AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

One Update Task

skill-onehorizonai-skills-one-update-task · by onehorizonai

Apply a direct update to known One Horizon work when the target and action are clear, such as changing status, reassigning, adding a comment, or reacting to a comment. Prefer one-task-management for ambiguous or multi-step operational requests. Requires One Horizon MCP.

No reviews yet
0 installs
29 views
0.0% view→install

Install

$ agentstack add skill-onehorizonai-skills-one-update-task

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-onehorizonai-skills-one-update-task)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of One Update Task? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Update Task

Update existing One Horizon work or interact with its comments. Choose the MCP tool that matches the work type and action.

Shared rules

  • Never modify task descriptions to record progress. Use comments instead.
  • When changing status (e.g. to Completed), add a comment explaining what changed and why.
  • Resolve IDs first with one-list-work or get-task-details when needed.
  • When editing an initiative description, use patch-document with workspaceId, taskId set to the initiative ID, and precise ops; the server resolves or creates the linked content document automatically.
  • Prefer replace_text, insert_before, insert_after, and delete_text over rewriting the entire description.
  • Use update-initiative only for initiative metadata: title, status, assigneeIds, teamIds, taxonomyLabelIds, and parentInitiativeId.
  • If both description and metadata change, call patch-document(taskId=initiativeId, ...) first, then update-initiative(...). If you need the refreshed full initiative, call get-task-details after the mutations.
  • If a patch fails because the target or anchor is stale or missing, call get-task-details, then retry with corrected ops.

By work type

Todo

Call update-todo:

update-todo({
  "taskId": "",
  "workspaceId": "",
  "status": "Completed"
})

Then add a comment with what changed:

add-task-comment({
  "taskId": "",
  "workspaceId": "",
  "source": "skill",
  "content": "**Changes**\n- What changed: Added retry backoff and idempotency guard\n- Why: Prevent duplicate processing on transient failures"
})

Roadmap initiative

Use patch-document for initiative description edits and update-initiative for metadata.

Description edit only:

patch-document({
  "workspaceId": "",
  "taskId": "",
  "ops": [
    {
      "kind": "replace_text",
      "target": "EMEA pilot",
      "replacement": "EU launch"
    }
  ]
})

Description plus metadata:

patch-document({
  "workspaceId": "",
  "taskId": "tsk_123",
  "ops": [
    {
      "kind": "insert_after",
      "anchor": "### Rollout",
      "text": "\n- Roll out to two design partners first.\n"
    }
  ]
})
update-initiative({
  "initiativeId": "tsk_123",
  "workspaceId": "",
  "status": "In Progress"
})

Metadata only:

update-initiative({
  "initiativeId": "",
  "workspaceId": "",
  "status": "In Progress",
  "assigneeIds": [""],
  "teamIds": [""]
})

Then add a comment:

add-task-comment({
  "taskId": "",
  "workspaceId": "",
  "source": "skill",
  "content": "**Changes**\n- What changed: Implemented OAuth callback and token persistence\n- Why: Enable first end-to-end auth handshake"
})

Bug

Call update-bug. When writing back a fix, add root cause, code changes, and why as a comment:

update-bug({
  "taskId": "",
  "workspaceId": "",
  "status": "In Progress",
  "assigneeIds": [""],
  "teamIds": [""]
})
add-task-comment({
  "taskId": "",
  "workspaceId": "",
  "source": "skill",
  "content": "**Changes**\n- What changed: Fixed stale cache key invalidation\n- Why: Totals were computed with outdated cache entries"
})

Feature request

Call update-feature-request:

update-feature-request({
  "taskId": "",
  "workspaceId": "",
  "status": "Planned",
  "assigneeIds": [""],
  "teamIds": [""]
})
add-task-comment({
  "taskId": "",
  "workspaceId": "",
  "source": "skill",
  "content": "## Update\n- Summary: Scoped implementation approach and acceptance criteria"
})

Comment formats

Delivery update (code shipped / fix completed):

**Changes**
- What changed: 
- Why: 

Research or planning update (no implementation delivered):

## Update
- Summary: 

List comments

list-task-comments({
  "taskId": "",
  "workspaceId": ""
})

React to a comment

Toggles an emoji reaction (adds if missing, removes if already present):

toggle-task-comment-reaction({
  "taskId": "",
  "workspaceId": "",
  "commentId": "",
  "emoji": "👍"
})

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.