executing-plans
/executing-plans
Realizuje istniejący plan wdrożenia, śledząc zależności, dostosowując nieaktualne kroki i weryfikując kryteria akceptacji.
- Autor
- seaworld008 ↗
- Repozytorium
- commonly-used-high-value-skills ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 27.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 1
Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Realizuje istniejący plan wdrożenia, śledząc zależności, dostosowując nieaktualne kroki i weryfikując kryteria akceptacji.
Oryginalny opis (EN)
Use when executing an existing implementation plan, tracking dependencies, adapting outdated steps, and verifying acceptance checks.
Jak działa
- Overview
- The Process
- When to Stop and Ask for Help
- When to Revisit Earlier Steps
- Remember
- Task Evidence Ledger
- Plan Drift and Recovery
- Completion Example
Podgląd SKILL.md
--- name: executing-plans description: 'Use when executing an existing implementation plan, tracking dependencies, adapting outdated steps, and verifying acceptance checks.' zh_description: "用于按既定实现计划逐步执行任务,并在关键节点进行审查和完成验证。" version: "1.0.7" author: "seaworld008" source: "github:obra/superpowers" source_url: "https://github.com/obra/superpowers/blob/main/skills/executing-plans/SKILL.md" license: MIT tags: '["plans", "execution", "workflow"]' created_at: "2026-04-13" updated_at: "2026-09-22" quality: 3 complexity: "intermediate" --- # Executing Plans ## Overview Load plan, review critically, execute all tasks, report when complete. **Announce at start:** "I'm using the executing-plans skill to implement this plan." Use subagents only when supported, permitted, and useful for independent tasks. Otherwise execute the plan directly; no extra runtime setup is needed. ## The Process ### Step 1: Load and Review Plan 1. Inspect workspace ownership; reuse a clean task branch or isolate work if necessary 2. Read plan file 3. Review critically - identify any questions or concerns about the plan 4. Resolve routine concerns from repository evidence; ask about material unresolved decisions 5. If no concerns: Create todos for the plan items and proceed ### Step 2: Execute Tasks For each task: 1. Mark as in_progress 2. Preserve the intended outcome; adapt obsolete implementation details from current evidence 3. Run verifications as specified 4. Mark as completed ### Step 3: Complete Development After all tasks complete and verified: - Inspect the requested delivery target and repository completion checks - Use an available finishing workflow when its methods are needed - Verify required checks and execute the delivery path already requested; ask only if it is unresolved ## When to Stop and Ask for Help **STOP executing immediately when:** - Required access or a consequential user decision is unavailable after investigation - Plan has critical gaps preventing starting - A material scope conflict cannot be resolved from current instructions or evidence - Verification reveals an external blocker that cannot be repaired within the authorized scope Investigate test failures and missing local dependencies first; repair routine blockers within scope. Ask for the specific missing input only when it is necessary. ## When to Revisit Earlier Steps **Return to Review (Step 1) when:** - Partner updates the plan based on your feedback - Fundamental approach needs rethinking **Don't force through blockers** - stop and ask. ## Remember - Review plan critically first - Follow acceptance criteria and update the plan when current evidence requires a change - Don't skip verifications - Reference skills when plan says to - Stop when blocked, don't guess - Never start implementation on main/master branch without explicit user consent ## Task Evidence Ledger Track results against the actual work revision: ```text Task: Implement retry policy Input: Existing plan, current error contract, caller tests Files: Client implementation and focused retry tests Acceptance: Bounded attempts; cancellation propagates Evidence: Test command, exit status, revision Next: Integration check after the dependent caller changes ``` Reuse passing evidence while its relevant inputs are unchanged. Invalidate the affected check when a dependency or implementation changes. Keep failed checks visible until their causes are resolved. A skipped external integration is not a passing integration test. ## Plan Drift and Recovery Compare each step with current repository files before executing it. When a command or file moved, update the plan from observed evidence. Keep unfinished user tasks separate from newly discovered follow-up work. For an unavailable dependency, complete independent tasks first. Report the precise missing access or decision needed for blocked work. ## Completion Example ```text Implemented: Tasks 1-4, with dependency order preserved. Validated: Focused tests and required repository checks. Delivery: PR created and merged when that was requested. Unverified: External staging flow requires a configured environment. ```
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · seaworld008/commonly-used-high-value-skills | 100 | MIT |
| arklab/ark.tools | 100 | MIT |
| osmontero/opencode-skills | 100 | MIT |
| GanyuanRan/Aegis | 100 | MIT |
| FrancoStino/opencode-skills-collection | 100 | MIT |
| transparent-pegasus/herdrpowers | 100 | MIT |
| jamditis/claude-skills-journalism | 100 | MIT |
| zpyoung/quirk | 100 | MIT |
| khaledsaeed18/dotclaude | 100 | MIT |
Identyczna treść występuje jeszcze w 3 innych folderach na GitHubie. Tu pokazujemy jedną, najlepiej ocenioną kopię.
Migawka bazy z 28.10.2026 · wersja paczki a1b2b410be77 (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
- 90sr-executing-plans
Wykonuje spisany plan wdrożenia w osobnej sesji, z punktami kontrolnymi przeglądu. - 100review-plan
Sprawdza plan implementacji przed jego wykonaniem, zwłaszcza wygenerowany przez writing-plans, zanim ruszy executing-plans. - 100writing-plans
Tworzy plan wieloetapowej pracy z granicami zadań, zależnościami i kryteriami akceptacji, gdy użytkownik o to prosi.