talont-org/smoke-task
src/autoskillit/skills_extended/smoke-task/SKILL.md
Execute an arbitrary prose task as a headless Claude session. For smoke-test pipeline use only.
$ install --global
skillsauthnpx skillsauth add talont-org/autoskillit smoke-taskInstall 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: May 9, 2026, 5:29 AM182.6s1 file scanned
SKILL.md
- name:
- smoke-task
- description:
- Execute an arbitrary prose task as a headless Claude session. For smoke-test pipeline use only.
- - matcher:
- *
- - type:
- command
- command:
- echo '[SKILL: smoke-task] Executing smoke task...'
- once:
- true
Smoke Task Skill
Execute an arbitrary prose task as a headless Claude session. For smoke-test pipeline use only.
Usage
/autoskillit:smoke-task <prose description of the task>
When to Use
Used exclusively by recipes/smoke-test.yaml to test that the headless runner can execute
arbitrary tasks and produce capturable outputs. Not for production pipeline use.
Critical Constraints
NEVER:
- Use this skill outside of smoke-test pipeline execution
- Ignore explicit output-line instructions (e.g.
key=value) — they must be emitted exactly
ALWAYS:
- Execute the prose task exactly as specified in the argument
- Output any requested key=value lines on their own lines for recipe capture
Instructions
Execute the task described in the argument provided to this skill invocation.
Complete the task exactly as specified. If the task asks you to output a specific line
(e.g. key=value), output it on its own line so it can be captured.
Related Skills
talont-org/write-recipe
development
VerifiedTrustedCommunity
Generate YAML recipes for .autoskillit/recipes/. Use when user says "make script skill", "generate script", "script a workflow", "write a script", "create a script", "new recipe", "write a pipeline", or when loaded by other skills for script formatting.
2SKILL.mdUpdated May 9, 2026
talont-org/vis-lens-uncertainty
data-ai
VerifiedTrustedCommunity
Create Uncertainty Representation visualization planning spec showing error bar definitions, distribution-aware alternatives, and multi-seed variance protocols. Statistical lens answering "How is uncertainty honestly represented?"
2SKILL.mdUpdated May 9, 2026
talont-org/vis-lens-temporal
data-ai
VerifiedTrustedCommunity
Create Temporal Dynamics visualization planning spec showing axis scaling (linear vs log), smoothing disclosure, epoch/step alignment, run aggregation (mean + variance bands), early-stopping markers, and wall-clock vs step-count x-axis. Temporal lens answering "Are training dynamics shown clearly and honestly?"
2SKILL.mdUpdated May 9, 2026
talont-org/vis-lens-story-arc
data-ai
VerifiedTrustedCommunity
Create Narrative Story Arc visualization planning spec showing visual consistency across the report (same color = same model everywhere), logical figure progression, redundant figure detection, and narrative dependency between figures. Narrative lens answering "Do the figures tell a coherent story across the report?"
2SKILL.mdUpdated May 9, 2026