一键在 Manus 中运行任何 Skill

prior-day-summary

星标1

分支0

更新时间2026年6月19日 19:22

Produce changelog-first, evidence-backed summaries of prior-day work for prompts like "what we did yesterday", "what shipped yesterday", "what changed yesterday", "what was visibly different", and "how do I try it". Use this skill for daily automation reports, release-adjacent status synthesis, empty-day audits, and branch-local versus shipped reconciliation. Progressive disclosure: classify the day first, then load only the workflow docs needed for visible-surface analysis, debt/wins framing, or visual-summary output.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

miethe

miethe/research-foundry

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

prior-day-summary Skill

High-level router for prior-day delivery summaries. Keep the main path shell-first, evidence-first, and model-agnostic. For the formal capability contract see ./SPEC.md.

Route Table

User Intent	Workflow Doc	Canonical Doc
Summarize what we did yesterday	`./workflows/core-workflow.md`	`./README.md`
Prove what actually shipped yesterday	`./workflows/provenance-rules.md`	`CHANGELOG.md`, `docs/current-state.md`
Separate user-visible changes from internal work	`./workflows/visible-surface-pass.md`	`./references/phrasing-rules.md`
Explain how to try the changes as a user	`./workflows/visible-surface-pass.md`	`./references/command-reference.md`
Choose short/full/audit/visual output modes	`./workflows/output-modes.md`	`./templates/standard-summary.md`
Render a deterministic first draft from shell evidence	`./workflows/core-workflow.md`	`./scripts/render_prior_day_summary.py --help`

Policy

Core Guardrails

Check the exact date window before doing any storytelling.
Let git date-window evidence outrank plan docs, memory, and adjacent narrative.
Treat dated changelog headings and origin/main history as shipping sanity checks, not as standalone proof.
Keep empty days empty.
Label docs-only or planning-only work explicitly.
Never describe branch-local work as shipped unless origin/main, a tag, or a dated changelog section proves it.

Progressive Disclosure

Start with ./workflows/core-workflow.md.
Load ./workflows/provenance-rules.md when shipped versus branch-local status is ambiguous.
Load ./workflows/visible-surface-pass.md only when real visible surfaces exist or the user explicitly asks for try-it steps.
Load ./workflows/output-modes.md only when the answer needs a specific format such as audit-style or visual-companion output.

Quick Commands

# Collect deterministic evidence for one date window
python3 .Codex/skills/prior-day-summary/scripts/collect_window_evidence.py --date 2026-05-19

# Render a first-pass markdown summary from collected evidence
python3 .Codex/skills/prior-day-summary/scripts/render_prior_day_summary.py \
  --input /tmp/prior-day-summary.json

Read-Only Default

The summary path is read-only by default. Writing reports, saving rendered output, or copying visual assets is allowed only when the surrounding task explicitly asks for durable artifacts.

同仓库更多 Skills

同仓库

research-foundry

miethe/research-foundry

Drives the Research Foundry control plane — a Markdown/YAML-first research pipeline that captures an idea, routes it through source discovery, claim mapping, synthesis, and deterministic verification, then publishes an evidence bundle. Use when the operator wants to run, plan, or audit an end-to-end research run with the `rf` CLI, or wants claim-traceable, governance-gated research instead of a freehand answer.

2026-07-101

research-foundry-swarm

miethe/research-foundry

Installs and initializes a Research Foundry workspace from scratch, then orchestrates a Claude Code agent swarm to produce a claim-verified evidence bundle. Covers the uv-tool install, `rf init`, `rf doctor` bootstrap sequence; the two swarm-drive patterns (RF-native `rf swarm run` vs. Claude-Code-orchestrated discovery feeding `rf ingest`); the deterministic tail that converts raw sources into a verified, governance-gated report; and key-profile governance. Cross-links the `research-foundry` skill for the full 21-step pipeline loop and per-command reference. Use when an agent needs to stand up a Research Foundry workspace from scratch or orchestrate a Claude Code agent swarm into a claim-verified evidence bundle.

