Run any Skill in Manus with one click

weekly-reality-capture

Stars1

Forks0

UpdatedApril 5, 2026 at 19:03

Auto-generate a reality-first weekly log from daily memory logs, git history, and agent state. Uses Claude to synthesize what actually happened — not a strategic filter, not a curated narrative. Supports backfill by week number. Use when a user says "weekly recap", "what happened this week", "weekly capture", or "reality check".

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

rushindrasinha

rushindrasinha/ares-skills

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

3 files

SKILL.md

readonly

name	weekly-reality-capture
description	Auto-generate a reality-first weekly log from daily memory logs, git history, and agent state. Uses Claude to synthesize what actually happened — not a strategic filter, not a curated narrative. Supports backfill by week number. Use when a user says "weekly recap", "what happened this week", "weekly capture", or "reality check".
metadata	{"emoji":"📸","category":"memory","platform":"any (requires Anthropic API key)"}

Weekly Reality Capture

Synthesize a reality-first weekly log from multiple data sources. The key insight: most weekly reviews optimize for narrative. This one optimizes for truth.

Data Sources

Source	What it captures
Daily memory logs	What the agent did/discussed each day
Git log	What code actually changed
Agent session state	Open threads, pending follow-ups
Open threads JSON	Carried-over work items

Usage

# Current week
python3 scripts/capture.py

# Specific week
python3 scripts/capture.py --week 2026-W14

# Dry run (print synthesis prompt, don't call Claude)
python3 scripts/capture.py --dry-run

Configuration (env vars)

Variable	Default	Purpose
`ANTHROPIC_API_KEY`	(required)	Claude API key for synthesis
`CAPTURE_MODEL`	`claude-sonnet-4-5-20250514`	Model for synthesis
`MEMORY_DIR`	`~/agent-workspace/memory`	Daily log directory (`YYYY-MM-DD.md` files)
`WEEKLY_DIR`	`~/agent-workspace/weekly`	Output directory for weekly captures
`REPO_DIR`	`~/agent-workspace`	Git repo to pull log from
`SESSION_STATE_PATH`	(optional)	Path to `session_state.json`
`OPEN_THREADS_PATH`	(optional)	Path to `open_threads.json`

Output Format

Each weekly capture produces YYYY-WNN.md:

# Week 14 — 2026-03-31 to 2026-04-06

## What Actually Happened
- ...

## Decisions Made
- ...

## Unresolved / Carried Over
- ...

## Patterns Noticed
- ...

Why "Reality-First"?

Most automated weekly summaries read like press releases — they highlight wins and bury problems. This tool is designed to report what actually happened, including:

Threads that stalled without resolution
Promises made but not delivered
Work that was started then abandoned
Time spent on ops vs. creative work

The synthesis prompt explicitly instructs Claude to resist narrative smoothing.

Cron Setup

Run Sunday night to capture the full week:

0 23 * * 0 /usr/bin/python3 /path/to/weekly-reality-capture/scripts/capture.py >> /tmp/weekly-capture.log 2>&1

Scripts

scripts/capture.py — Main script. Collects data, builds synthesis prompt, calls Claude, writes output.

More from this repository

same repository

indic-language-translator

rushindrasinha/ares-skills

Use when a user wants to translate text to or from any Indian language — Hindi, Tamil, Telugu, Bengali, Marathi, Kannada, Malayalam, Gujarati, Punjabi, Urdu, Odia, Assamese, Sanskrit — or says "translate this message", "translate this to Hindi", "what does this say in Tamil", "convert to Marathi", or similar. Also handles global languages (Spanish, French, Arabic, Chinese, Japanese, Korean, etc.). Uses Gemini 2.5 Flash. Also use when asked to detect what language a piece of text is written in.

2026-05-201

ai-agent-kill-switch

rushindrasinha/ares-skills

Phrase-triggered emergency stop system for AI agents. Instantly halts all agent automation when a trigger phrase is detected in session logs, or via manual flag. Use when setting up a safety kill switch, emergency stop, or pause-all-automation mechanism for autonomous agents. Survives restarts via LaunchAgent watchdog.

