AC construction-law
FIDIC (Red/Yellow/Silver), PSSCOC, SIA, and Singapore SOP Act toolkit. Generate notices, claims, EOT applications, and obligations registers. Computes statutory deadlines against eGazette-verified holiday data. Use when (1) analysing contract clauses, risk allocation, or obligations; (2) preparing or reviewing claims (delay, disruption, prolongation, EOT, loss & expense); (3) comparing contract forms or advising on procurement strategy; (4) drafting or reviewing notices, correspondence, or contract documents; (5) building obligations registers or notice calendars; (6) discussing dispute resolution (DAB/DAAB, adjudication, arbitration, mediation, CAB); (7) Singapore-specific construction law (SOP Act, BCA, SIArb); (8) MDB procurement frameworks (ADB, World Bank). NOT for: non-construction commercial contracts, pure property/real-estate conveyancing, or insurance law.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 0
✓ No critical or high findings
Files scanned: 32. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7665 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70Execution cost. Instruction body is 7665 tokens
- 100Steps. 189 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 20 top-level sections: this looks like several domains in one skill
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
- +3Description length 878: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -220 emoji in the instructions: noise for the model
- -31 of 13 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 58 headings
- +3Step-by-step instructions: 189 items
- +4Has examples (18 code blocks)
- +4Reference files are cited in the instructions (6 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.