New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pilot Update

by quay in quay/quay

Post a biweekly Agentic SDLC pilot update comment to PROJQUAY-11352.

Apache-2.0Auto-check passedTesting & QA

Install Pilot Update

skills CLI
$ npx skills add quay/quay --skill pilot-update -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install quay/quay pilot-update --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/quay/quay.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pilot-update .claude/skills/pilot-update && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pilot-update
GitHub stars
2.8k
Token cost
~3.5k tokens
SKILL.md length
1,505 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Post a biweekly Agentic SDLC pilot update comment to PROJQUAY-11352.

  • Works in 5 steps: Gather Jira Activity (BFS traversal) → Gather GitHub Activity → Draft the Update → …
  • Testing & QA work in your project
  • SKILL.md covers Phase 1: Gather Jira Activity…, Phase 2: Gather GitHub Activity, Phase 3: Draft the Update and Phase 4: Review and Confirm, plus 2 more sections
  • Calls gh, jq and curl; reaches redhat.atlassian.net; needs JIRA_API_TOKEN

What it does

Pilot Update is an agent skill from quay/quay. Post a biweekly Agentic SDLC pilot update comment to PROJQUAY-11352. Traverses the Jira issue hierarchy, scans 15 quay/ repos for pilot-relevant PRs, drafts a structured 5-section update, and posts after user review. Accepts an optional lookback window in days (default 14).

Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA. It works with Jira and Model Context Protocol. The repository describes itself as: Build, Store, and Distribute your Applications and Containers. The licence is Apache-2.0.

When your agent uses it

  • Testing & QA work in your project

Example prompts

  • “/pilot-update”

Requirements

  • A credential in JIRA_API_TOKEN
  • Pre-approved tools (allowed-tools): Bash(gh search prs *), Bash(gh pr view *), Bash(gh pr list *), Bash(gh api *), Bash(git log *), Bash(date *), Bash(bash .claude/scripts/jira-ops.sh *), Bash(curl *), Bash(acli jira workitem comment create *), Bash(acli jira workitem comment list *), mcp__mcp-atlassian__jira_get_issue, mcp__mcp-atlassian__jira_search, mcp__mcp-atlassian__jira_batch_get_changelogs, Read, Grep, Glob, AskUserQuestion

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Gather Jira Activity (BFS traversal)
  2. Gather GitHub Activity
  3. Draft the Update
  4. Review and Confirm
  5. Post the Comment

What it can do on your machine

Read from SKILL.md and the folder at commit ceb1eb0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(gh search prs *)
    • Bash(gh pr view *)
    • Bash(gh pr list *)
    • Bash(gh api *)
    • Bash(git log *)
    • Bash(date *)
    • Bash(bash .claude/scripts/jira-ops.sh *)
    • Bash(curl *)
    • Bash(acli jira workitem comment create *)
    • Bash(acli jira workitem comment list *)

    …and 7 more on the same allowed-tools line.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • jq
    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • redhat.atlassian.net

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • JIRA_API_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pilot Update loads about 3.5k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 1,505 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from quay/quay at commit ceb1eb0, republished under its Apache-2.0 licence (© quay). 1,505 words, ~3,508 tokens.

Download SKILL.mdSave it as .claude/skills/pilot-update/SKILL.md (or your agent's skills folder).
name
pilot-update
description
Post a biweekly Agentic SDLC pilot update comment to PROJQUAY-11352. Traverses the Jira issue hierarchy, scans 15 quay/* repos for pilot-relevant PRs, drafts a structured 5-section update, and posts after user review. Accepts an optional lookback window in days (default 14).
allowed-tools
Bash(gh search prs *), Bash(gh pr view *), Bash(gh pr list *), Bash(gh api *), Bash(git log *), Bash(date *), Bash(bash .claude/scripts/jira-ops.sh *), Bash(curl *), Bash(acli jira workitem comment create *), Bash(acli jira workitem comment list *), mcp__mcp-atlassian__jira_get_issue, mcp__mcp-atlassian__jira_search, mcp__mcp-atlassian__jira_batch_get_changelogs, Read, Grep, Glob, AskUserQuestion
argument-hint
[days]

Quay Agentic SDLC Pilot Update

Gather data from Jira and GitHub, draft a biweekly update comment, get user input on subjective sections, and post the final comment to PROJQUAY-11352.

