Explain Why
Answer 'why is X in my priorities/activities/signals/drift alerts?' by tracing a brief item back to its source signals and breadcrumbs.
Skill by YuiZhou
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yuizhou-explain-why
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/explain-why
What's inside
- Skill name
Explain Why- Description
- Answer 'why is X in my priorities/activities/signals/drift alerts?' by tracing a brief item back to its source signals and breadcrumbs.
- License
- MIT
- Instructions
- 89 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Explain Why" does not match folder "dayarc-explain-why"
Files (1)
- SKILL.md
SKILL.md (first lines)
## When to Use
Invoke this skill when the user asks a question matching any of these patterns (case-insensitive):
- "why is [item] in my priorities?"
- "why did [item] show up?"
- "where does [item] come from?"
- "what signals produced [item]?"
- "why am I seeing [item]?"
- Any question containing "why" paired with a named item from a brief (priority, activity, drift alert, or signal).
## Output
Render to terminal only. Do NOT send email or write to memory.
```
📍 Why "[item name]"?
Source breadcrumb: [source_breadcrumb]
Urgency / relevance: [urgency or relevance score]
Pass reason: [pass_reason, if applicable]
This item was produced by: [skill name]
Found in: [memory file and field path]
```
If multiple breadcrumbs exist (e.g., item appears in both priorities and activities), show all of them.
## Instructions
### Step 1 — Parse the item name
Extract the subject noun phrase from the user's question. For example:
- "Why is auth migration in my priorities?" → `auth migration`
- "Why did the cost review show up?" → `cost review`
- "Where does ARM CI pipeline come from?" → `ARM CI pipeline`
### Step 2 — Search memory (most-recent first)
Search the following memory files in order, stopping as soon as the item is found. Use the **dayarc-memory** skill to read each file. Match by fuzzy keyword overlap (not exact string match).
1. **`daily/daily-profile-{today}.json`** — check these fields:
- `priorities_today[].description` + `priorities_today[].source_breadcrumb` (produced by `infer_priorities`)
- `unfinished[].description` + `unfinished[].source_breadcrumb` (produced by `learn_user_profile`)
- `active_threads[].subject` + `active_threads[].source_breadcrumb`
- `impact_summaries[]` across `title`, `situation`, `task`, `action`, `result`, and `impact`, plus
`source_breadcrumbs[]` (produced by `write_impact_summary`)
2. **`weekly-summary-current.json`** — check:
- `themes[].label` + any breadcrumbs stored under activities for that theme
- `stuck[].description` + `stuck[].source_breadcrumb`
- `impact_summaries[]` + `source_breadcrumbs[]`
3. **`monthly-summary.json`** — check:
- `themes[].label` + activity breadcrumbs
- `stuck[].description` + `stuck[].source_breadcrumb`
- `impact_summaries[]` + `source_breadcrumbs[]`
4. **Recent daily profiles** — if today's profile has no match, try the previous 3 days:
`daily/daily-profile-{yesterday}.json`, `{day-2}.json`, `{day-3}.json`.
In each, check `priorities_today`, `unfinished`, `active_threads`, and `impact_summaries` as above.
### Step 3 — If item not found in memory
If no match is found across all memory files, say:
> I couldn't find "[item]" in your recent memory (last 3 days, current weekly, current monthly). It may be from an older brief or may have been removed. Try asking about a specific date, e.g. "why was auth migration in my priorities on March 20?"
### Step 4 — Render breadcrumbs
Once the item is found, render all available source fields:
- **For priorities** (`infer_priorities` output): show `source_breadcrumb` and `urgency`.
- **For activities** (`classify_activity` output): show `source_breadcrumb` per activity in the theme cluster.
- **For impact summaries** (`write_impact_summary` output): show all `source_breadcrumbs` and identify the matching
situation, task, action, result, or impact field.
- **For drift alerts** (`detect_drift` output): show `source_breadcrumb` (the priority that was neglected) and `days_inactive`.
- **For signals** (`filter_signals` output): show `source_breadcrumb`, `relevance`, and `pass_reason`.
