Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Memory
skillminer
Try itSuggest reusable skills from recurring patterns in local memory files. Human review gate, drafts only to skills/_pending/, local-first runner with optional external fallback. Triggers on "skill forge", "propose a skill", "what skills should I have", "skill candidates", "what patterns have I been doing", "forge me a skill", "forge show", "forge accept", "forge reject", "forge promote".
What it does
Your AI assistant keeps solving the same problems. skillminer notices and suggests turning them into reusable skills.
The skill document
skillminer ⚒️
Your AI assistant keeps solving the same problems. skillminer notices and suggests turning them into reusable skills.
skillminer watches your local memory files, spots recurring work, and surfaces the patterns worth keeping. No auto-activation, no cloud sync, no noise by default. A morning suggestion in your inbox when something actually deserves to become a skill.
Trust model
- Human gate first, always. Nothing ships without your explicit accept.
- Drafts go to
skills/_pending//, never to live skills. - Default runner is local OpenClaw. No data leaves the host.
FORGE_RUNNER=claudeis an opt-in external fallback that sends prompt data to Anthropic's API.- Notifications are off by default; review files are written locally regardless.
Flow
nightly scan reads recent memory/YYYY-MM-DD.md files
detects recurring task patterns
writes a review file to state/review/
↓
YOU DECIDE forge accept / reject / defer / silence
↓
morning write drafts a SKILL.md into skills/_pending//
you review it, promote it, ship it
Nothing goes live automatically. You stay in control at every step.
Quick start
openclaw skills install skillminer
cd "${CLAWD_DIR:-$HOME/clawd}/skills/skillminer"
bash setup.sh
CLAWD_DIR="${CLAWD_DIR:-$HOME/clawd}" bash scripts/run-nightly-scan.sh
If the manual scan looks good, add the printed scheduler jobs using the dispatcher prompts.
Environment
CLAWD_DIR— optional, defaults to~/clawdFORGE_RUNNER— defaults toopenclaw(local). Set toclaudeonly if you accept that prompt data leaves the host.
Commands
forge is the command prefix.
forge show— list current candidatesforge review— open the latest review fileforge accept— accept a candidate for the next morning writeforge reject "reason"— reject permanentlyforge defer "reason"— defer with cooldownforge silence "reason"— silence without cooldownforge unsilence— resurface a silenced entryforge promote— move a pending draft into live skills
Manual triggers
When you want a one-shot run without remembering full paths:
skillminer scan # run nightly scan now
skillminer write # run morning write now
skillminer full # scan + write in sequence
skillminer status # show current ledger state
skillminer help # show usage
Security
- Slug validation gates every filesystem-path boundary (regex-enforced)
- Atomic state writes with backup rotation and JSON validation
flock-based single-instance guarantee across all entry points- Memory files are treated as untrusted data in the nightly scan prompt
See README.md and USER_GUIDE.md for full docs.
Related skills
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Site audit, content writing, and competitor analysis for organic search rankings.
More from robbyczgw-cla
Browse all skillsGenerate reflective AI diary entries with pattern tracking, quote logs, and weekly digests.
Continuously monitor topics across web search, RSS/Atom feeds, and GitHub releases, alerting only when relevant.
Synthesize speech in 18 voices across 32 languages, generate sound effects, and design custom voices via ElevenLabs.
Three specialized agents tackle your question in parallel and optionally cross-examine each other before synthesis.
Fetch YouTube transcripts from cloud IPs without getting blocked by bot detection.
Get three context-aware follow-up questions after any AI response, grouped into quick, deep-dive, and related.