Tracking issue: PROJQUAY-11352 ("Quay Agentic Tool Pilot") Deadline: June 30, 2026

Prerequisite: This skill uses Jira MCP tools (mcp__mcp-atlassian__jira_*) which are configured at the Ambient session level, not in the repo's .mcp.json. It must be run inside an Ambient Code session with the Jira integration enabled. If running locally, the skill falls back to the Jira REST API via curl using the same credential locations as .claude/scripts/jira-ops.sh (~/.config/acli/jira_config.yaml + token from ~/.config/acli/token.txt or ~/.acli-token, or JIRA_API_TOKEN environment variable).

Phase 1: Gather Jira Activity (BFS traversal)

Determine the lookback window. Default is 14 days. If $ARGUMENTS was provided and is a single positive integer (> 0), use that value instead. If $ARGUMENTS is empty, missing, or not provided, use 14. If it contains a non-numeric value, zero, a negative number, or multiple tokens, inform the user the input is invalid and ask them to provide a single positive integer before proceeding.

Compute:

  • end_date = today's date
  • start_date = today minus lookback days

BFS traversal starting at PROJQUAY-11352:

Use a queue-based BFS. Start with ["PROJQUAY-11352"]. Before traversal, fetch and store PROJQUAY-11352's own fields using mcp__mcp-atlassian__jira_get_issue with fields="key,summary,description,status,assignee,issuetype,created,updated".

For each key in the queue:

  1. Search for direct children: parent = KEY ORDER BY updated DESC
    • Use mcp__mcp-atlassian__jira_search with fields="key,summary,description,status,assignee,issuetype,created,updated" and limit=50
    • Paginate with start_at if total > 50 (pagination applies per parent-key search, not once globally)
  2. Fetch each child's key, summary, description, status, assignee, issuetype, created, updated fields
  3. Add each child's key to the queue
  4. Continue until the queue is empty

The hierarchy under PROJQUAY-11352 is at least 3 levels deep (Feature → Epic → Story/Task). The BFS must traverse all levels.

After collecting all keys in the hierarchy (including PROJQUAY-11352 itself, with fields stored for each):

Fetch changelogs for all discovered keys using mcp__mcp-atlassian__jira_batch_get_changelogs with fields="status" to get status transitions. Each changelog item has a created timestamp — compare it (in UTC) against the lookback window using inclusive start, exclusive end: [start_date 00:00 UTC, end_date+1 00:00 UTC). If more than 20 keys, batch in groups of 20.

Classify findings:

  • Completed issues: status transitioned to "Done", "Closed", "Resolved", or "MODIFIED" within the window
  • Created issues: created field is within the window
  • Status transitions: any status change within the window (excluding completions)
  • Blocked issues: status is "Blocked" or summary/description contains "blocked" (case-insensitive)

Phase 2: Gather GitHub Activity

Repos to search:

  • quay/quay
  • quay/quay-operator
  • quay/quay-bridge-operator
  • quay/quay-bridge-operator-konflux
  • quay/container-security-operator
  • quay/quay-builder
  • quay/quay-builder-qemu
  • quay/quay-distribution
  • quay/quay-konflux-components
  • quay/quay-fbcs
  • quay/registry-proxy
  • quay/registry-proxy-tests
  • quay/mirror-registry
  • quay/mirror-registry-konflux
  • quay/quay-tests

All repos are under the quay/ org and team-owned. No cross-team author filtering is required.

For each repo, search for PRs using the GitHub CLI:

Merged PRs (last N days):

bash
gh search prs --repo quay/<repo> --merged --merged-at ">={start_date}" --json number,title,author,closedAt,url --limit 50

Open PRs (in progress):

bash
gh search prs --repo quay/<repo> --state open --updated ">={start_date}" --json number,title,author,createdAt,url --limit 50

Filter to pilot-relevant PRs by checking if any of these apply:

  • Has label agentic-sdlc-pilot or ai-pilot
  • Touches paths: .claude/, CLAUDE.md, AGENTS.md, WORKFLOW.md, claude-plugin/, skills, agents
  • Title or body mentions: "SDLC", "pilot", "agentic", "skill", "claude", "AI", "ambient", "factory"
  • PR body contains AI-generated signatures: Co-Authored-By: Claude, Generated with Claude Code, Generated with Ambient

If a repo returns a 404 or 403, skip it gracefully and note it was skipped in the output.

Collect for each pilot-relevant PR: number, title, state, merged_at or created_at, repo name, author.

Phase 3: Draft the Update

Assemble gathered data into the 5-section template below.

