/analyse

name: analyse
description: |
  Analyze GitHub issues, Pull Requests (PRs), Discussions, and repo vitality for an Open Source Software (OSS) project. For any specific item, casts a wide net — finds and lists all related open and closed issues/PRs/discussions, explicitly flags duplicates. Summarizes long threads, extracts reproduction steps, and generates repo vitality stats. Uses gh Command Line Interface (CLI) for GitHub Application Programming Interface (API) access. Complements oss:shepherd (requires `oss` plugin). NOT for PR readiness assessment or code review (use oss:review).
  TRIGGER when: user provides GitHub issue number (#N), PR number, or github.com URL with issue/PR/discussion path AND asks to analyze, summarize, understand, or triage it; user asks for repo vitality stats or "is this repo healthy".
  SKIP: user already pasted full thread text inline; oss:resolve already active on same PR; user wants code review (use oss:review); user phrasing is "review PR" meaning code quality assessment, not thread triage (route to oss:review).
argument-hint: <N|vitality [<owner>/<repo>|github-url]|ecosystem|path/to/report.md> [--reply] [--quick] [--keep "<items>"]
allowed-tools: Read, Bash, Write, Edit, Agent, AskUserQuestion, TaskList, TaskCreate, TaskUpdate
context: fork
model: sonnet
effort: high

<objective>

Analyze GitHub threads + repo vitality. Help maintainers triage, respond, decide fast. Output actionable + structured — not just summaries.

NOT for implementing PR action items (use oss:resolve). NOT for **code-quality assessment on a PR** — phrasing like "review PR #N" or "does this PR look good?" routes here via TRIGGER (PR number + "analyze/summarize" verbs) but yields thread analysis, not code review. When request is code quality, route to `oss:review` (requires `oss` plugin) instead. NOT for multi-agent code review (use oss:review). NOT for CI pipeline diagnosis (use oss:cicd-steward (requires `oss` plugin)).

</objective>

<inputs>

• **$ARGUMENTS**: one of:
• `N` (number, plain `123` or `#123`) — any GitHub thread: issue, PR, or discussion; auto-detects type
• `vitality [<owner>/<repo> | <github-url>]` — repo vitality overview with 9-axis health scorecard, duplicate detection. Optional repo argument accepts `owner/repo` shorthand or full `https://github.com/owner/repo` URL. Omitted → auto-detected from git upstream. Non-GitHub remotes (GitLab, Bitbucket, etc.) stop with warning.
• `ecosystem` — downstream consumer impact analysis for library maintainers
• `--reply` — only valid with `N`; spawns shepherd to draft contributor-facing reply after thread analysis. Silently ignored for `vitality` and `ecosystem`.
• `--quick` — only meaningful with `vitality`; fast daily-scorecard path skipping Codex independent review (Step 5) and mandatory adversarial rework loop (Step 6), reduces spawns to core 4 (gh-scraper + 3 axis scorers). Full mode (all quality passes) stays default. Silently ignored for `N`, `ecosystem`, report-path modes.
• `path/to/report.md` — path to existing report file; only valid combined with `--reply`; skips all analysis, spawns shepherd directly using provided file

</inputs>

<constants>

> Agent health monitoring (CLAUDE.md §6) — applies to Step 7 shepherd spawn. The spawn is background; end the turn after it and resume on the completion notification. The constants bound silence, not a poll cadence — nothing sleeps.

HARD_CUTOFF=900        # no file activity for this long across wake-ups → declare timed out
EXTENSION=300          # one +5 min extension if output file explains delay

</constants>

<compaction>

> loads: compaction-contract.md

• Key boundary: end of Step 5 — gather/fetch complete, before Step 6 synthesis gate.
• Preserve: cache-dir (.cache/gh), target # (CLEAN_ARGS), synthesized report path, reply-mode flag.

</compaction>

<workflow>

<!-- Agent resolution: see _OSS_SHARED/agent-resolution.md -->

Agent Resolution

export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
# loads: compaction-contract.md
# cold-start fallback
_OSS_SHARED=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_oss}/bin/resolve_shared_path.py" oss skills/_shared 2>/dev/null)  # timeout: 5000
# empty _OSS_SHARED → resolve_shared_path.py failed (no python/script/oss plugin) — downstream `[ -f ... ]` silently expands, Step7 fails after full analysis
# --reply: hard fail; non-reply: degrade gracefully
if [ -z "$_OSS_SHARED" ]; then
    if [ "$REPLY_MODE" = "true" ]; then
        echo "! BLOCKED — could not resolve _OSS_SHARED (oss plugin missing, python unavailable, or resolve_shared_path.py absent); --reply mode requires it"
        exit 1
    else
        echo "⚠ _OSS_SHARED empty — oss plugin shared dir unresolved; continuing with degraded functionality (--reply will fail in this run)"
    fi
fi
# persist $_OSS_SHARED (Check 41)
# loads: terminal-summaries.md (ships in this plugin's _shared); consumed by modes/thread.md, modes/vitality.md, modes/ecosystem.md
echo "${_OSS_SHARED:-}" > "${TMPDIR:-/tmp}/analyse-oss-shared-${CSID}"
# cold-resolve skill dir once; thread.md/vitality.md warm-read this sentinel, skip re-globbing (Check 41)
_OSS_ANALYSE=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_oss}/bin/resolve_shared_path.py" oss skills/analyse 2>/dev/null)  # timeout: 5000
[ -z "$_OSS_ANALYSE" ] && _OSS_ANALYSE="plugins/cc_oss/skills/analyse"
echo "$_OSS_ANALYSE" > "${TMPDIR:-/tmp}/analyse-oss-analyse-${CSID}"

> loads: oss-shared-resolver.md

Step 1: Flag parsing

export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
# flags: --reply, --quick (vitality fast-path: skips codex review + adversarial rework; ignored for N/ecosystem), --keep
# shared flag/--keep parser (C5; also resolve/review SKILL.md)
eval "$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_oss}/bin/parse-skill-flags.py" --flags reply,quick "$ARGUMENTS")"  # timeout: 5000
REPLY_MODE="$FLAG_REPLY"
QUICK_MODE="$FLAG_QUICK"
echo "${KEEP_ITEMS:-}" > "${TMPDIR:-/tmp}/analyse-keep-items-${CSI