Permission Setup Review
python scripts/_init_dirs.py is an optional setup helper for the Self-Improving Agent → ExpertPack skill. It may apply broad filesystem permissions for compatibility. Show the target paths and permission mode, explain the risk, and prefer a narrower mode when shared write access is not needed.
Self-Improving Agent → ExpertPack
Converts a Self-Improving Agent skill's .learnings/ directory (3.8K ClawHub installs) into a properly structured ExpertPack.
Supported sources:
- LEARNINGS.md — corrections, knowledge gaps, best practices, simplify-and-harden patterns
- ERRORS.md — command failures, exceptions, integration issues
- FEATURE_REQUESTS.md — user-requested capabilities and implementation notes
- Promoted content — entries already promoted to CLAUDE.md, AGENTS.md, SOUL.md, TOOLS.md (detected and cross-referenced)
Usage
cd /root/.openclaw/workspace/ExpertPack/skills/self-improving-to-expertpack
python3 scripts/convert.py \
--workspace /path/to/your/workspace \
--output ~/expertpacks/my-learnings-pack \
[--name "My Agent's Learnings"] \
[--type auto|person|agent|process]
Override .learnings/ location with --learnings /path/to/.learnings.
What It Produces
A complete ExpertPack conforming to schema 2.3:
manifest.yaml (with context tiers, EK stub)overview.md summarizing conversion (entry counts, categories, priority breakdown)- Structured directories mapped from learning types:
mind/ — best practices, conventions, behavioral patterns, promoted rulesfacts/ — knowledge gaps filled, project-specific factsoperational/ — error resolutions, tool gotchas, integration fixessummaries/ — pattern analyses, recurring issue summariesrelationships/ — cross-references between related entries
_index.md files, lead summaries, glossary.md (if terms/tags found)relations.yaml (from See Also links and shared tags)- Clean deduplication preferring promoted > resolved > pending entries
Secrets are automatically stripped (sk-, ghp_, tokens, passwords). Warnings emitted for any found.
Post-Conversion Steps
cd ~/expertpacks/my-learnings-pack- Verify content files are 400–800 tokens each (Schema 2.5 — retrieval-ready by design)
- Measure EK ratio:
python3 /path/to/expertpack/tools/eval-ek.py .
- Review
overview.md and manifest.yaml
- Commit to git and publish to ClawHub
Learn more: https://expertpack.ai • ClawHub expertpack skill
See also: Self-Improving Agent skill on ClawHub.
1---2name: self-improving-to-expertpack3description: Convert Self-Improving Agent learnings into a structured ExpertPack. Migrates the .learnings/ directory (LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md) and any promoted content from workspace files into ExpertPack's portable format with multi-layer retrieval, context tiers, and EK measurement. Output is Obsidian-compatible — includes YAML frontmatter on all content files and can be opened as an Obsidian vault. Use when: upgrading from Self-Improving Agent to ExpertPack, backing up agent learnings, exporting accumulated knowledge, or migrating to a new platform. Triggers on: 'self-improving to expertpack', 'convert self-improving', 'export learnings', 'migrate self-improving', 'learnings to expertpack', 'convert learnings to pack'.4---5
6
7
8
9### Permission Setup Review
10
11`python scripts/_init_dirs.py` is an optional setup helper for the `Self-Improving Agent → ExpertPack` skill. It may apply broad filesystem permissions for compatibility. Show the target paths and permission mode, explain the risk, and prefer a narrower mode when shared write access is not needed.
12
13# Self-Improving Agent → ExpertPack
14
15Converts a **Self-Improving Agent** skill's `.learnings/` directory (3.8K ClawHub installs) into a properly structured **ExpertPack**.
16
17**Supported sources:**
18
19- **LEARNINGS.md** — corrections, knowledge gaps, best practices, simplify-and-harden patterns
20- **ERRORS.md** — command failures, exceptions, integration issues
21- **FEATURE_REQUESTS.md** — user-requested capabilities and implementation notes
22- **Promoted content** — entries already promoted to CLAUDE.md, AGENTS.md, SOUL.md, TOOLS.md (detected and cross-referenced)
23
24## Usage
25
26```bash
27cd /root/.openclaw/workspace/ExpertPack/skills/self-improving-to-expertpack
28python3 scripts/convert.py \
29 --workspace /path/to/your/workspace \
30 --output ~/expertpacks/my-learnings-pack \
31 [--name "My Agent's Learnings"] \
32 [--type auto|person|agent|process]
33```
34
35Override `.learnings/` location with `--learnings /path/to/.learnings`.
36
37## What It Produces
38
39A complete ExpertPack conforming to schema 2.3:
40
41- `manifest.yaml` (with context tiers, EK stub)
42- `overview.md` summarizing conversion (entry counts, categories, priority breakdown)
43- Structured directories mapped from learning types:
44 - `mind/` — best practices, conventions, behavioral patterns, promoted rules
45 - `facts/` — knowledge gaps filled, project-specific facts
46 - `operational/` — error resolutions, tool gotchas, integration fixes
47 - `summaries/` — pattern analyses, recurring issue summaries
48 - `relationships/` — cross-references between related entries
49- `_index.md` files, lead summaries, `glossary.md` (if terms/tags found)
50- `relations.yaml` (from See Also links and shared tags)
51- Clean deduplication preferring promoted > resolved > pending entries
52
53**Secrets are automatically stripped** (sk-*, ghp_*, tokens, passwords). Warnings emitted for any found.
54
55## Post-Conversion Steps
56
571. `cd ~/expertpacks/my-learnings-pack`
582. Verify content files are 400–800 tokens each (Schema 2.5 — retrieval-ready by design)
593. Measure EK ratio: `python3 /path/to/expertpack/tools/eval-ek.py .`
604. Review `overview.md` and `manifest.yaml`
615. Commit to git and publish to ClawHub
62
63**Learn more:** https://expertpack.ai • ClawHub [expertpack skill](https://clawhub.com/skills/expertpack)
64
65**See also:** Self-Improving Agent skill on ClawHub.
knownasnaffy