Skip to main content
Exécutez n'importe quel Skill dans Manus
en un clic
Dépôt GitHub

takode

takode contient 16 skills collectées depuis MrVPlusOne, avec une couverture métier par dépôt et des pages de détail sur le site.

skills collectés
16
Stars
7
mis à jour
2026-06-30
Forks
2
Couverture métier
7 catégories métier · 100% classifié
explorateur de dépôts

Skills dans ce dépôt

leader-dispatch
Autres occupations informatiques

Dispatch workflow for leader/orchestrator sessions. Use when dispatching a quest to a worker, choosing which worker to assign, spawning new worker sessions, or deciding whether to reuse vs spawn. Triggers: 'dispatch', 'send quest', 'assign worker', 'spawn worker', 'which worker', 'reuse or spawn'.

2026-06-30
takode-orchestration
Autres occupations informatiques

Cross-session orchestration for Takode. Use when you need to interact with other sessions: listing active sessions, peeking at session activity, reading messages, sending instructions to workers, or spawning new sessions. Triggers: 'check on workers', 'send to session', 'orchestrate', 'coordinate agents', 'list sessions', 'peek at session', 'what are my sessions doing', 'check session status'.

2026-06-26
quest-design
Spécialistes en gestion de projets

Confirm quest intent before creating a new quest or refining an idea into a worker-ready quest. Invoke when a user asks to create, file, refine, scope, or prepare a quest, or before materially rewriting quest title/description/tags as part of refinement. Do not use for routine quest feedback, claiming, completion, verification checks, or other bookkeeping.

2026-06-23
worktree-rules
Développeurs de logiciels

Port changes from a git worktree to the main repository. This is the skill behind `/port-changes`; `worktree-rules` remains the underlying skill slug/directory. Use when asked to 'port changes', 'sync to main', 'push to main repo', '/port-changes', or when porting worktree commits.

2026-06-02
reviewer-groom
Analystes en assurance qualité des logiciels et testeurs

Quality review for another agent's change. Invoke it with a concise description of the change to review, then inspect that worker's status and diff and later verify whether required findings were addressed.

2026-05-21
skeptic-review
Analystes en assurance qualité des logiciels et testeurs

Adversarial review of a worker's completed task. Independently evaluates whether the worker did thorough, honest work or took shortcuts. Returns ACCEPT or CHALLENGE with specific questions. Invoked by the reviewer session after being spawned by the leader.

2026-05-21
takode-ui-e2e-validation
Analystes en assurance qualité des logiciels et testeurs

Use when validating Takode UI or E2E workflows in a browser, checking frontend behavior, using shared persistent validation state or isolated exceptions, gathering screenshot evidence, exercising Playground states, coordinating dev-server:companion or agent-browser leases, or documenting Quest Journey Execute evidence. This Takode project skill uses agent-browser for interactive validation and forbids stopping, killing, or replacing the live :3456 server.

2026-05-21
takode-orchestration-design
Spécialistes en gestion de projets

Use when designing, reviewing, or changing Takode leader/worker/reviewer orchestration instructions, Quest Journey phase briefs, leader dispatch templates, or related project agent workflow docs. Do not use for ordinary quest execution, normal code review, or phase work that only follows existing instructions.

2026-05-10
takode-cli-design
Administrateurs de réseaux et de systèmes informatiques

Use when designing, changing, or reviewing Takode CLI commands, JSON output schemas, inspection commands, or orchestration command output that may expose session objects, prompts, histories, logs, recordings, images, tool results, artifacts, or other bulky/uncommon fields.

2026-05-10
takode-cli-design
Administrateurs de réseaux et de systèmes informatiques

Use when designing, changing, or reviewing Takode CLI commands, JSON output schemas, inspection commands, or orchestration command output that may expose session objects, prompts, histories, logs, recordings, images, tool results, artifacts, or other bulky/uncommon fields.

2026-05-10
takode-codex-session-safety
Analystes en sécurité de l'information

Use before changing or reviewing Takode Codex adapter/session behavior involving Codex skills/changed notifications, skills/list or app/list metadata refresh, stale skill/app metadata state, startup or relaunch metadata pickup, Codex session close waves, browser-open relaunch or recovery behavior, or image attachment transport safety.

2026-05-10
takode-codex-session-safety
Analystes en sécurité de l'information

Use before changing or reviewing Takode Codex adapter/session behavior involving Codex skills/changed notifications, skills/list or app/list metadata refresh, stale skill/app metadata state, startup or relaunch metadata pickup, Codex session close waves, browser-open relaunch or recovery behavior, or image attachment transport safety.

2026-05-10
takode-injected-message-design
Développeurs de logiciels

Use before changing Takode injected messages, synthetic user messages, model-only reminders, reminder messages, or reminder-message rendering/delivery. Future agents working on injected-message behavior must read this skill first.

2026-05-08
random-memory-ideas
Commis de bureau généraux

Use when the user wants to remember, capture, save, or add a random idea, thought, note, link, reference, decision, or memory to Yuege's Random Memory Hub in Notion.

2026-04-29
confirm
Développeurs de logiciels

Confirm the user's intent before doing any work. Invoke this skill whenever the user includes /confirm anywhere in their message -- even mid-sentence, even if it looks like conversational agreement (e.g. "/confirm Yes, do it"). The /confirm token is always a skill invocation, never conversational. Do not take action on the specific instruction or change request under /confirm until the confirm workflow completes.

2026-04-28
self-groom
Analystes en assurance qualité des logiciels et testeurs

Expensive multi-perspective self-review using parallel subagents. Use when asked for a deep self-review, when the reviewer explicitly escalates to the parallel path, or when you need broader code-quality coverage than the default reviewer-owned pass.

2026-04-16