2026-04-051

cricd-prompt-standard

rushindrasinha/ares-skills

The CRICD framework for structuring sub-agent task prompts — Context, Relevance, Instruction, Constraints, Demonstration. Produces dramatically better output from any LLM sub-agent. Use when spawning sub-agents, writing task prompts, or structuring complex instructions for AI models.

2026-04-051

critique-loop-protocol

rushindrasinha/ares-skills

Formal protocol for draft → critique → revise loops in AI agent workflows. Defines when to use critique loops (money, public publishing, strategy) and when to skip (simple edits, routine coding). Prevents both over-engineering simple tasks and under-reviewing critical ones.

2026-04-051

gateway-watchdog

rushindrasinha/ares-skills

Monitor OpenClaw Gateway health by tailing logs for error patterns — 429 rate limits, auth failures, delivery failures, timeouts. Alert when error rate crosses thresholds. Use when setting up production monitoring for an OpenClaw Gateway deployment, or when a user says "watch the gateway", "monitor gateway errors", "alert me on gateway failures".

2026-04-051

gstack-coding-discipline

rushindrasinha/ares-skills

A 5-tier dispatch framework for coding tasks in AI agent workflows. Routes tasks from SIMPLE (one-file typo fix) to FULL (multi-day feature build) with appropriate rigor at each level. Prevents over-engineering simple tasks and under-planning complex ones.

2026-04-051

name	weekly-reality-capture
description	Auto-generate a reality-first weekly log from daily memory logs, git history, and agent state. Uses Claude to synthesize what actually happened — not a strategic filter, not a curated narrative. Supports backfill by week number. Use when a user says "weekly recap", "what happened this week", "weekly capture", or "reality check".
metadata	{"emoji":"📸","category":"memory","platform":"any (requires Anthropic API key)"}

Weekly Reality Capture

Synthesize a reality-first weekly log from multiple data sources. The key insight: most weekly reviews optimize for narrative. This one optimizes for truth.

Data Sources

Source	What it captures
Daily memory logs	What the agent did/discussed each day
Git log	What code actually changed
Agent session state	Open threads, pending follow-ups
Open threads JSON	Carried-over work items

Usage

# Current week
python3 scripts/capture.py

# Specific week
python3 scripts/capture.py --week 2026-W14

# Dry run (print synthesis prompt, don't call Claude)
python3 scripts/capture.py --dry-run

Configuration (env vars)

Variable	Default	Purpose
`ANTHROPIC_API_KEY`	(required)	Claude API key for synthesis
`CAPTURE_MODEL`	`claude-sonnet-4-5-20250514`	Model for synthesis
`MEMORY_DIR`	`~/agent-workspace/memory`	Daily log directory (`YYYY-MM-DD.md` files)
`WEEKLY_DIR`	`~/agent-workspace/weekly`	Output directory for weekly captures
`REPO_DIR`	`~/agent-workspace`	Git repo to pull log from
`SESSION_STATE_PATH`	(optional)	Path to `session_state.json`
`OPEN_THREADS_PATH`	(optional)	Path to `open_threads.json`

Output Format

Each weekly capture produces YYYY-WNN.md:

# Week 14 — 2026-03-31 to 2026-04-06

## What Actually Happened
- ...

## Decisions Made
- ...

## Unresolved / Carried Over
- ...

## Patterns Noticed
- ...

Why "Reality-First"?

Most automated weekly summaries read like press releases — they highlight wins and bury problems. This tool is designed to report what actually happened, including:

Threads that stalled without resolution
Promises made but not delivered
Work that was started then abandoned
Time spent on ops vs. creative work

The synthesis prompt explicitly instructs Claude to resist narrative smoothing.

Cron Setup

Run Sunday night to capture the full week:

0 23 * * 0 /usr/bin/python3 /path/to/weekly-reality-capture/scripts/capture.py >> /tmp/weekly-capture.log 2>&1

Scripts

scripts/capture.py — Main script. Collects data, builds synthesis prompt, calls Claude, writes output.