Actualize
/install actualize
Actualize Knowledge Base
This command is a core part of maintaining a living assurance case. It keeps your FPF knowledge base (.fpf/) in sync with the evolving reality of your project's codebase.
The command performs a three-part audit against recent git changes to surface potential context drift, stale evidence, and outdated decisions. This aligns with the Observe phase of the FPF Canonical Evolution Loop (B.4) and helps manage Epistemic Debt (B.3.4).
Action (Run-Time)
Step 1: Check Git Changes
Run git commands to identify changes since last actualization:
# Get current commit hash
git rev-parse HEAD
# Check for changes since last known baseline
# (Read .fpf/.baseline file if it exists, otherwise use initial commit)
git diff --name-only \x3Cbaseline_commit> HEAD
# List all changed files
git diff --stat \x3Cbaseline_commit> HEAD
Step 2: Analyze Report for Context Drift
-
Review changed files for core project configuration:
package.json,go.mod,Cargo.toml,requirements.txtDockerfile,docker-compose.yml.env.example, config files
-
If configuration files changed:
- Re-read project structure (README, config files)
- Compare detected context with
.fpf/context.md - Present diff to user
-
Ask user if they want to update
context.md
Step 3: Analyze Report for Evidence Staleness (Epistemic Debt)
- Read all evidence files in
.fpf/evidence/ - Check
carrier_reffield in each evidence file - Cross-reference with changed files from git diff
- If a referenced file changed:
- Flag the evidence as STALE
- Note which hypothesis is affected
Step 4: Analyze Report for Decision Relevance
- Read all DRR files in
.fpf/decisions/ - Trace back to source evidence and hypothesis files
- If foundational files changed:
- Flag the DRR as POTENTIALLY OUTDATED
Step 5: Update Baseline
Create/update .fpf/.baseline file:
# FPF Actualization Baseline
# Last actualized: 2025-01-15T16:00:00Z
commit: abc123def456
Step 6: Present Findings
Output a structured report:
## Actualization Report
**Baseline**: abc123 (2025-01-10)
**Current**: def456 (2025-01-15)
**Files Changed**: 42
### Context Drift
The following configuration files have changed:
- package.json (+5 dependencies)
- Dockerfile (base image updated)
**Action Required**: Review and update `.fpf/context.md` if constraints have changed.
### Stale Evidence (3 items)
| Evidence | Hypothesis | Changed File |
|----------|------------|--------------|
| ev-benchmark-api | api-optimization | src/api/handler.ts |
| ev-test-auth | auth-module | src/auth/login.ts |
| ev-perf-db | db-indexing | migrations/002.sql |
**Action Required**: Re-validate to refresh evidence for affected hypotheses.
### Decisions to Review (1 item)
| DRR | Affected By |
|-----|-------------|
| DRR-2025-01-10-api-design | src/api/handler.ts changed |
**Action Required**: Consider re-evaluating decision via `/fpf:propose-hypotheses`.
### Summary
- Context drift detected: YES
- Stale evidence: 3 items
- Decisions to review: 1 item
Run `/fpf:decay` for detailed freshness management.
File: .fpf/.baseline
Track the last actualization point:
# FPF Actualization Baseline
last_actualized: 2025-01-15T16:00:00Z
commit: abc123def456789
branch: main
When to Run
- Before starting new work: Ensure knowledge base is current
- After major changes: Sync evidence with code changes
- Weekly maintenance: Part of regular hygiene
- Before decisions: Ensure evidence is still valid
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install actualize - 安装完成后,直接呼叫该 Skill 的名称或使用
/actualize触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
Actualize 是什么?
Reconcile the project's FPF state with recent repository changes. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 73 次。
如何安装 Actualize?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install actualize」即可一键安装,无需额外配置。
Actualize 是免费的吗?
是的,Actualize 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Actualize 支持哪些平台?
Actualize 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Actualize?
由 hahamumu08(@hahamumu08)开发并维护,当前版本 v1.0.0。