メニュー
Use when asked about project health, velocity, bug trends, or whether we're making progress.
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。
SOC 職業分類に基づく
Rewrite an issue's Implementation Steps, Acceptance Criteria, and Files to Modify in place from its own accumulated research findings, without appending or bulldozing human prose
Use when asked to audit documentation accuracy, coverage, or find documentation gaps.
Use when asked for an adversarial go/no-go review or whether an issue is worth implementing.
Use when asked to manually compact a session's memory, trigger session summarization, or reduce a long session's context footprint.
Use when asked to manually compact a session's memory, trigger session summarization, or reduce a long session's context footprint.
Use when asked to detect conflicting requirements or incompatible decisions across open issues.
| name | analyze-history |
| description | Use when asked about project health, velocity, bug trends, or whether we're making progress. |
| disable-model-invocation | true |
| model | haiku |
| allowed-tools | ["Bash(ll-history:*)"] |
| metadata | {"short-description":"Use when asked about project health, velocity, bug trends, or whether we're maki"} |
This skill helps users understand their issue history and project health trends.
Proactively offer or invoke this skill when the user:
Run the ll-history CLI command based on user needs:
For a basic summary:
ll-history summary
For comprehensive analysis:
ll-history analyze
For a shareable report:
ll-history analyze --format markdown
To compare recent vs previous period:
ll-history analyze --compare 30
Generate architecture documentation from completed issue history:
ll-history export "authentication"
Write to a file with a specific format:
ll-history export "sprint system" --output docs/arch/sprint.md --format structured
Filter by date or issue type:
ll-history export "API layer" --since 2026-01-01 --type ENH
| Format | Command | Best For |
|---|---|---|
| Text | ll-history analyze | Terminal viewing |
| Markdown | ll-history analyze --format markdown | Documentation, sharing |
| JSON | ll-history analyze --format json | Programmatic access |
| YAML | ll-history analyze --format yaml | Config, further processing |
| Period | Command | Use Case |
|---|---|---|
| Weekly | ll-history analyze --period weekly | Short sprints |
| Monthly | ll-history analyze --period monthly | Default, general use |
| Quarterly | ll-history analyze --period quarterly | Long-term trends |
| User Says | Action |
|---|---|
| "How's our project health?" | ll-history analyze |
| "Show me bug trends" | ll-history analyze --format markdown |
| "Compare last month to previous" | ll-history analyze --compare 30 |
| "Are we making progress?" | ll-history analyze --format markdown |
| "What's our velocity?" | ll-history summary |
| "Show quarterly trends" | ll-history analyze --period quarterly |
| "Generate docs about the sprint system" | ll-history export "sprint system" |
| "Document our auth changes since January" | ll-history export "authentication" --since 2026-01-01 |
The full analysis includes:
When .ll/history.db is available, analyze-history includes an Evolution Triggers section with two subsections:
User corrections that have recurred ≥ history.evolution.feedback_min_recurrence times (default: 2) across sessions. Each entry includes:
memory/feedback_* files)Rule Candidates — the recurring corrections most likely to become permanent CLAUDE.md rules — are listed separately for easy copy-paste into CLAUDE.md.
Skills where the user performed the work manually instead of invoking the skill, detected by matching user message content against skill keyword sets. Requires ≥ 2 keyword tokens to match (conservative to reduce false positives). Each entry includes:
Configuration: history.evolution.feedback_min_recurrence and history.evolution.bypass_min_count in .ll/ll-config.json control the thresholds.