- Home
- Skills
- Prompt & Skill Engineering
- self update skills
Works with the AI Agents you already use
self update skills
Maintain and modernize agent skills through evidence-backed audits and structured, human-approved updates.
Free
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 ## What it does - **Audit existing skills** by checking for stale citations, dead links, and outdated metadata against primary sources.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
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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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