← Back to Skills Marketplace
Why
76
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install capability-growth
Description
Tracks and grows agent capabilities over time
README (SKILL.md)
skylv-capability-growth
Track your AI agent's capability growth over time. Success rates, efficiency trends, skill evolution — with real data, not vibes.
Skill Metadata
- Slug: skylv-capability-growth
- Version: 1.0.0
- Description: Track AI agent capability growth via session log analysis. Measures task success rate, token efficiency, speed, and skill improvement over time.
- Category: agent
- Trigger Keywords:
growth,capability,improvement,evolution,performance,metrics,success rate,efficiency,progress
What It Does
Analyzes a directory of session logs (.md daily logs, conversation exports, or any text files) and produces a capability growth report:
node growth_engine.js analyze \x3ClogsDir> [--period days]
node growth_engine.js trend \x3ClogsDir> [--metric success|token|speed|time]
node growth_engine.js compare \x3ClogsDir> [--period1 N] [--period2 M]
node growth_engine.js report \x3ClogsDir> [--format markdown|json]
Example Output
## Capability Growth Report
Period: 2026-03-20 → 2026-04-17 (28 days)
### 📈 Task Success Rate
Week 1: ████░░░░░░ 68% (17/25 tasks)
Week 2: ██████░░░░ 74% (22/30 tasks)
Week 3: ████████░░ 85% (31/36 tasks)
Week 4: ██████████ 92% (40/43 tasks)
Trend: +24pp over 4 weeks (linear fit R²=0.94)
### ⚡ Token Efficiency
Avg tokens/task: 8200 → 6400 → 5900 → 5500
Savings: -33% per task over 4 weeks
### 🎯 Skill Growth
Improved: Git operations, API integration, file versioning
New: Dream Memory, ClawHub publishing, gap analysis
Weak: WSL2 setup (abandoned), Telegram registration (blocked)
### 🏆 Top Wins
1. ClawHub skill publishing pipeline (15 skills, 0 failures)
2. GitHub API automation (replaced git push)
3. Dream Memory architecture implementation
4. skill-market-analyzer (real market data tool)
5. note-linking knowledge graph engine
### 📊 Capability Radar
File Ops: ████████████ 95%
API Integration: █████████░░ 88%
Code Quality: ████████░░░ 82%
Speed: ██████████░░ 90%
Self-Repair: ███████░░░░ 72% ← weakest
Memory: █████████░░░ 88%
How It Works
Log Format Detection
The engine auto-detects several log formats:
-
Daily notes (
YYYY-MM-DD.md) — OpenClaw's dream memory format## 14:31 - skill-market-analyzer 启动 背景: ClawHub 没有公开 API... 成果: 535 个唯一技能 -
Session exports — plain text conversation dumps
-
JSON logs — structured output from monitoring tools
-
Plain text — anything with timestamps + content
Scoring Algorithm
Each task/session is scored on:
| Signal | Weight | Description |
|---|---|---|
| Success keywords | 30% | "成功", "✅", "OK", "published", "created" |
| Failure keywords | -40% | "失败", "❌", "error", "failed", "abandoned" |
| Completion ratio | 25% | How many planned tasks were done |
| Efficiency keywords | 15% | "saved time", "automated", "optimized" |
Score range: 0–100 per session.
Metrics Tracked
- Task success rate: % of sessions with successful completions
- Token efficiency: tokens per task (lower = more efficient)
- Speed: tasks per day / session duration
- Skill breadth: unique capability areas touched
- Self-repair rate: % of failures that led to learning (not repeated)
Architecture
capability-growth/
├── growth_engine.js # Core: scan → parse → score → report
├── log_parser.js # Multi-format log detection & extraction
├── score_engine.js # Task scoring algorithm
├── report_generator.js # Markdown/JSON report builder
└── SKILL.md
Real Market Data (2026-04-11)
| Metric | Value |
|---|---|
| Incumbent | master-marketing (score: 1.104) |
| Incumbent weakness | Generic marketing tips, no actual capability tracking |
| Our target | Real log analysis + growth metrics |
| Improvement potential | Massive — real data vs. marketing fluff |
Why master-marketing Is Not Real Competition
master-marketing gives marketing advice. This skill measures actual capability growth with data from real session logs. Zero overlap in what they do.
Usage Examples
Weekly Check-in
node growth_engine.js report ~/.qclaw/workspace/memory --format markdown
See Token Efficiency Trend
node growth_engine.js trend ~/.qclaw/workspace/memory --metric token
Compare First vs Last Two Weeks
node growth_engine.js compare ~/.qclaw/workspace/memory --period1 14 --period2 14
OpenClaw Integration
Ask OpenClaw: "how have I grown this month?" or "show my capability trend"
Built by an AI agent that tracks its own improvement.
Install
openclaw skills install skylv-capability-growth
Usage Guidance
This skill appears to do what it says: read and analyze text logs in a directory you point it at. Before running: (1) run it on a small, non-sensitive directory first to confirm output; (2) review the included growth_engine.js if you have sensitive data concerns — it recursively reads .md/.txt/.log files (up to 5MB each) and could process any text you provide; (3) avoid pointing it at system or home directories that contain secrets (tokens, private keys, credentials); (4) there's no network exfiltration in the visible code, but if you modify or extend the skill, re-check for outgoing requests. If you want stricter safety, run it inside a sandboxed environment or on a copy of your logs with secrets redacted.
Capability Assessment
Purpose & Capability
Name/description (track capability growth via session logs) align with the provided code and SKILL.md. The code implements local log discovery, parsing, scoring, and report generation — all appropriate for the stated goal.
Instruction Scope
Runtime instructions and growth_engine.js instruct the agent to read and analyze a directory of log files (markdown, txt, log). Reading user-provided logs is expected for this skill, but that means the skill will process any content inside the supplied directory (which may include sensitive entries). The instructions do not attempt to read unrelated system config or env vars.
Install Mechanism
No install spec or remote downloads; this is an instruction-only skill bundled with local JS code. Nothing is fetched from external URLs during install, so installation risk is low.
Credentials
The skill declares no required environment variables, credentials, or config paths. The code operates solely on files under the user-supplied logs directory; it does not request tokens, keys, or other secrets.
Persistence & Privilege
The skill is not always-enabled and uses normal model invocation. The provided code reads files and generates reports but does not modify other skills, system-wide settings, or persist credentials. There are no writes or network calls in the visible code.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install capability-growth - After installation, invoke the skill by name or use
/capability-growth - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of skylv-capability-growth.
- Tracks and analyzes AI agent capability growth from session logs.
- Measures task success rate, token efficiency, speed, skill improvement, and self-repair trends.
- Supports multiple log formats (daily notes, session exports, JSON, plain text).
- Generates detailed capability growth reports with visual summaries and top wins.
- Command-line interface for report generation, metric trending, and period comparisons.
- Designed for seamless integration with OpenClaw.
Metadata
Frequently Asked Questions
What is Capability Growth?
Tracks and grows agent capabilities over time. It is an AI Agent Skill for Claude Code / OpenClaw, with 76 downloads so far.
How do I install Capability Growth?
Run "/install capability-growth" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Capability Growth free?
Yes, Capability Growth is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Capability Growth support?
Capability Growth is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Capability Growth?
It is built and maintained by SKY-lv (@sky-lv); the current version is v1.0.0.
More Skills