2026 (11 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from martiin3d

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 scrum-activity 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying scrum-activity?

CallGet help
Cite this page

scrum-activity skill. Agent Mart. https://agentmart.dev/skills/martiin3d-scrum-activity (last updated 2026-10-24)