ワンクリックでManusで任意のスキルを実行

research-refresh

スター1

フォーク0

更新日2026年4月24日 19:42

Audits freshness across all briefs. Lists briefs by age class — current (<30d), aging (30-90d), stale (>90d). Optionally re-runs stale briefs via /deep-research. Use for weekly or monthly maintenance, or before a big /create session where multiple topics will be referenced. Auto-triggers on: "/research-refresh", "check brief freshness", "which briefs are stale", "audit the research cache", "refresh stale briefs". Do not use for a specific topic — use /deep-research <topic> for that.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

enchanter-ai

enchanter-ai/wixie

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Research Refresh

Audit and optionally refresh stale briefs.

Inputs

Optional: --auto-refresh — re-run briefs whose age exceeds the threshold. Default: report only.
Optional: --threshold <days> — override the 30-day default for the stale classifier.

Execution

Step 1: Scan

Glob state/briefs/*/claims.json. For each, read the freshness field. Compute age = today − freshness.

Step 2: Classify

Age	Class	Default action
< 30 days	current	skip
30 - 90 days	aging	flag
> 90 days	stale	flag; re-run only if `--auto-refresh`

Also classify anything with verdict: FAIL as failed — surface these regardless of age.

Step 3: Report

<N> briefs total:
  current: <count>
  aging:   <count>
    - <slug> (<age> days, verdict: <X>)
  stale:   <count>
    - <slug> (<age> days, verdict: <X>)
  failed:  <count>
    - <slug> (verdict: FAIL — re-run needed)

Step 4: Conditional refresh

If --auto-refresh was passed:

For each stale brief, invoke /deep-research <slug> sequentially (not parallel — avoid fetch storms).
Report per-brief outcome: <slug>: <old verdict> → <new verdict>.

failed briefs are NOT auto-refreshed — they may have an underlying issue that re-running won't fix. Ask the developer.

Rules

Do NOT auto-refresh unless --auto-refresh is explicitly passed.
Do NOT delete stale briefs. Retention is the developer's call.
Do NOT re-run aging briefs automatically — 30-90 days may be an intentional snapshot window.
Run refreshes sequentially, not in parallel — the fetcher's WebSearch budget is shared.

Failure modes

Code	Signature	Counter
F10	Auto-deleted a brief as "cleanup"	This skill never deletes; retention is manual
F09	Parallel re-runs caused fetch races	Serialize auto-refreshes

このリポジトリの他の Skills

同じリポジトリ

deep-research

enchanter-ai/wixie

Deep research engine (E0) that produces a verified, cited claims artifact before prompts are engineered. Decomposes the query, fans out parallel Haiku fetchers, triangulates claims across independent sources, synthesizes, and verifies every claim traces to a fetched quote. Auto-fires inside /create when the topic depends on external or time-sensitive facts. Also callable standalone. Auto-triggers on: "/deep-research", "/research", "research this topic", "look up the current state of", "what's the latest on", "fact-check this", "find sources on", "before we craft the prompt, research". Do not use for static topics (pure logic, timeless writing tasks) or when a fresh brief already exists (freshness < 30 days) — reuse it. Do not use to render an existing brief — use /research-render for that.

2026-05-311

freshness-check

enchanter-ai/wixie

Runs the Wixie model-freshness aggregator over state/model-usage.ndjson and flags any models-registry.json entry whose sunset_date has elapsed. Use when the developer asks about model deprecation, registry staleness, retired models, sunset dates, F-006 closure, or wants a current freshness summary. Auto-triggers on: "model freshness", "registry stale", "deprecated models", "sunset", "F-006", "freshness report", "model usage telemetry". Do not use for emitting telemetry events (the SessionStart hook does that automatically) or for editing the registry itself (developer edits the JSON directly).

2026-05-061

converge

enchanter-ai/wixie

Run the Convergence Engine on any prompt file. Iterates up to 100 times, automatically fixing clarity, completeness, efficiency, model fit, and failure resilience until the prompt reaches DEPLOY quality. Auto-triggers on: "/converge", "converge this prompt", "optimize until perfect", "iterate until deploy", "run convergence".

2026-05-051

prompt-creator

enchanter-ai/wixie

Creates optimized, model-fitted prompts from raw task descriptions with technique selection and explained reasoning. Auto-triggers on: "I need a prompt for", "build me a prompt", "make this prompt better", "optimize this prompt", "help me prompt", "write a system prompt", "what prompting technique should I use", "how should I structure this prompt", "/create".

2026-05-051

harden

enchanter-ai/wixie

Tests a prompt for security vulnerabilities — injection attacks, jailbreak patterns, data leakage risks. Reports exploits found and suggests specific defenses. Use on any user-facing or API-deployed prompt. Auto-triggers on: "/harden", "harden this prompt", "test for injection", "is this prompt safe", "security check prompt", "red team this prompt".

2026-05-051

prompt-improver

enchanter-ai/wixie

Improves existing prompts by re-selecting techniques, adapting format to the target model, and fixing weaknesses while preserving the user's intent and domain knowledge. Auto-triggers on: "make this prompt better", "improve this prompt", "refine this prompt", "fix this prompt", "optimize this prompt", "what's wrong with this prompt", "/refine".

2026-05-051

name	research-refresh
description	Audits freshness across all briefs. Lists briefs by age class — current (<30d), aging (30-90d), stale (>90d). Optionally re-runs stale briefs via /deep-research. Use for weekly or monthly maintenance, or before a big /create session where multiple topics will be referenced. Auto-triggers on: "/research-refresh", "check brief freshness", "which briefs are stale", "audit the research cache", "refresh stale briefs". Do not use for a specific topic — use /deep-research <topic> for that.
allowed-tools	Read, Glob, Bash(date *)

Research Refresh

Audit and optionally refresh stale briefs.

Inputs

Optional: --auto-refresh — re-run briefs whose age exceeds the threshold. Default: report only.
Optional: --threshold <days> — override the 30-day default for the stale classifier.

Execution

Step 1: Scan

Glob state/briefs/*/claims.json. For each, read the freshness field. Compute age = today − freshness.

Step 2: Classify

Age	Class	Default action
< 30 days	current	skip
30 - 90 days	aging	flag
> 90 days	stale	flag; re-run only if `--auto-refresh`

Also classify anything with verdict: FAIL as failed — surface these regardless of age.

Step 3: Report

<N> briefs total:
  current: <count>
  aging:   <count>
    - <slug> (<age> days, verdict: <X>)
  stale:   <count>
    - <slug> (<age> days, verdict: <X>)
  failed:  <count>
    - <slug> (verdict: FAIL — re-run needed)

Step 4: Conditional refresh

If --auto-refresh was passed:

For each stale brief, invoke /deep-research <slug> sequentially (not parallel — avoid fetch storms).
Report per-brief outcome: <slug>: <old verdict> → <new verdict>.

failed briefs are NOT auto-refreshed — they may have an underlying issue that re-running won't fix. Ask the developer.

Rules

Do NOT auto-refresh unless --auto-refresh is explicitly passed.
Do NOT delete stale briefs. Retention is the developer's call.
Do NOT re-run aging briefs automatically — 30-90 days may be an intentional snapshot window.
Run refreshes sequentially, not in parallel — the fetcher's WebSearch budget is shared.

Failure modes

Code	Signature	Counter
F10	Auto-deleted a brief as "cleanup"	This skill never deletes; retention is manual
F09	Parallel re-runs caused fetch races	Serialize auto-refreshes