agentleFS
claudio-atilano-uviclaudio-atilano-uvi/claude-skills/tempo/SKILL.md

tempo

Skill0 starsChanged 4 months agoMITView on GitHub

Log and manage Tempo timesheets via the Jira worklog API plus the Tempo Cloud API for the Schedule (work) attribute. Trigger when: user mentions tempo, timesheets, worklogs, logging time, hours, time tracking, schedule attribute, overtime. Also trigger for: "log my hours", "fill timesheet", "mark time", "what did I log", "submit timesheet", "set schedule to regular hours".

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. grafana/skills★ 302same name
    2. evrenayaz/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify with a follow-up GET:

    line 97
  2. Distinctive:

    After all worklogs are posted, re-list the week's worklogs and confirm:

    line 107
  3. Distinctive:

    Every worklog has the Schedule attribute set

    line 109
  4. Distinctive:

    Delete from Tempo (which cascades to Jira):

    line 131

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Tempo Timesheet Management

Logging time is a two-system job: create the worklog through the Jira REST API, then set the Tempo Schedule (work attribute) through the Tempo Cloud API. The Tempo plugin uses the standard Jira worklog endpoint (NOT /rest/tempo-timesheets/), but the Schedule attribute lives only in Tempo's own database and must be set via api.tempo.io.

Setup

  1. Copy .env.example to ~/.claude-skills/.env and fill in all variables.
  2. JIRA_EMAIL + JIRA_API_TOKEN: from https://id.atlassian.com/manage-profile/security/api-tokens
  3. TEMPO_API_TOKEN: from Tempo Settings > API Integration (this is a separate token from Jira — the Jira token returns 401 on api.tempo.io).
  4. JIRA_ACCOUNT_ID: your Atlassian account ID (find it in Jira user profile API responses).

Helper Scripts

This skill uses both helper scripts:

# Jira worklogs (Basic auth)
.claude/skills/jira/scripts/jira-api --help

# Tempo API (Bearer token)
.claude/skills/tempo/scripts/tempo-api --help

Workflow

Step 1 — Create the Jira worklog

.claude/skills/jira/scripts/jira-api POST /rest/api/3/issue/{issueKey}/worklog '{
  "timeSpentSeconds": 28800,
  "started": "2026-07-07T09:00:00.000-0400",
  "comment": {
    "type": "doc",
    "version": 1,
    "content": [{ "type": "paragraph", "content": [{ "type": "text", "text": "Work description here" }] }]
  }
}'
  • timeSpentSeconds: hours * 3600 (e.g. 8h = 28800)
  • started: use the correct UTC offset for your timezone (e.g. -0400 for EDT)
  • Returns 201 with the Jira worklog id
  • Batching up to ~10 worklogs in a loop is fine

Step 2 — Resolve the Tempo worklog ID

GET /4/worklogs/jira/{jiraWorklogId} returns 404 on some instances — do NOT rely on it. Instead, after creating all Jira worklogs (wait ~3 seconds for sync), query Tempo's user endpoint:

.claude/skills/tempo/scripts/tempo-api GET '/4/worklogs/user/{accountId}?from=2026-07-07&to=2026-07-07&limit=50'

Match results by startDate + description + timeSpentSeconds to find the tempoWorklogId.

Important: The general GET /4/worklogs?from&to endpoint returns ALL users' worklogs with anonymized descriptions. Always use the /user/{accountId} variant.

Step 3 — Set the Schedule (work attribute)

.claude/skills/tempo/scripts/tempo-api PUT /4/worklogs/{tempoWorklogId} '{
  "issueId": 12345,
  "timeSpentSeconds": 28800,
  "startDate": "2026-07-07",
  "startTime": "09:00:00",
  "description": "Work description here",
  "authorAccountId": "712020:xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "attributes": [{ "key": "_Overtime_", "value": "UUID-from-table-below" }]
}'

You must pass the FULL worklog body (issueId, timeSpentSeconds, startDate, startTime, description, authorAccountId) — Tempo overwrites missing fields.

_Overtime_ is Tempo's internal name for the Schedule field. UUID map:

Schedule TypeUUID
Regular Hours68eae85b-815e-46cc-81e9-ce20ca29ee01
Sunday OT7fa98c32
Holiday OTe93b25f1
Panama OT1a41d729
Honduras Before 7pm19ba5b3c
Honduras After 7pme08c03fc
ICS/Miami/Jamaica OT915b89d7
Leave/Billable24f83052
Leave/Non-Billable91abad5f

Verify with a follow-up GET:

.claude/skills/tempo/scripts/tempo-api GET /4/worklogs/{tempoWorklogId}

Attributes are at worklog.attributes.values[] (array of {key, value}).

Step 4 — Post-log audit

After all worklogs are posted, re-list the week's worklogs and confirm:

  1. Each day totals the expected hours
  2. Every worklog has the Schedule attribute set
  3. Offer to transition completed tickets (get transition IDs via GET /rest/api/3/issue/{key}/transitions)

Gotchas

  • Jira worklog property write is ignored by Tempo: PUT /rest/api/3/issue/{key}/worklog/{id}/properties/tempo succeeds on the Jira side but Tempo ignores it. Always use Step 3 (Tempo PUT endpoint).
  • Tempo PUT returns empty body: wrap JSON.parse in try/catch and verify with a follow-up GET.
  • Closed timesheet periods return 403 "Period is closed": an admin must reopen the period before backdated worklogs will take.
  • Timezone display: Jira ADF started time in -0400 may display shifted in Tempo (UTC-6 board display); harmless for daily totals.

Listing Existing Worklogs

# Get a user's worklogs for a date range
.claude/skills/tempo/scripts/tempo-api GET '/4/worklogs/user/{accountId}?from=2026-07-01&to=2026-07-07&limit=50'

# Get worklogs for a specific Jira issue
.claude/skills/tempo/scripts/tempo-api GET '/4/worklogs/issue/{issueId}?from=2026-07-01&to=2026-07-07'

Deleting a Worklog

Delete from Tempo (which cascades to Jira):

.claude/skills/tempo/scripts/tempo-api DELETE /4/worklogs/{tempoWorklogId}

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.