SKILLEMALL.ai

AC cpa-irs-representation

Activate when: a client receives an IRS notice or letter; an examination opens or an IDR arrives; a client has unfiled returns, a balance owed, or a lien/levy pending; deciding whether to appeal an adjustment or collection action; scoping a representation engagement; user says 'IRS notice', 'audit letter', 'exam', 'IDR', 'levy', 'lien', 'back taxes', 'unfiled returns', 'Form 2848', 'appeal this', 'the IRS is after my client'. Do NOT activate when: the work is return preparation or review with no controversy; the matter is purely a state or local authority (different rules and timelines); facts suggest criminal exposure — stop and involve counsel. More: deciqai.com/c/cpa-irs-representation

ClawHub Agent Skills author: deciqAI v1.0.0 MIT-0 2 files body ≈ 4 010 tokens Open the sourceclawhub.ai analyzed 2 d ago

Activate when: a client receives an IRS notice or letter; an examination opens or an IDR arrives; a client has unfiled returns, a balance owed, or a lien/levy…

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureSecuritytype and topics are labelled automatically from the skill text
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
80
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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: 2. 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 51/100

    • 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
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 2 mutating operations with no state check
    • 70Execution cost. Instruction body is 4010 tokens
    • 100Tools and files. No external tools needed
    • 100Steps. 42 steps
    • 100Consistency. Name and required fields are in place
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 697: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 42 items

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

    External checks

    ClawHub: clean
    This is a non-executable guidance skill for handling IRS representation matters and its sensitive tax-data references fit that purpose.
    LLM: benign (high) · VirusTotal: · 16 Aug 2026