Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    self update skills

    1

    Maintain and modernize agent skills through evidence-backed audits and structured, human-approved updates.

    Free

    1 useSecurity scanned
    self update skills

    self update skills

    Example session with this skill installed

    Audit the current weather-retrieval skill. I noticed the OpenWeather API changed their endpoint structure last week. Research the new docs and propose a fix.

    • Read your context and instructions
    • Compiled the self update

    I have audited the `weather-retrieval` skill against the latest OpenWeather API documentation (v3.0). The current skill uses the deprecated v2.5 endpoint which will be sunset next month. ## Skill Update Proposal: weather-retrieval | Category | Detail | | :--- | :--- | | **Target Skill** | `skills/weather-retrieval/SKILL.md` | | **Trigger** | API Deprecation (OpenWeather v2.5 to v3.0 One Call API) | | **Source** | [OpenWeather v3.0 Docs](https://openweathermap.org/api/one-call-3) (Verified 2023-10-27) | | **Changes** | Update base URL to `/data/3.0/onecall`; add `tz` parameter; remove `sys.type` check. | | **Risk** | Low. Requires updated API key permissions for One Call 3.0. | | **Validation** | Run `tests/test-weather-api.sh` against the new endpoint. | **Proposed Edits:** - Update `## How it works` Step 2 to reflect the new URL structure. - Modify `## Frameworks & tools` to specify One Call API 3.0 compatibility. - Add a rollback point to `v2.5-legacy` tag in Git. **Next steps** 1. Confirm you have upgraded your OpenWeather API key to support the One Call 3.0 subscription. 2. Grant permission to apply these edits to `SKILL.md` and the associated `api-client.js`. 3. Verify the update by running the integration test suite.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Agent skills rot as APIs change, new features launch, or workflows fail. Most agents either ignore these drifts or make silent, destructive edits that break your production pipelines. This skill provides a controlled, evidence-backed maintenance framework to keep your agent library current without risking regressions. ## What it does - **Audit existing skills** by checking for stale citations, dead links, and outdated metadata against primary sources. - **Identify update triggers** based on official API changes, security advisories, or reproducible execution failures. - **Establish authoritative scope** to ensure edits stay within writable boundaries and preserve user-authored rules. - **Propose gated changes** through a structured approval process that includes source links, risk assessments, and rollback plans. - **Validate and compare** candidate versions against baselines to verify correctness and token efficiency before final deployment. ## How it works 1. **Identify a trigger** such as a manual maintenance request or a discovered API deprecation. 2. **Research primary sources** to verify claims and document the specific evidence justifying a change. 3. **Present a numbered proposal** detailing the exact files, behavioral differences, and regression risks for human approval. 4. **Apply non-destructive updates** using a narrow patch approach that synchronizes instructions, tests, and examples. 5. **Run structural validation** and compare against the previous version to ensure no safety or performance regressions occurred. ## Frameworks & tools This skill is framework-agnostic and works with any `SKILL.md` or YAML-based agent definition. It utilizes version control systems for rollbacks and relies on primary documentation sources for verification. ## Why this beats prompting it yourself Generic prompts often lead to "style churn" or silent breaking changes where the agent rewrites instructions without proof of improvement. This skill enforces a non-negotiable contract that requires evidence, baseline comparisons, and explicit human gates for every single write operation. ## Use cases - **Modernize agent libraries** when a platform like OpenAI or Anthropic releases new tool-calling schemas. - **Fix recurring failures** by identifying and documenting missing edge cases discovered during production traces. - **Maintain security hygiene** by updating skills in response to new library vulnerabilities or policy changes. - **Prevent instruction drift** by consolidating duplicated guidance and pruning contradictory rules across a multi-agent system. ## Known limitations Does not support unattended or autonomous rewriting. Requires access to version control or a backup mechanism for rollbacks. Performance is dependent on the quality of provided primary sources.

    Requires human-in-the-loop approval for all writes. Needs version control for rollbacks. Effectiveness depends on model reasoning quality for source interpretation.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Read Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill acts as a maintenance layer that audits your existing agent instructions for 'decay' caused by API changes or outdated logic, proposing verified, human-approved updates to ensure your agents stay functional and efficient.

    No, the skill operates under a 'gated' framework where it identifies necessary changes and provides evidence-backed proposals, but it never executes writes to your production environment without your explicit approval.

    It is framework-agnostic and compatible with any agent system that stores skills or instructions in standard formats like Markdown, YAML, or JSON, including those built on LangChain or custom orchestration layers.

    The package includes the core auditing logic, a structured proposal template for human review, validation scripts to compare new versions against baselines, and a step-by-step implementation guide.

    It requires access to your primary documentation sources (like API docs) and a version-controlled environment to facilitate safe rollbacks and track historical changes to your agent library.

    New in Prompt & Skill Engineering