Section 1: What We Tried (auto-populated)

Populate from:

  • New Jira issues created in the window (list as: [KEY] Summary — issuetype)
  • PRs opened (not yet merged) — include repo and PR number
  • Tools, workflows, or skills referenced in PR titles/descriptions/Jira summaries
  • Explicitly note which tool was used where possible: Ambient Code, Factory AI, or manual
  • Note the workflow type: bug fix, story implementation, triage, documentation, CI/CD
  • Note the issue type: Bug, Story, Epic, Task
Section 2: What Happened (auto-populated)

Populate from:

  • PRs merged during the window — include repo, PR number, title, and link
  • PRs opened but not yet merged — note as "in review" or "in progress"
  • PRs closed without merging — note as "closed/abandoned" with reason if available
  • Jira issues completed (status → Done/Closed/Resolved/MODIFIED) within the window
  • Status transitions on pilot-related issues
  • CI/test results if notable (failures, regressions)

Do NOT list PRs that are ordinary feature or bug work unless they were produced using the AI-assisted workflow. The signal here is: did the agentic pipeline produce output, and did that output land?

Section 3: What We Learned (seeded + user input)

Seed with data where possible:

  • PR review comment themes (e.g., recurring feedback patterns on AI-generated PRs)
  • Issues that required significant rework or were rejected
  • Issues that went smoothly and why (fast merge, no review comments)

After presenting the seeded bullets, use AskUserQuestion to prompt the user:

The "What We Learned" section above is seeded from PR/Jira data. Please add subjective insights: What surprised you? What context was missing? What would you do differently? Any observations about code quality, review burden, or team dynamics?

Section 4: What's Blocked (seeded + user input)

Seed with data:

  • Jira issues with "Blocked" status
  • Issues whose descriptions mention: blocked, waiting, dependency, access, permission
  • PRs stuck in review for >7 days

After presenting the seeded bullets, use AskUserQuestion to prompt the user:

The "What's Blocked" section above is seeded from Jira/GitHub data. Please add any additional blockers: tooling gaps, access issues, Jira integration problems, anything else slowing you down?

Show full SKILL.md (621 more words)Show less
Section 5: What We're Trying Next (seeded + user input)

Seed with data:

  • Jira issues in "New", "To Do", or "Refinement" status under PROJQUAY-11352
  • Unmerged pilot-relevant PRs (work in flight)
  • Upcoming epics or stories with future start dates

After presenting the seeded bullets, use AskUserQuestion to prompt the user:

The "What We're Trying Next" section above is seeded from upcoming Jira work. Please add or adjust: planned experiments, focus areas, changes in strategy or approach?

Phase 4: Review and Confirm

Assemble the complete comment using the template below for terminal preview (Markdown for readability). The actual posted comment will use ADF format — see Phase 5.

markdown
## Quay Agentic SDLC Pilot Update — {start_date} to {end_date}

### What We Tried
{bullet list: tools used, workflows attempted, issue types worked on, PRs opened}

### What Happened
{bullet list: PRs merged/closed, issues completed, status changes, outcomes}

### What We Learned
{bullet list: surprises, missing context, quality observations, process insights}

### What's Blocked
{bullet list: tooling gaps, access issues, integration problems, dependencies}

### What We're Trying Next
{bullet list: upcoming work, planned experiments, strategy changes}

Display the full formatted Markdown in the terminal. Use AskUserQuestion to ask the user to confirm or request edits:

Here is the full draft comment for PROJQUAY-11352. Reply with:

  • "post" to post as-is
  • Specific edits to apply
  • "cancel" to abort

Apply any requested edits and re-display until the user confirms with "post".

Deduplication rule: Each PR or Jira issue should appear in at most one of "What We Tried" or "What Happened" unless it has a distinct outcome to report in the latter. Specifically:

  • If an item appears in "What We Tried" (opened/created) and also merged or completed within the window, move it to "What Happened" (do not list in both).
  • For items with multiple status transitions within the window, report only the most recent transition.
  • Items that remain in the same state across both sections should appear only once, in whichever section is most relevant.

Phase 5: Post the Comment

Critical: Jira Cloud requires Atlassian Document Format (ADF) JSON for rich comment formatting. Markdown and Jira wiki markup both render as raw unformatted text. You must convert the comment to ADF before posting.

