AC parabolic-short-trade-planner
Screen US equities for parabolic exhaustion patterns and generate conditional pre-market short plans, then evaluate intraday trigger fires from live 5-min bars. Phase 1 daily 5-factor scorer (MA extension / acceleration / volume climax / range expansion / liquidity), Phase 2 per-candidate plans for ORL break / first-red 5-min / VWAP fail with explicit borrow / SSR / manual-confirmation gating, Phase 3 one-shot intraday FSM that detects trigger fires and resolves concrete share counts. Covers Phase 1 + Phase 2 + Phase 3.
Screen US equities for parabolic exhaustion patterns and generate conditional pre-market short plans, then evaluate intraday trigger fires from live 5-min bars.
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, progress reporting
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-privilegereferences/smoke_test_runbook.md:485Privilege escalation / world-writable permissions (detector / deny-list definition; documentation table row; security demo / example; test fixture / example file)| `state-dir permission denied` | The `state/` directory is owned by another user (e.g. root from a Docker run) | `sudo chown -R "$USER" state/` |
detectortabledemofixture
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 139, 148): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2074 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- -318 of 21 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 525: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 30 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (5 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.