phase-issue
Generates a Phase-N tracking issue. Assembles a structured issue body containing cross-session handoff context, a decisions table, per-PR tasks, DoD, and the Phase N+1 outlook, then files it with gh issue create. Supports a non-interactive mode where all items are passed as arguments, and an interactive mode (Claude Code companion) that fills in whatever is missing.
- License 许可
- MIT
- 所属仓库
- ozzy-labs/skills
- 最近更新
- 2026-07-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- description
- Generates a Phase-N tracking issue. Assembles a structured issue body containing cross-session handoff context, a decisions table, per-PR tasks, DoD, and the Phase N+1 outlook, then files it with gh issue create. Supports a non-interactive mode where all items are passed as arguments, and an interactive mode (Claude Code companion) that fills in whatever is missing.
- allowed-tools
- Bash, Read, Write, AskUserQuestion
- argument-hint
- <phase-number> "<title>" [--description ...] [--refs ...] [--donts ...] [--decisions-file ...] [--tasks-file ...] [--dod ...] [--outlook ...] [--related ...] [--label ...] [--repo ...] [--draft]
- disable-model-invocation
- true
03 SKILL.md 正文
phase-issue
Read .agents/skills/phase-issue/SKILL.md and follow its workflow steps.
Important: Follow the canonical SKILL.md's conventions for the section structure, formatting rules, and marker block strictly. Do not add or remove sections at Claude's own discretion.
Claude Code-specific additions
Argument parsing
Parse $ARGUMENTS:
- If
<phase-number>and<title>are missing, confirm each with AskUserQuestion (do not set theanswersparameter) - Obtain optional options (
--description,--refs,--donts,--decisions-file,--tasks-file,--dod,--outlook,--related,--label,--repo,--draft) from the arguments
Interactively filling in missing items
For optional items not passed as arguments, confirm individually via AskUserQuestion whether to fill them in (do not set the answers parameter).
Question order (follows the section order):
- 「プロジェクト概要を入力する」 / 「省略する」 → corresponds to
--description - 「参考実装を入力する」 / 「省略する」 → corresponds to
--refs(comma-separated) - 「やってはいけないことを入力する」 / 「省略する」 → corresponds to
--donts(newline-separated) - 「決定事項ファイルを指定する」 / 「TBD で残す」 → corresponds to
--decisions-file - 「タスクファイルを指定する」 / 「TBD で残す」 → corresponds to
--tasks-file - 「DoD を入力する」 / 「TBD で残す」 → corresponds to
--dod(newline-separated) - 「Phase N+1 outlook を入力する」 / 「(未定) で残す」 → corresponds to
--outlook - 「関連を入力する」 / 「省略する」 → corresponds to
--related(newline-separated)
If 「入力する」 is chosen, ask for the specific content via AskUserQuestion (free-form entry is done via a separate AskUserQuestion call).
For items already passed as arguments, do not ask (do not collect the same information twice).
Body preview and final confirmation
After assembling the body, before filing the issue or outputting to stdout, confirm via AskUserQuestion (do not set the answers parameter):
- 「この内容で起票する」 → file the issue with
gh issue create --body-file(or output to stdout when--draftis specified) - 「修正する」 → ask which section to revise and re-enter the corresponding item
- 「キャンセル」 → abort
Important: Do not run gh issue create without approval. Even in --draft mode, confirm the content before outputting to stdout.
Next action after completion
Immediately after the completion report, call AskUserQuestion (do not set the answers parameter):
- 「この issue から
/driveで実装を始める」 → guide the user to/drivewith the filed issue number as an argument (do not execute it) - 「別の Phase issue を作成する」 → guide the user to run this skill again
- 「終了する」 → end
Do not execute the next action without the user's confirmation.
04 同仓库更多 Skills
verify
An integrated skill that runs the combined validation of build / typecheck / test / lint in one shot. The `verify.mjs` engine auto-discovers validation commands via a discovery chain (AGENTS.md's 「検証」 section → package.json scripts → justfile/Makefile/lefthook → language heuristics), executes them serially with their source attached, and returns a result summary. If a higher-priority stage produces a hit, only that stage is executed (no crossing stages).
usage-guard
Monitors Claude Code's Usage Limit (5-hour = Current / weekly = Weekly), pauses work when it exceeds 95%, and automatically resumes once the reset restores headroom. Bundles an engine form that a caller such as drive Reads at a checkpoint, and a standalone form, `/usage-guard "<continuation command>"`, that guards arbitrary work. Claude-only (depends on the OAuth usage-rate endpoint + ScheduleWakeup).
topics
Selects GitHub topic candidates by having the `topics.mjs` engine perform constraint validation, popularity measurement, broad+narrow / singular-plural comparison, and hardcoded ozzy-labs conventions, then applies them via `gh repo edit --add-topic` following the policy's `externally-visible` gate (default batch-confirm). Scope is limited to use within ozzy-labs.
skill-observability
Defines the skill observability event contract (event.schema.json) and emit substrate (obs-emit.mjs). The SSOT for the measurement layer of the skill improvement loop. Referenced by other skills and hooks.
skill-metrics
Aggregates the local observability event log (~/.agents/observability/events.jsonl) and presents, read-only, per-skill invocation counts and notable events (fallback / HITL rejection / loop cap reached / abort). Fires on "show me the skill metrics," "aggregate the observability results," "which skills get used the most?" Does not send anything.
ship
Runs verification, commit, and PR creation all at once. An integrated pipeline that runs verify (build + type + test + lint) → commit → PR creation in sequence against the changes.