Apply the breadcrumb quality rule: if a breadcrumb contains a Teams meeting thread link (`19:meeting_...@thread.v2`), flag it with ⚠️ and include whatever fallback context (meeting title, date, participants) is stored alongside it.
### Step 5 — Cite the source skill
End the response with a one-line attribution:
> *Produced by `[skill-name]` · found in `[memory-file]` › `[field-path]`*
Example:
> *Produced by `infer_priorities` · found in `daily-profile-2026-03-28.json` › `priorities_today[1]`*From YuiZhou/dayarc-agent, MIT.
More from YuiZhou/dayarc-agent
- 0.546score
Review Prep
YuiZhou
Generate structured talking points for performance reviews, 1:1s, and self-assessments from accumulated monthly summaries.
SkillBFreshness: B★ 2Claude Code +9 - 0.543score
Learn User Profile
YuiZhou
Update the user's daily profile by learning from outgoing signals.
SkillBFreshness: B★ 2Claude Code +9 - 0.543score
Classify Activity
YuiZhou
Group raw activity signals into thematic clusters with effort estimates.
SkillBFreshness: B★ 2Claude Code +9 - 0.543score
Deliver Brief
YuiZhou
Render brief from template and deliver to configured targets (email, GitHub issue, terminal).
SkillBFreshness: B★ 2Claude Code +9 - 0.543score
Write Impact Summary
YuiZhou
Turn work evidence into concise Situation-Task-Action-Result-Impact narratives without inventing outcomes.
SkillBFreshness: B★ 2Claude Code +9 - 0.540score
Summarize Period
YuiZhou
Roll up daily/weekly data into period summaries.
SkillBFreshness: B★ 2Claude Code +9 - 0.493score
Dayarc Memory
YuiZhou
Read and write memory JSON files in the user's dayarc folder.
SkillCFreshness: C★ 2Claude Code +9 - 0.493score
Dayarc Upgrade
YuiZhou
Check for and apply updates to the Dayarc agent package from GitHub.
SkillCFreshness: C★ 2Claude Code +9 - 0.431score
Dayarc Add Connector
YuiZhou
Conversationally configure a new signal source connector (Jira, ADO, Linear, Slack, etc.), generate a custom COLLECT skill, and register it in config.json.
SkillDFreshness: D★ 2Claude Code +9 - 0.428score
Dayarc Report Issue
YuiZhou
Auto-fill and file a GitHub issue on the Dayarc repo with user confirmation.
SkillDFreshness: D★ 2Claude Code +9 - 0.428score
Infer Priorities
YuiZhou
Rank items by urgency into a priority list with source breadcrumbs.
SkillDFreshness: D★ 2Claude Code +9 - 0.428score
Dayarc Setup
YuiZhou
Initialize Dayarc data directories, user config, and optional scheduler on first run or reconfiguration.
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 2
- Open issues
- 7
- Last commit (this folder)
- Aug 26, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/YuiZhou/dayarc-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from YuiZhou
- 0.546score
Review Prep
YuiZhou
Generate structured talking points for performance reviews, 1:1s, and self-assessments from accumulated monthly summaries.
SkillBFreshness: B★ 2Claude Code +9 - 0.543score
Write Impact Summary
YuiZhou
Turn work evidence into concise Situation-Task-Action-Result-Impact narratives without inventing outcomes.
SkillBFreshness: B★ 2Claude Code +9 - 0.543score
Classify Activity
YuiZhou
Group raw activity signals into thematic clusters with effort estimates.
SkillBFreshness: B★ 2Claude Code +9 - 0.543score
Learn User Profile
YuiZhou
Update the user's daily profile by learning from outgoing signals.
SkillBFreshness: B★ 2Claude Code +9 - 0.543score
Deliver Brief
YuiZhou
Render brief from template and deliver to configured targets (email, GitHub issue, terminal).
SkillBFreshness: B★ 2Claude Code +9 - 0.540score
Summarize Period
YuiZhou
Roll up daily/weekly data into period summaries.
SkillBFreshness: B★ 2Claude Code +9
Cite this page
Explain Why skill. Agent Mart. https://agentmart.dev/skills/yuizhou-explain-why (last updated 2026-10-24)