Converting to ADF

Build an ADF JSON document from the confirmed Markdown. The top-level structure is:

json
{
  "type": "doc",
  "version": 1,
  "content": [ ... ]
}

Map Markdown elements to ADF nodes:

MarkdownADF node
## Heading{"type":"heading","attrs":{"level":2},"content":[{"type":"text","text":"..."}]}
### Heading{"type":"heading","attrs":{"level":3},"content":[{"type":"text","text":"..."}]}
- bullet itemWrap items in {"type":"bulletList","content":[{"type":"listItem","content":[{"type":"paragraph","content":[...]}]}]}
**bold text**{"type":"text","text":"...","marks":[{"type":"strong"}]}
[link text](url){"type":"text","text":"...","marks":[{"type":"link","attrs":{"href":"..."}}]}
Plain text{"type":"text","text":"..."}
Paragraph break{"type":"paragraph","content":[...]}

Write the ADF JSON to a temp file (e.g., /tmp/pilot-update-adf.json).

Method 1 — acli (preferred)

acli is pre-authenticated in Ambient sessions (encrypted token stored in ~/.config/acli/jira_config.yaml). Post the comment with:

bash
acli jira workitem comment create \
  --key PROJQUAY-11352 \
  --body-file /tmp/pilot-update-adf.json

Verify success by checking the exit code. If it fails, proceed to Method 2.

Method 2 — Jira REST API via curl (fallback)

This requires both JIRA_EMAIL and JIRA_API_TOKEN to be set (not available in all Ambient sessions). Source credentials from .claude/scripts/jira-ops.sh locations: JIRA_API_TOKEN env var (or ~/.config/acli/token.txt / ~/.acli-token), and JIRA_EMAIL (defaults to quay-devel@redhat.com if not set).

The ADF document must be wrapped in a body field. Set the default email if not already configured:

bash
: "\${JIRA_EMAIL:=quay-devel@redhat.com}"
bash
resp_file="$(mktemp)"
http_code="$(
  jq -n --argjson body "$(cat /tmp/pilot-update-adf.json)" '{body: $body}' | \
  curl -sS -o "$resp_file" -w "%{http_code}" -X POST \
    -u "${JIRA_EMAIL}:${JIRA_API_TOKEN}" \
    -H "Content-Type: application/json" \
    "https://redhat.atlassian.net/rest/api/3/issue/PROJQUAY-11352/comment" \
    -d @-
)"

if [[ "$http_code" != 2* ]]; then
  echo "ERROR: Jira comment POST failed (HTTP $http_code):"
  cat "$resp_file" >&2
fi

If both methods fail, save the ADF JSON to a file and provide the user with both options:

  • A manual curl command they can run with their own credentials
  • The original Markdown so they can format it manually in the Jira editor

Report the error.

Confirm success with: "Comment posted to PROJQUAY-11352."

Error Handling

  • Repo not accessible: skip that repo, note it was skipped in the output.
  • No pilot-relevant PRs found: include "No pilot-relevant PRs found in this period" in "What Happened".
  • BFS finds no children under PROJQUAY-11352: report only PROJQUAY-11352 itself; this is valid.
  • Jira batch changelog limit: if >20 keys, batch in groups of 20.
  • User provides empty input for a subjective section: use "Nothing to report this period." as the placeholder.
  • Comment post fails: save ADF JSON, provide a manual curl command and the original Markdown for Jira editor formatting. Report the error.
  • Jira MCP tools unavailable (running outside Ambient): fall back to the Jira REST API via curl for both data gathering and comment posting. If credentials are not available, report the error and display instructions for manual posting.

© quay, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/pilot-update of quay/quay.

Open the folder on GitHubat commit ceb1eb0

Compare with similar skills

Pilot Update next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pilot Update compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pilot Update this skillquay/quay2.8k—~3.5kAutomated safety check: PassApache-2.0
Sprint Summaryshopsys/shopsys350—~3.5kAutomated safety check: PassCustom licence
Link Ticket To SessionJayantDevkar/claude-code-karma329—~1.8kAutomated safety check: NotesApache-2.0
Jira Natural Language Interfacejjmartres/opencode1333 repos~1.7kAutomated safety check: PassMIT
Issue Triage Loopcobusgreyling/loop-engineering11k—~522Automated safety check: PassMIT
Create Epic RecapDataDog/datadog-agent3.8k—~5kAutomated safety check: NotesApache-2.0

Similar skills

  • Sprint Summary

    shopsys/shopsys

    Generates a Czech sprint summary article from Jira sprint data, preferably via Jira MCP with CSV as a fallback, and can optionally prepare Playwright screenshots/videos as side attachments for…

    350 GitHub stars~3.5k tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Link Ticket To Session

    JayantDevkar/claude-code-karma

    Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma.

    329 GitHub stars~1.8k tokensUpdated 10 days ago
    DevelopmentAuto-check: notes

  • Jira Natural Language Interface

    jjmartres/opencode

    Lets an agent view, create, update and transition Jira issues in natural language, automatically choosing between the jira CLI and Atlassian MCP tools.

