Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

planning-with-files

Étoiles335

Forks17

Mis à jour10 juillet 2026 à 20:27

Persistent file-based planning for complex or long-running work. Use when asked to plan, organize, research, or execute work requiring multiple phases or roughly 5+ tool calls. Keeps task_plan.md, findings.md, and progress.md recoverable across sessions and compaction.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

khaneliman

khaneliman/khanelinix

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Spécialistes en gestion de projetsProfessions des affaires et des opérations financières·SOC 13-1082

Explorateur de fichiers

30 fichiers

SKILL.md

readonly

name	planning-with-files
description	Persistent file-based planning for complex or long-running work. Use when asked to plan, organize, research, or execute work requiring multiple phases or roughly 5+ tool calls. Keeps task_plan.md, findings.md, and progress.md recoverable across sessions and compaction.
user-invocable	true
allowed-tools	Read Write Edit Bash Glob Grep
hooks	{"UserPromptSubmit":[{"hooks":[{"type":"command","command":"SH=\"${CLAUDE_SKILL_DIR}/scripts/inject-plan.sh\"; [ -f \"$SH\" ] \|\| SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/inject-plan.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/inject-plan.sh\" 2>/dev/null \| head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" --context=userprompt; exit 0"}]}],"Stop":[{"hooks":[{"type":"command","command":"SH=\"${CLAUDE_SKILL_DIR}/scripts/gate-stop.sh\"; [ -f \"$SH\" ] \|\| SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/gate-stop.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/gate-stop.sh\" 2>/dev/null \| head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" 2>/dev/null; exit 0"}]}],"PreCompact":[{"matcher":"*","hooks":[{"type":"command","command":"SH=\"${CLAUDE_SKILL_DIR}/scripts/inject-plan.sh\"; [ -f \"$SH\" ] \|\| SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/inject-plan.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/inject-plan.sh\" 2>/dev/null \| head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" --context=precompact; exit 0"}]}]}
metadata	{"version":"3.4.0"}

Planning with Files

Use persistent markdown files as working memory for complex or long-running tasks. Hook behavior is provider-specific; this skill body is the routing layer.

Restore First

Before complex work, read existing planning state when present:

task_plan.md
findings.md
progress.md

Then run scripts/session-catchup.py when resuming after a gap or when prior tool activity may not be reflected in the files.

Start or Continue

New complex task: create task_plan.md, findings.md, and progress.md from templates.
Existing plan: re-read the files before major decisions.
After each phase: update phase status and append progress.
After research or external content: record facts in findings.md, not task_plan.md.

References

Detailed workflow and security notes: reference.md
Example plans and logs: examples.md
Templates: templates/task_plan.md, templates/findings.md, templates/progress.md

Plus depuis ce dépôt

même dépôt

sarif-toolkit

khaneliman/khanelinix

Deterministic SARIF reporting and partitioning. Use when inspecting .sarif or .sarif.json static-analysis output, summarizing findings without loading full JSON into chat, or splitting results by rule, path, severity, or balanced chunks.

2026-07-11335

nix-toolkit

khaneliman/khanelinix

Nix operational playbooks for package diffs, build debugging, closure analysis, dependency forensics, flake maintenance, and evaluation performance tuning. Use when comparing Nix build outputs, diagnosing derivation failures, finding unexpected runtime/build dependencies, inspecting closure size, maintaining flakes, or profiling slow NixOS/Home Manager/Nixvim evaluation.

2026-07-11335

github-toolkit

khaneliman/khanelinix

GitHub issue discovery, targeted triage, issue creation, pull-request creation, review authoring, review-feedback handling, and CI check-fix workflows using gh CLI. Use for read or write work against GitHub issues, pull requests, reviews, or checks.

2026-07-11335

git-toolkit

khaneliman/khanelinix

Git commit planning, fixup/autosquash, branch cleanup, conflict resolution, regression bisect, and multi-commit change-stack workflows. Use for safe local history operations or deciding how changes should be split, repaired, or validated.

2026-07-11335

architect

khaneliman/khanelinix

Progressive context-architecture expert for repository instructions, AI prompts, rules, agents, commands, and skills. Use when initializing, designing, refactoring, or auditing AI configuration for clear boundaries and token-efficient disclosure.

2026-07-11335

jj-toolkit

khaneliman/khanelinix

Use for working with Jujutsu (jj) history workflows, including hunk-level split/squash/diffedit/restore via `jj-hunk-tool`.

2026-07-11335

name	planning-with-files
description	Persistent file-based planning for complex or long-running work. Use when asked to plan, organize, research, or execute work requiring multiple phases or roughly 5+ tool calls. Keeps task_plan.md, findings.md, and progress.md recoverable across sessions and compaction.
user-invocable	true
allowed-tools	Read Write Edit Bash Glob Grep
hooks	{"UserPromptSubmit":[{"hooks":[{"type":"command","command":"SH=\"${CLAUDE_SKILL_DIR}/scripts/inject-plan.sh\"; [ -f \"$SH\" ] \|\| SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/inject-plan.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/inject-plan.sh\" 2>/dev/null \| head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" --context=userprompt; exit 0"}]}],"Stop":[{"hooks":[{"type":"command","command":"SH=\"${CLAUDE_SKILL_DIR}/scripts/gate-stop.sh\"; [ -f \"$SH\" ] \|\| SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/gate-stop.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/gate-stop.sh\" 2>/dev/null \| head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" 2>/dev/null; exit 0"}]}],"PreCompact":[{"matcher":"*","hooks":[{"type":"command","command":"SH=\"${CLAUDE_SKILL_DIR}/scripts/inject-plan.sh\"; [ -f \"$SH\" ] \|\| SH=$(ls \"$HOME/.claude/skills/planning-with-files/scripts/inject-plan.sh\" \"$HOME/.claude/plugins/marketplaces/planning-with-files/scripts/inject-plan.sh\" 2>/dev/null \| head -1); [ -n \"$SH\" ] && [ -f \"$SH\" ] && sh \"$SH\" --context=precompact; exit 0"}]}]}
metadata	{"version":"3.4.0"}

Planning with Files

Use persistent markdown files as working memory for complex or long-running tasks. Hook behavior is provider-specific; this skill body is the routing layer.

Restore First

Before complex work, read existing planning state when present:

task_plan.md
findings.md
progress.md

Then run scripts/session-catchup.py when resuming after a gap or when prior tool activity may not be reflected in the files.

Start or Continue

New complex task: create task_plan.md, findings.md, and progress.md from templates.
Existing plan: re-read the files before major decisions.
After each phase: update phase status and append progress.
After research or external content: record facts in findings.md, not task_plan.md.

References

Detailed workflow and security notes: reference.md
Example plans and logs: examples.md
Templates: templates/task_plan.md, templates/findings.md, templates/progress.md