skills/tech-assessment/SKILL.md
Generate tech assessment reports for mentor/mentee relationships tracking growth, goals, and action items over time. Use when the mentor says "tech-assessment", "/tech-assessment", or "tech assessment" and provides meeting notes, a transcript, or a summary. The skill produces an updated overview.md and a dated assessment.md archival file.
npx skillsauth add tmaffia/skills tech-assessmentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate progress reports from mentor-mentee meetings for technical assessment and continuous improvement.
Find the directory where tech assessment files are stored. This is typically a nested subfolder within the current working directory.
Search strategy:
Glob to search for **/overview.md files containing "Tech Assessment Overview" in their contentConfirmation prompt:
"Found tech assessments at
<path>. Is this correct, or provide the correct path."
Once located, store this path as the base for all assessment files.
Determine the mentee's name from context or the directory structure found in Step 1.
If unclear, ask explicitly:
"Who is this tech assessment for?"
The mentee name determines the subfolder structure within the assessments directory.
Before processing new input, check for existing files:
<mentee-name>/overview.md*-assessment.md fileIf no previous context exists, note this as the first assessment.
Analyze the provided notes/transcript/summary and extract:
Compare all goals and action items from previous context against today's date. Identify any that are overdue and flag them for follow-up with the mentor.
After parsing, check what's missing. If any of these cannot be inferred, prompt the mentor:
| Element | Prompt if Missing | |---------|-------------------| | Current focus | "What projects is {{mentee}} currently working on?" | | New learnings | "Any new techniques or tools discussed?" | | Goals | "What goals should we track?" | | Goal deadlines | "What is the deadline for {{goal}}?" | | Action items | "What action items were identified?" | | Action item deadlines | "What is the due date for {{action item}}?" | | Goal status | "How is {{mentee}} progressing toward each goal?" | | Overdue items | "The following items are overdue: {{list}}. What's the status? Should deadlines be adjusted?" |
Deadline requirement: Every goal and action item must have a deadline. Always ask for deadlines if not provided.
Be specific in prompts - reference the input provided to show what was found and what's missing.
overview.mdUpdate the living document using the template at assets/overview.md.
YYYY-MM-DD-assessment.mdCreate a dated archival file using the template at assets/assessment.md.
Key elements:
When creating new assessment files, organize within the assessments directory identified in Step 1:
<assessments-directory>/
└── <mentee-name>/
├── overview.md # Living document, update after each assessment
├── 2025-02-05-assessment.md # Archived assessments
├── 2025-02-12-assessment.md
└── ...
Always use lowercase mentee-name with hyphens for spaces (e.g., john-doe).
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.