    133 GitHub starsUsed in 3 repos~1.7k tokens
    Product & Project ManagementAuto-check passed

  • Issue Triage Loop

    cobusgreyling/loop-engineering

    Scans open GitHub issues and discussions, flags duplicates, scores priority and proposes labels into issue-triage-state.md without ever labeling or closing.

    11k GitHub stars~522 tokensUpdated today
    DevelopmentAuto-check passed

  • Create Epic Recap

    DataDog/datadog-agent

    Official

    A skill your agent uses when an engineer or manager asks to recap, summarize, or post an update on a Jira Epic — a progress update for an in-progress Epic (how far along it is, what's shipped so…

    3.8k GitHub stars~5k tokensUpdated today
    DevelopmentAuto-check: notes

  • Akb Ingest

    dnotitia/akb

    Ingest whatever you point at into an AKB vault — a local file, a web URL, a GitHub PR/release/commit, a Confluence page, or a Jira issue.

    162 GitHub stars~2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from quay/quay

  • Debug Playwright Prow

    quay/quay

    Deep-dive diagnosis of a Playwright test failure already isolated to one Quay Prow/OpenShift CI run: downloads its GCS artifacts (results.json, JUnit, build/pod logs, Jaeger traces), classifies real…

    2.8k GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Quay Prow Triage

    quay/quay

    Diagnose any Quay Prow job failure end to end: prowjob.json - top-level build log - JUnit - resolved failing step - Playwright results.json when the failing step is Playwright, continuing through…

    2.8k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Triage Flaky Test

    quay/quay

    Triage a flaky Playwright test end to end, from a Sippy signal to a written fix proposal: Sippy numbers and failing run URLs, Prow artifacts (or the access gap), the spec, a local reproduction, and…

    2.8k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Debug Playwright

    quay/quay

    Debug Playwright E2E test failures from GitHub Actions CI runs.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Pilot Update

What does Pilot Update do?

Post a biweekly Agentic SDLC pilot update comment to PROJQUAY-11352. Pilot Update is an agent skill from quay/quay. Post a biweekly Agentic SDLC pilot update comment to PROJQUAY-11352.

When should I use Pilot Update?

Pilot Update fits situations like: testing & QA work in your project.

How do I install Pilot Update in Claude Code?

Run `npx skills add quay/quay --skill pilot-update -a claude-code`. Or copy the skill folder (.agents/skills/pilot-update in quay/quay) into .claude/skills/pilot-update in your project. Claude Code loads it when a task matches its description.

How do I install Pilot Update in Codex?

Run `npx skills add quay/quay --skill pilot-update -a codex`. Or copy the skill folder (.agents/skills/pilot-update in quay/quay) into .agents/skills/pilot-update in your project. Codex loads it when a task matches its description.

Can I use Pilot Update in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add quay/quay --skill pilot-update -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pilot-update, .gemini/skills/pilot-update, .github/skills/pilot-update and .opencode/skills/pilot-update in your project.

What does Pilot Update need to run?

Going by SKILL.md and its folder, Pilot Update needs the command-line tools its instructions call (gh, jq and curl) and credentials named JIRA_API_TOKEN. Our summary lists: A credential in JIRA_API_TOKEN. Its frontmatter pre-approves these tools: Bash(gh search prs *), Bash(gh pr view *), Bash(gh pr list *), Bash(gh api *), Bash(git log *), Bash(date *), Bash(bash .claude/scripts/jira-ops.sh *), Bash(curl *), Bash(acli jira workitem comment create *), Bash(acli jira workitem comment list *), mcp__mcp-atlassian__jira_get_issue, mcp__mcp-atlassian__jira_search, mcp__mcp-atlassian__jira_batch_get_changelogs, Read, Grep, Glob, AskUserQuestion.

Does Pilot Update access the network?

SKILL.md names 1 domain. In commands or code: redhat.atlassian.net; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Pilot Update safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pilot Update use?

Pilot Update is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pilot Update use?

About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pilot Update?

Skills that share tags, products or a category with Pilot Update: Sprint Summary (shopsys/shopsys, 350 stars), Link Ticket To Session (JayantDevkar/claude-code-karma, 329 stars), Jira Natural Language Interface (jjmartres/opencode, 133 stars) and Issue Triage Loop (cobusgreyling/loop-engineering, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pilot Update?

quay (a GitHub organization) maintains it in quay/quay, which has 2,829 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.

Source: quay/quay on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.