progress-report
/progress-report
Prowadzi na żywo raport postępu planu lub funkcji Spec Kit, zbierając stan zadań i zdarzenia agentów, a wynik pokazuje w przeglądarce.
- Autor
- samykabu ↗
- Repozytorium
- sanduq-skills ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 06.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 106
- Skrypty
- 67
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 06.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 67 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: assets/ui/blocks.js, scripts/hook.py, scripts/progress.py, scripts/sanduq_progress/__init__.py, scripts/sanduq_progress/collect/clarifications.py, scripts/sanduq_progress/collect/hosts.py, scripts/sanduq_progress/collect/lifecycle.py, scripts/sanduq_progress/collect/plan.py, scripts/sanduq_progress/collect/runs.py, scripts/sanduq_progress/collect/tasks.py, scripts/sanduq_progress/collect/workflow.
Co robi i kiedy
Prowadzi na żywo raport postępu planu lub funkcji Spec Kit, zbierając stan zadań i zdarzenia agentów, a wynik pokazuje w przeglądarce.
Wyzwalacze z opisu
Oryginalny opis (EN)
Keep a live, deterministic progress report for a Markdown plan checklist or a Spec Kit feature. Collects task state from the plan file, hook events from Claude Code or Codex, and lane, blocker and decision facts you record, then renders a browser view and a Markdown export with no agent spent on upkeep. Use when asked to "track progress on this plan", "show a progress dashboard", "report which agents work on which tasks", to install progress hooks, or to record a lane assignment, blocker, decision or note.
Jak działa
- When to use it
- Plan mode quick start
- Verbs
- Rules
Podgląd SKILL.md
--- name: progress-report description: Keep a live, deterministic progress report for a Markdown plan checklist or a Spec Kit feature. Collects task state from the plan file, hook events from Claude Code or Codex, and lane, blocker and decision facts you record, then renders a browser view and a Markdown export with no agent spent on upkeep. Use when asked to "track progress on this plan", "show a progress dashboard", "report which agents work on which tasks", to install progress hooks, or to record a lane assignment, blocker, decision or note. --- # Progress report Reporting is a deterministic projection. Never spawn, retain, message or poll an agent solely to maintain it. Record only missing assignment, decision or blocker facts. Run the CLI from the repository root: `progress` below stands for `python <skill dir>/scripts/progress.py` (`.claude/skills/progress-report`, `.agents/skills/progress-report`, or `$CLAUDE_PLUGIN_ROOT/skills/progress-report`). Type the full command each time. Verbs print one line (`refresh` prints nothing); relay it. ## When to use it - A plan file (Markdown with `- [ ]` / `- [x]` items) drives the work: **plan mode**, no Spec Kit needed. - A Spec Kit feature has `specs/<feature>/tasks.md`: **feature mode**; Workflow files are collected when present. ## Plan mode quick start 1. `progress hooks install --host claude` (or `codex`; add `--scope user` for a plugin install) once, for model, effort, context and child agents. Skip it and tasks are still tracked. 2. `progress init --plan docs/plan.md` creates `.progress/plan/` (see `--name`, `--dir`) and prints `bind=<nonce>`; the next hook binds (`hooks install` prints one if a report exists). 3. Check items off in the plan file; the report follows. Progress never writes the plan. 4. `progress status` gives the one-line state; the view is `.progress/plan/.view/index.html`. Items keep a written id (`T001`); others get stable `P001`... ids. With one plan or feature active no target flag is needed; otherwise pass `--plan NAME` or `--feature DIR`. ## Verbs | Need | Command | | --- | --- | | Create a report | `progress init --plan PATH [--name N] [--dir D]` or `progress init` (Spec Kit) | | One-line state | `progress status` | | Assign a lane | `progress lane L1 --tasks P001-P004 --owner ID --harness H --model M --effort E` | | Close a lane | `progress lane L1 --close` | | Blocker | `progress block P007 --by L2` (or `P003`, `ext:"text"`); `progress unblock B4` | | Decision | `progress decide ask "question" --options a,b`; `progress decide made D2 b --by user` | | Note | `progress note "text" --target P005` | | Export | `progress export --format md` | | Hooks | `progress hooks install\|uninstall\|status --host claude\|codex [--scope project\|user]`; Codex also needs the project trusted and hooks approved | ## Rules 1. Record a lane when you assign work (`L#`; host children `C#` appear on their own). Starts, completions and retries need no command. 2. Never put secrets, absolute paths or transcript text in a note (200 characters at most). 3. Unknown values stay unknown. Do not estimate model, effort, context or time. 4. Errors read `progress: error CODE`; fix the cause, do not retry in a loop. Details: `references/verbs.md`; contract `docs/contracts.md`; flags `docs/commands.md`.