2026-07-101

dev-execution

miethe/research-foundry

Unified execution engine for all development workflows. Progressive disclosure for phase execution, quick features, story completion, and scaffolding. Integrates with artifact-tracking and meatycapture-capture. Use when running /dev:execute-phase, /dev:quick-feature, /dev:implement-story, /dev:complete-user-story, or /dev:create-feature commands.

2026-06-251

planning

miethe/research-foundry

Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 lines), or setting up progress tracking. Supports: 1) Create PRD from feature request, 2) Create Implementation Plan from PRD with phase breakdown and subagent assignments, 3) Optimize existing plans by breaking into phase-specific files, 4) Create progress tracking with task assignments. Example: "Create a PRD for user authentication feature" or "Break down the sidebar-polish implementation plan into phase files" or "Create progress tracking for data-layer-fixes PRD".

2026-06-251

symbols

miethe/research-foundry

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.

2026-06-221

artifact-tracking

miethe/research-foundry

Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.

2026-06-191

name	prior-day-summary
description	Produce changelog-first, evidence-backed summaries of prior-day work for prompts like "what we did yesterday", "what shipped yesterday", "what changed yesterday", "what was visibly different", and "how do I try it". Use this skill for daily automation reports, release-adjacent status synthesis, empty-day audits, and branch-local versus shipped reconciliation. Progressive disclosure: classify the day first, then load only the workflow docs needed for visible-surface analysis, debt/wins framing, or visual-summary output.
version	0.1.0
updated	"2026-05-20T00:00:00.000Z"
spec	./SPEC.md
status	active

prior-day-summary Skill

High-level router for prior-day delivery summaries. Keep the main path shell-first, evidence-first, and model-agnostic. For the formal capability contract see ./SPEC.md.

Route Table

User Intent	Workflow Doc	Canonical Doc
Summarize what we did yesterday	`./workflows/core-workflow.md`	`./README.md`
Prove what actually shipped yesterday	`./workflows/provenance-rules.md`	`CHANGELOG.md`, `docs/current-state.md`
Separate user-visible changes from internal work	`./workflows/visible-surface-pass.md`	`./references/phrasing-rules.md`
Explain how to try the changes as a user	`./workflows/visible-surface-pass.md`	`./references/command-reference.md`
Choose short/full/audit/visual output modes	`./workflows/output-modes.md`	`./templates/standard-summary.md`
Render a deterministic first draft from shell evidence	`./workflows/core-workflow.md`	`./scripts/render_prior_day_summary.py --help`

Policy

Core Guardrails

Check the exact date window before doing any storytelling.
Let git date-window evidence outrank plan docs, memory, and adjacent narrative.
Treat dated changelog headings and origin/main history as shipping sanity checks, not as standalone proof.
Keep empty days empty.
Label docs-only or planning-only work explicitly.
Never describe branch-local work as shipped unless origin/main, a tag, or a dated changelog section proves it.

Progressive Disclosure

Start with ./workflows/core-workflow.md.
Load ./workflows/provenance-rules.md when shipped versus branch-local status is ambiguous.
Load ./workflows/visible-surface-pass.md only when real visible surfaces exist or the user explicitly asks for try-it steps.
Load ./workflows/output-modes.md only when the answer needs a specific format such as audit-style or visual-companion output.

Quick Commands

# Collect deterministic evidence for one date window
python3 .Codex/skills/prior-day-summary/scripts/collect_window_evidence.py --date 2026-05-19

# Render a first-pass markdown summary from collected evidence
python3 .Codex/skills/prior-day-summary/scripts/render_prior_day_summary.py \
  --input /tmp/prior-day-summary.json

Read-Only Default

The summary path is read-only by default. Writing reports, saving rendered output, or copying visual assets is allowed only when the surrounding task explicitly asks for durable artifacts.