AC task-files-explorer
MANDATORY when the user wants to replace, bypass, or stop relying on the platform "All files in task" preview popup; when they want a custom HTML page (index.html) served on the platform preview URL; when they want a persistent file dashboard/explorer for download/ and archive/ served by a custom dev.sh; or when they ask how to make scripts survive container restarts via the /start.sh boot hook. Deploys a zero-dependency Python explorer to 127.0.0.1:3000 (the upstream of the preview ingress) with search, type filters, sorting, inline preview (md, images, pdf, json, text) and per-task grouping parsed automatically from worklog.md. Auto-starts on every container boot, self-heals every 30 seconds via watcher. NOT for Next.js/web-app projects - the web dev server always owns port 3000.
MANDATORY when the user wants to replace, bypass, or stop relying on the platform "All files in task" preview popup; when they want a custom HTML page…
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-background-processassets/explorer.py:16Starts a background / autostarted process (string literal in code, not executed)Dijalankan sebagai double-fork orphan oleh explorer.sh (PPID=1, setsid) agar
code literal -
low Dangerous commands
cmd-background-processassets/explorer.sh:73Starts a background / autostarted process( setsid python3 "$PY" "$PORT" >> "$LOG" 2>&1 & )
-
low Dangerous commands
cmd-background-processSKILL.md:36Starts a background / autostarted processsatu-satunya cara daemon hidup terus = **double-fork orphan** (PPID=1 + setsid).
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 22 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1218 tokens
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 792: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.