skills/one-on-one/SKILL.md
Prepare one-on-one/status bullets from ~/moz_artifacts using qmd and copy a topic-organized HTML/RTF list with embedded links to the macOS clipboard. Use when summarizing recent Mozilla work for a manager, 1:1, or status update. DO NOT USE FOR generating raw daily logs; use daily-log.
npx skillsauth add jwmossmoz/agent-skills one-on-oneInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Prepare manager-facing bullets from recent Mozilla work notes and put them on the clipboard in a Google Docs-friendly rich format.
qmd indexes ~/moz_artifacts as collection moz./usr/bin/swift; the clipboard helper uses AppKit.gh for resolving GitHub PR URLs when notes only mention
repo#123 or PR #123.peekaboo for inspecting Google Docs paste results, but do not
drive the document unless the user explicitly asks.Most runs are interactive: gather the relevant artifacts, write the bullets, then call the clipboard helper with a JSON payload.
qmd query "one on one work summary May 13 May 19 2026" -c moz -n 20
qmd get "daily-log-2026-05-19.md"
swift ~/.claude/skills/one-on-one/scripts/copy-rich-bullets.swift /tmp/one-on-one.json
Minimal payload:
{
"sections": [
{
"title": "Windows / Firefox CI reliability",
"bullets": [
{
"segments": [
{"text": "Validated "},
{"text": "Bug 1970481", "url": "https://bugzilla.mozilla.org/show_bug.cgi?id=1970481"},
{"text": " on 25H2 alpha with all target rows green."}
]
}
]
}
]
}
The helper sets three pasteboard types at once: HTML, RTF, and plain text. Google Docs usually consumes the HTML/RTF path; the plain-text fallback keeps the clipboard readable in terminals and plain editors.
Determine the date range. If the user gives relative dates, state the concrete range you are using.
Query qmd before grepping ~/moz_artifacts:
qmd query "work summary one on one <date range>" -c moz -n 20
qmd ls
Pull full source documents for the range with qmd get. Check the
filesystem for new markdown files if the user just regenerated logs:
rg --files ~/moz_artifacts | rg '2026-05-(13|14|15|16|17|18|19)'
Extract work items, outcomes, IDs, and URLs. Prefer concrete outcomes: PR opened/merged, bug filed, validation passed, cost impact quantified, root cause found, or handoff written.
Resolve hyperlinks for all externally meaningful references:
https://bugzilla.mozilla.org/show_bug.cgi?id=<bug>https://mozilla-hub.atlassian.net/browse/<KEY>https://github.com/<owner>/<repo>/pull/<n>https://treeherder.mozilla.org/jobs?repo=try&revision=<rev>Organize bullets by topic, not date. Good default topics:
Keep bullets manager-facing. Avoid implementation trivia unless it explains impact, risk, or a decision.
Write /tmp/one-on-one.json and run the clipboard helper.
Tell the user the clipboard is ready, and mention any date gaps or missing source logs.
Each bullet should be one sentence when possible. Use links on the words a human would expect to click, not naked URLs:
{
"segments": [
{"text": "Opened "},
{"text": "fxci-config PR #1002", "url": "https://github.com/mozilla-releng/fxci-config/pull/1002"},
{"text": " with eviction and cost evidence for Spot pools."}
]
}
Use text-only segments for unlinked parts. Do not put literal bullet
characters in the text; the helper creates native HTML list items.
qmd update, qmd embed, or qmd collection add unless the
user explicitly asks. Reading commands like qmd query, qmd search,
qmd get, and qmd ls are safe.peekaboo to inspect the active window first and verify the cursor is
in the intended date section.qmd status and
fd -e md ~/moz_artifacts --changed-within <range> before concluding a
day had no artifacts.daily-log when the user needs to generate or refresh a daily log from
Claude Code/Codex session JSONL files before building the one-on-one notes.redash or bigquery when the summary needs fresh telemetry or CI data,
rather than only prior notes in ~/moz_artifacts.development
Download Azure Cost Management exports and query local Parquet/CSV in DuckDB. Use when refreshing local Azure cost caches or writing DuckDB SQL over exports. DO NOT USE FOR live Cost Management API diagnosis; use azure-cost-analysis.
data-ai
Use when creating performance self-reviews from local notes, prior reviews, review prompts, and verified evidence. Helps draft H1/H2, annual, and promotion self evaluations, example answers, and rich review-form paste output. Do not use for routine status or 1:1 summaries; use one-on-one.
development
Use when tracing Taskcluster Azure VM startup from worker-manager request through in-VM boot scripts to generic-worker `workerReady` with tc-logview, paperctl, Splunk Web, and Yardstick Prometheus. Applies to Windows worker provisioning latency. DO NOT USE FOR task failure triage (use worker-image-investigation).
testing
Use when validating, auditing, grading, or checking an agent skill, SKILL.md, validator report, eval coverage, or production-readiness claim against agentskills.io and repo conventions. Checks spec, style, links, references, and eval evidence. DO NOT USE FOR creating or iterating skills; use skill-creator.