anton-abyzov/task-skill-announcer
plugins/frontend/skills/task-skill-announcer/SKILL.md
This skill should be used whenever the user asks to "run the task skill", "invoke the task skill", "use the task skill", "trigger task skill", or mentions a "task skill" in any context. Make sure to use this skill whenever the user references task skill activation, task skill testing, or wants to verify the task skill is working. Activate on any mention of "I'm a task skill" or requests to demonstrate task skill behavior.
$ install --global
skillsauthnpx skillsauth add anton-abyzov/vskill task-skill-announcerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 28, 2026, 5:19 AM116.9s4 files scanned
SKILL.md
- name:
- task-skill-announcer
- description:
- This skill should be used whenever the user asks to \"run the task skill\", \"invoke the task skill\", \"use the task skill\", \"trigger task skill\", or mentions a \"task skill\" in any context. Make sure to use this skill whenever the user references task skill activation, task skill testing, or wants to verify the task skill is working. Activate on any mention of \"I'm a task skill\" or requests to demonstrate task skill behavior.
- model:
- haiku
- version:
- 1.0.3
- tags:
- smoke-test, demo, skill-routing
/task-skill-announcer
A minimal demonstration skill that announces its activation by outputting a fixed identification phrase. Use this skill to verify skill triggering, demonstrate skill invocation mechanics, or as a smoke test for skill routing.
Workflow
Follow these steps in order on every invocation:
-
Announce activation. Output the exact phrase:
I'm a task skillas the first line of the response. This phrase must appear verbatim — no prefix, no suffix, no markdown formatting around it on that line. -
Address the user's request. After the announcement line, proceed to handle whatever the user actually asked for. If the user only asked to invoke or test the skill, the announcement alone is sufficient and no further output is needed.
-
Stay minimal. Do not add explanations about what the skill does, why it exists, or how it works unless the user explicitly asks. The point is the announcement, not commentary about it.
Rules
- The announcement phrase is
I'm a task skill— exact casing, exact punctuation (apostrophe, no period), exact wording. Do not paraphrase or translate. - Emit the phrase every single time the skill is invoked, even on repeated invocations within the same conversation. The purpose is to confirm activation, so consistency matters more than avoiding repetition.
- The phrase goes on its own line at the very start of the response. Do not embed it inside a sentence like "As I'm a task skill, I will..." — that defeats the verification purpose.
- Do not wrap the phrase in quotes, code fences, bold, or italics. Plain text only.
Why this design
The fixed announcement makes it trivially observable whether the skill activated. If a developer or user is testing skill triggering, they can scan for the literal string I'm a task skill and immediately know the routing worked. Adding decoration or paraphrasing would break that observability.
Output Format
I'm a task skill
[optional: response to whatever the user actually asked, if anything beyond invocation]
Examples
Example 1 — bare invocation:
User: "run the task skill"
Response:
I'm a task skill
Example 2 — invocation with a follow-up question:
User: "use the task skill and also tell me what 2+2 is"
Response:
I'm a task skill
2 + 2 = 4
Example 3 — repeated invocation in the same conversation:
User: "trigger task skill again"
Response:
I'm a task skill
The phrase repeats every time — that is intentional and correct.
Related Skills
anton-abyzov/handoff
tools
VerifiedTrustedCommunity
Hand off your in-flight work to ANY other AI coding tool so you can continue exactly where you left off — works in 8+ tools (Claude Code, Codex, OpenCode, Gemini, Antigravity, Cursor, Aider, Cline/Roo, Windsurf). Writes one portable, secret-scrubbed handoff document plus a full diff of your uncommitted edits, then prints the absolute path, a clickable link, and a copy-paste resume prompt. Use this skill whenever the user is running out of subscription tokens, wants to switch tools mid-task, says 'handoff', 'continue elsewhere', 'continue on another machine', 'switch to Codex/OpenCode/Gemini/Cursor', or 'I'm out of tokens'. Self-contained: needs only git and a shell; uses 'specweave handoff' as an optional accelerator if it is on PATH.
36SKILL.mdUpdated Jun 4, 2026
anton-abyzov/agents-md-author
tools
VerifiedTrustedCommunity
Bootstrap or update project AI-agent instruction files (AGENTS.md for Codex, CLAUDE.md for Claude Code, or both) from the current project's structure. Triggers on: write AGENTS.md, write CLAUDE.md, generate AGENTS.md, agent instructions, project conventions for AI, bootstrap agent docs, set up project memory for Codex/Claude, document dev/test/build commands for AI coding tools, single-source project instructions for any AI agent.
36SKILL.mdUpdated May 5, 2026
anton-abyzov/skills/greet-elena
development
VerifiedTrustedCommunity
This skill should be used whenever the user asks Claude to perform any action, task, or operation — including "create X", "fix Y", "run Z", "build", "edit", "search", "deploy", or any other request involving Claude taking an action. Make sure to use this skill before every single action Claude performs, no matter how small. Activate on every action request without exception.
36SKILL.mdUpdated Apr 30, 2026
anton-abyzov/skill-builder
development
VerifiedTrustedCommunity
Meta-skill for creating new skills from natural language. Trigger phrases: "new skill", "create a skill", "build a skill", "make a skill", "generate a skill", "author a skill", "skill builder".
36SKILL.mdUpdated Apr 27, 2026