Pliki w paczce (106)
- README.md 27 KB
- SKILL.md 3 KB
- agents/openai.yaml 1 KB
- assets/ui/base.css 15 KB
- assets/ui/blocks.js 41 KB
- assets/ui/index.html 1 KB
- docs/commands.md 48 KB
- docs/contracts.md 59 KB
- docs/hosts.md 15 KB
- docs/token-benchmark.md 6 KB
- docs/assets/progress-dark.png 87 KB
- docs/assets/progress-light.png 87 KB
- docs/assets/progress-narrow.png 77 KB
- references/verbs.md 5 KB
- scripts/hook.py 8 KB
- scripts/progress.py 36 KB
- scripts/sanduq_progress/__init__.py 1 KB
- scripts/sanduq_progress/facts.py 6 KB
- scripts/sanduq_progress/hook.py 4 KB
- scripts/sanduq_progress/hooks_install.py 19 KB
- scripts/sanduq_progress/lock.py 3 KB
- scripts/sanduq_progress/model.py 37 KB
- scripts/sanduq_progress/model_v3.py 49 KB
- scripts/sanduq_progress/paths.py 20 KB
- scripts/sanduq_progress/refresh.py 3 KB
- scripts/sanduq_progress/render_data.py 2 KB
- scripts/sanduq_progress/render_md.py 6 KB
- scripts/sanduq_progress/safelog.py 1 KB
- scripts/sanduq_progress/selfreport.py 3 KB
- scripts/sanduq_progress/snapshot.py 18 KB
- scripts/sanduq_progress/statusline.py 7 KB
- scripts/sanduq_progress/theme.py 14 KB
- scripts/sanduq_progress/util.py 8 KB
- scripts/sanduq_progress/validate.py 6 KB
- scripts/sanduq_progress/collect/clarifications.py 7 KB
- scripts/sanduq_progress/collect/hosts.py 1 KB
- scripts/sanduq_progress/collect/lifecycle.py 5 KB
- scripts/sanduq_progress/collect/plan.py 10 KB
- scripts/sanduq_progress/collect/runs.py 9 KB
- scripts/sanduq_progress/collect/tasks.py 6 KB
- scripts/sanduq_progress/collect/workflow.py 13 KB
- scripts/sanduq_progress/hosts/__init__.py 4 KB
- scripts/sanduq_progress/hosts/claude.py 5 KB
- scripts/sanduq_progress/hosts/codex.py 5 KB
- tests/helpers.py 8 KB
- tests/live_ab.py 22 KB
- tests/screenshots.py 2 KB
- tests/test_core.py 11 KB
- tests/test_hooks_install.py 18 KB
- tests/test_hosts.py 15 KB
- tests/test_legacy.py 8 KB
- tests/test_live_ab.py 10 KB
- tests/test_p1_review.py 11 KB
- tests/test_plan.py 24 KB
- tests/test_projection.py 8 KB
- tests/test_review_c1.py 21 KB
- tests/test_review_c1b.py 45 KB
- tests/test_review_c2.py 11 KB
- tests/test_review_c3.py 8 KB
- tests/test_review_c4.py 5 KB
- tests/test_review_pr87.py 3 KB
- tests/test_review_r1.py 24 KB
- tests/test_review_r2.py 12 KB
- tests/test_run842.py 11 KB
- tests/test_skill_review.py 12 KB
- tests/test_skill_review_c2.py 8 KB
- tests/test_skill_review_c3.py 4 KB
- tests/test_theme.py 12 KB
- tests/test_token_budget.py 3 KB
- tests/test_ui_v3_browser.py 47 KB
- tests/test_v3_model.py 41 KB
- tests/ui_v3_make_fixtures.py 16 KB
- tests/ui_v3_screenshots.py 2 KB
- tests/bench/__init__.py 1 KB
- tests/bench/approaches.py 14 KB
- tests/bench/counting.py 1 KB
- tests/bench/model.py 7 KB
- tests/bench/report.py 9 KB
- tests/bench/run.py 2 KB
- tests/bench/traces.py 7 KB
- tests/fixtures/checkpoint.json 1 KB
- tests/fixtures/clarifications-vector.json 9 KB
- tests/fixtures/claude_child_event.json 1 KB
- tests/fixtures/claude_post_task.json 1 KB
- tests/fixtures/claude_pre_task.json 1 KB
- tests/fixtures/claude_statusline.json 1 KB
- tests/fixtures/codex_child_hook.json 1 KB
- tests/fixtures/codex_hook.json 1 KB
- tests/fixtures/codex_rollout.jsonl 1 KB
- tests/fixtures/decisions.json 1 KB
- tests/fixtures/delegations.json 1 KB
- tests/fixtures/expected_plan_report.json 7 KB
- tests/fixtures/expected_report.json 10 KB
- tests/fixtures/projection-hostile.json 7 KB
- tests/fixtures/projection-minimal.json 3 KB
- tests/fixtures/projection-sample.json 8 KB
- tests/fixtures/tasks.md 1 KB
- tests/fixtures/ui_v3_edge.json 2 KB
- tests/fixtures/ui_v3_sample.json 105 KB
- tests/fixtures/run-842/README.md 1 KB
- tests/fixtures/run-842/tasks.md 4 KB
- tests/fixtures/run-842/progress/facts.jsonl 45 KB
- tests/fixtures/run-842/workflow/checkpoint.json 14 KB
- tests/fixtures/run-842/workflow/clarifications.json 2 KB
- tests/fixtures/run-842/workflow/decisions.json 1 KB
- tests/fixtures/run-842/workflow/delegations.json 193 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · samykabu/sanduq-skills | 90 | MIT |
| krishp147/skills | 90 | MIT |
| caidanw/skills | 86 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki d09ba1bbaaf0 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100report-progress
Pisze raport z postępu według szablonu statusu lub szablonu projektu, gdy ktoś prosi o aktualizację. - 86report-writer
Pisze tygodniowy raport postępu z ostatniej aktywności w repozytorium, gdy trzeba opisać stan prac. - 86progress
Raportuje postęp względem planu prostym językiem: czy jest na czas, co gotowe, co trwa, co zablokowane i co dalej. - 90status
Pokazuje tablicę postępu specyfikacji z katalogu specs i wskazuje, co robić dalej, albo szczegółowy stan jednej specyfikacji. - 90build-tracker
Pokazuje na żywo postęp wieloetapowej pracy na stronie HTML, z czasem zadań, zadaniami do zrobienia i szacowanym zakończeniem. - 86report-writer
Układa tygodniowy raport z postępu prac, czytając ostatnie zmiany w repozytorium i przygotowując opis statusu.