agentsclimarketplace
Sign in

Skill updater

Skill BioTender-max/awesome-bio-agent-skills/skills/neuroclaw/skill-updater

Use this skill after a task succeeds (user confirms 'success' or tools report success). It extracts new experience from the session log + daily memory, locates relevant skills, and proposes diff-formatted updates to SKILL.md files with a clear summary for the user.From its SKILL.md

Install
npx -y skills add BioTender-max/awesome-bio-agent-skills --skill skill-updater

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT License (NeuroClaw custom skill - freely modifiable within the project). That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, 525 tokens by cl100k_base, as published. Nobody here has run it

Skill Updater (Experience-to-Skill Diff)

Overview

skill-updater turns successful task execution into reusable skill improvements.

It reads the session log and daily memory, extracts new experience (what worked, new patterns, edge cases), identifies the most relevant skill files, and produces diff-formatted update suggestions for SKILL.md.

This skill follows NeuroClaw hierarchy:

  • Defines WHAT to do, not low-level implementation details.
  • Does not execute direct shell commands itself.
  • Delegates any file scanning or execution via helper skills.

When to Call This Skill

  • Task just finished successfully and user confirms "success".
  • A tool returns a success status and experience should be recorded.
  • Repeated tasks indicate missing instructions or edge-case guidance.

Core Workflow (Never Bypassed)

  1. Read the session log and the relevant daily memory.
  2. Extract new experience:
    • what worked
    • new patterns
    • edge cases solved
  3. Identify the most relevant skill(s):
    • Use skill-creator to scan workspace/skills/ if available.
    • If not available, request a list of relevant skill files from the user.
  4. Draft diff-formatted changes for the target SKILL.md:
    • Explicitly state: "New experience X: previously missing Y, now add Z."
    • Specify which sections change: instructions / examples / error handling.
  5. Present a clear summary + patch to the user.

Required Output Format

Always include:

  1. A concise summary list of new experience.
  2. A target skill name.
  3. A diff block for each proposed update.

Example output:

""" This successful task yields new experience:

  1. ...
  2. ...

Suggested update for skill xxx (diff):

@@
- Old line
+ New line

"""

Evidence Sources

  • Session log (task execution trace)
  • Daily memory (recent patterns and outcomes)

Safety and Execution Policy

  • Never write changes directly; only propose diffs.
  • Do not update unrelated skills.
  • Do not invent results; only use observed success outcomes.

Complementary / Related Skills

  • multi-search-engine
  • dependency-planner

Created At: 2026-03-30 18:39 HKT Last Updated At: 2026-03-30 18:39 HKT Author: chengwang96

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.