SKILLEMALL.ai
GitHub ↗ RU Sign in

DF skill-evolution

技能进化（知行环，英文 id `skill-evolution`）——Agent 经验沉淀与自改进闭环框架，把 WikiSkill（arXiv:2608.27454）的经验存储机制与 RSI 路线图（arXiv:2609.11873）的能力判据合成为一条可运行闭环：HCI 选域 → 三层记忆沉淀 → 原子化提议 → 四大追问门控 → 可回滚迭代 → 自主权升阶。支持 WorkBuddy / CodeBuddy / Claude Code / Codex 四平台与 Windows / Linux / macOS。当用户报出「技能进化」或别号「知行环」，或要求经验复盘、记录轨迹、能力评估、自改进闭环设计、自主性分级，或引用 RSI / HCI / WikiSkill 相关概念时触发。

ClawHub Agent Skills author: xxoyt v0.1.0 MIT-0 21 files · 7 scripts body ≈ 3 577 tokens Open the sourceclawhub.ai↗ analyzed 13 d ago

技能进化（知行环，英文 id skill-evolution）——Agent 经验沉淀与自改进闭环框架，把 WikiSkill（arXiv:2608.27454）的经验存储机制与 RSI 路线图（arXiv:2609.11873）的能力判据合成为一条可运行闭环：HCI 选域 → 三层记忆沉淀 → 原子化提议 →…

As a process F 30/100 · No process to follow — References files that are not bundled: scripts/wikiskill/, scripts/skill-evolution/wiki_remind.py

ProcedureSoftware developmentAI and agentsResearchtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
D
75/100
safety, quality, tests
Safety 60%
81
Quality 40%
66
Run on models
none yet
Process rating
F
30/100
No process to follow
References files that are not bundled: scripts/wikiskill/, scripts/skill-evolution/wiki_remind.py
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 7

✓ No critical or high findings

Medium and low: 7
  • medium Dangerous commands cmd-execpolicy-bypass references/AGENTS.template.md:99
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File "<skill目录>\scripts\wiki…ps1"
  • medium Dangerous commands cmd-execpolicy-bypass references/CLAUDE.template.md:99
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File "<skill目录>\scripts\wiki…ps1"
  • medium Dangerous commands cmd-execpolicy-bypass references/platforms.md:38
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File "$SKILL_DIR\scripts\wiki…ps1"
  • low Dangerous commands cmd-execpolicy-bypass README.md:140
    Runs PowerShell with execution policy bypassed (documentation table row)
    | 无 Python 的 Windows | `powershell -ExecutionPolicy Bypass -File "解压目录\scripts\wiki…ps1"` |
    table
  • low Dangerous commands cmd-execpolicy-bypass scripts/install.py:264
    Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
    powershell -ExecutionPolicy Bypass -File .wiki\\scripts\\wiki…ps1
    quoted
  • low Dangerous commands cmd-execpolicy-bypass scripts/wiki_init.ps1:4
    Runs PowerShell with execution policy bypassed (code comment)
    #   powershell -ExecutionPolicy Bypass -File wiki…ps1
    comment
  • low Dangerous commands cmd-execpolicy-bypass scripts/wiki_init.ps1:5
    Runs PowerShell with execution policy bypassed (code comment)
    #   powershell -ExecutionPolicy Bypass -File wiki…ps1 -Root "D:\proj"
    comment

Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: scripts/wikiskill/
  • warning missing-ref reference to a missing file: scripts/skill-evolution/wiki_remind.py
  • note frontmatter-key unknown frontmatter key "display_name"
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 30/100

Will not run. References files that are not bundled: scripts/wikiskill/, scripts/skill-evolution/wiki_remind.py
  • 0Tools and files. 2 referenced file(s) missing: scripts/wikiskill/, scripts/skill-evolution/wiki_remind.py
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 3 mutating operations with no state check
  • 40Consistency. Frontmatter name (skill-evolution) differs from the folder (skill-evolution-2)
  • 100Steps. 26 steps
  • 100Execution cost. Instruction body is 3577 tokens
  • 100Progress reporting. Reports progress
  • low 15 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -230 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 344: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 26 items
  • +4Has examples (13 code blocks)
  • +4Reference files are cited in the instructions (9 of 9)
  • +3All 7 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
The skill is a disclosed project wiki tool, but its Claude hook can persistently run scripts from a mutable project directory, so it should be reviewed before installation.
LLM: suspicious (high) · 23 Sept 2026